%% Genetic Programming Bibliography %%$Revision: 1.8081 $ $Date: 2024/11/29 19:51:44 $ %%Created by W.B.Langdon cs.ucl.ac.nl January 1995 %%Based on J.Koza's GP bibliography of 14 March 1994 %% To add references to your papers see %% ftp://ftp.cs.bham.ac.uk/pub/authors/W.B.Langdon/biblio/ %%optional @Proceedings{toc:2011:cec, key = "CEC 2011", title = "Proceedings of the 2011 IEEE Congress on Evolutionary Computation", year = "2011", month = jun, DOI = "doi:10.1109/CEC.2011.5949582", notes = "Also known as \cite{5949582}", } @Proceedings{cover:2010:MECHATRONIKA, key = "MECHATRONIKA, 2010", title = "13th International Symposium MECHATRONIKA, 2010", year = "2010", month = jun, URL = "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=5521207", notes = "Also known as \cite{5521207}", } @Article{tagkey1997126, title = "Genetic programming: Proceedings of the first annual conference 1996 : Edited by John R. Koza, David E. Goldberg, David B. Fogel and Rick L. Riolo. MIT Press, Cambridge, MA. (1996). 568 pages. \$75.00", journal = "Computers \& Mathematics with Applications", volume = "33", number = "5", pages = "126--127", year = "1997", ISSN = "0898-1221", DOI = "doi:10.1016/S0898-1221(97)00025-4", URL = "http://www.sciencedirect.com/science/article/B6TYJ-3SNTGM2-D/2/23afe396341b39baf74fcd29db315b46", key = "tagkey1997126", notes = "No author given. Contents listing of \cite{koza:gp96}", } @Article{tagkey1997129, title = "Advances in genetic programming, volume 2 : Edited by Peter Angeline and Kenneth Kinnear, Jr. MIT Press, Cambridge, MA. (1996). 538 pages. \$50.00", journal = "Computers \& Mathematics with Applications", volume = "33", number = "5", pages = "129", year = "1997", ISSN = "0898-1221", DOI = "doi:10.1016/S0898-1221(97)82933-1", URL = "http://www.sciencedirect.com/science/article/B6TYJ-3SNTGM2-T/2/4d3bcc2dda31e9aca679eba60ff95a3a", key = "tagkey1997129", size = "0.5 pages", notes = "Contents listing of \cite{book:1996:aigp2}. No author given. To get, try other articles on page 129", } @Article{tagkey1999291, title = "Advances in genetic programming, volume III : Edited by Lee Spector, William B. Langdon, Una-May O'Reilly and Peter J. Angeline. MIT Press, Cambridge, MA. (1999). 476 pages. \$55.00", journal = "Computers \& Mathematics with Applications", volume = "38", number = "11-12", pages = "291--291", year = "1999", ISSN = "0898-1221", DOI = "doi:10.1016/S0898-1221(99)91267-1", URL = "http://www.sciencedirect.com/science/article/B6TYJ-48778B1-3H/2/1d6f4728f10e14a24f4f28189d15f818", key = "tagkey1999291", notes = "Contents listing of \cite{spector:1999:aigp3}. No author given.", } @Article{tagkey1999132, title = "Genetic programming and data structures: Genetic programming + data STRUCTURES = automatic programming! : By W. B. Langdon. Kluwer Academic Publishers, Boston, MA. (1998). 278 pages. \$125.00. NLG 285.00, GBP 85.00", journal = "Computers \& Mathematics with Applications", volume = "37", number = "3", pages = "132--132", year = "1999", ISSN = "0898-1221", DOI = "doi:10.1016/S0898-1221(99)90375-9", DOI = "doi:10.1016/S0898-1221(99)90239-0", URL = "http://www.sciencedirect.com/science/article/B6TYJ-489YTT5-2T/2/13179f12104abafe66b36e402ef358d9", key = "tagkey1999132", notes = "Contents listing of \cite{langdon:book}. No author given.", } @Article{tagkey1995115, title = "Genetic programming II: Automatic discovery of reusable programs : By John R. Koza. MIT Press, Cambridge, MA. (1994). 746 pages. \$45.00", journal = "Computers \& Mathematics with Applications", volume = "29", number = "3", pages = "115--115", year = "1995", ISSN = "0898-1221", DOI = "doi:10.1016/0898-1221(95)90099-3", URL = "http://www.sciencedirect.com/science/article/B6TYJ-48F4PJH-H/2/bd467ac24453cb0b3f9dbbf15075bedb", key = "tagkey1995115", notes = "Contents listing of \cite{koza:gp2}. No author given.", } @Article{tagkey1999282, title = "Evolutionary algorithms in engineering and computer science: Recent advances in genetic algorithms, evolution strategies, evolutionary programming, genetic programming and industrial applications : Edited by K. Miettinen, P. Neittaanmaki, M. M. Makela and J. Periaux. John Wiley \& Sons, Ltd., Chichester. (1999). pounds60.00", journal = "Computers \& Mathematics with Applications", volume = "38", number = "11-12", pages = "282--282", year = "1999", ISSN = "0898-1221", DOI = "doi:10.1016/S0898-1221(99)91189-6", URL = "http://www.sciencedirect.com/science/article/B6TYJ-48778B1-24/2/ee28594e33abf3bd7c4a9fc997b98492", key = "tagkey1999282", } @Article{tagkey2002475, title = "Automated generation of robust error recovery logic in assembly systems using genetic programming : Cem M. Baydar, Kazuhiro Saitou, v20, n1, 2001, pp55-68", journal = "Journal of Manufacturing Systems", volume = "21", number = "6", pages = "475--476", year = "2002", ISSN = "0278-6125", DOI = "doi:10.1016/S0278-6125(02)80094-2", URL = "http://www.sciencedirect.com/science/article/B6VJD-4920DSC-1N/2/93bf79c7eb0d6ad94d169ed1b37ec77f", key = "tagkey2002475", notes = "Abstract of \cite{Baydar200155}", } @Misc{2018:MITtechreview, title = "Intelligent Machines Evolutionary algorithm outperforms deep-learning machines at video games", howpublished = "MIT Technolgy Review", key = "MIT Technolgy Review", year = "2018", month = "18 " # jul, keywords = "genetic algorithms, genetic programming", broken = "https://www.technologyreview.com/s/611568", size = "9 pages", abstract = "Neural networks have garnered all the headlines, but a much more powerful approach is waiting in the wings. by Emerging Technology from the arXiv July 18, 2018 Summary of https://arxiv.org/pdf/1806.05695 See instead \cite{Wilson:2018:GECCO}", notes = "No author given. another bit of electonic detritus?", } @Article{Sapienz:2018:sigevolution, title = "Evolutionary Algorithms for Software Testing in {Facebook}", journal = "SIGEVOlution", key = "SIGEVOlution", year = "2018", volume = "11", number = "2", pages = "7", month = "12 " # jul, keywords = "genetic algorithms, genetic programming, SBSE, mobile computing, smart phone", ISSN = "1931-8499", video_url = "https://www.youtube.com/watch?v=j3eV8NiWLg4", URL = "http://www.sigevolution.org/issues/SIGEVOlution1102.pdf", DOI = "doi:10.1145/3264700.3264702", size = "1 page", abstract = "Sapienz is an approach to Android testing that uses multi-objective evolutionary algorithms to automatically explore and optimise test sequences, minimising length, while simultaneously maximising coverage and fault revelation. It is in production now helping to improve the quality of Facebook software!", notes = "Yue Jia, Mark Harman, Ke Mao. Cites ISSTA 2016 \cite{mao:sapienz:16} https://doi.org/10.1145/2931037.2931054 https://github.com/Rhapsod/sapienz Sapienz Prototype (Out-of-date) MaJiCKe Sapienz Multiobjective Automated Android Testing", } @Misc{glasilo_1_16_ang, title = "Store Steel 165 years", howpublished = "Internal information magazine", key = "Store Steel", keywords = "genetic algorithms, genetic programming", URL = "http://www.store-steel.si/Data/InterniInformativniCasopis/glasilo_1_16_ang.pdf", size = "16 pages", notes = "a few paragraphs on Miha Kovacic. No author given.", } @Article{ababsa:2018:IJAC, author = "Tarek Ababsa and Noureddine Djedl and Yves Duthen", title = "Genetic programming-based self-reconfiguration planning for metamorphic robot", journal = "International Journal of Automation and Computing", year = "2018", volume = "15", number = "4", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/article/10.1007/s11633-016-1049-4", DOI = "doi:10.1007/s11633-016-1049-4", } @InProceedings{Ababsa:2022:ISNIB, author = "Tarek Ababsa", booktitle = "2022 International Symposium on iNnovative Informatics of Biskra (ISNIB)", title = "A {SIMD} Interpreter for Linear Genetic Programming", year = "2022", abstract = "Genetic programming (GP) has been applied as an automatic programming tool to solve various kinds of problems by genetically breeding a population of computer programs using biologically inspired operations. However, it is well known as a computationally demanding approach with a significant potential of parallelization. In this paper, we emphasize parallelizing the evaluation of genetic programs on Graphics Processing Unit (GPU). We used a compact representation for genotypes. This representation is a memory-efficient method that allows efficient evaluation of programs. Our implementation clearly distinguishes between an individual's genotype and phenotype. Thus, the individuals are represented as linear entities (arrays of 32 bits integers) that are decoded and expressed just like nonlinear entities (trees).", keywords = "genetic algorithms, genetic programming, linear genetic programming, GPU, Graphics, Automatic programming, Sociology, Graphics processing units, Arrays, Statistics, Parallel Processing, GPGPU, symbolic regression", DOI = "doi:10.1109/ISNIB57382.2022.10075819", month = dec, notes = "Also known as \cite{10075819}", } @InProceedings{Abarghouei:2009:SOCPAR, author = "Amir Atapour Abarghouei and Afshin Ghanizadeh and Saman Sinaie and Siti Mariyam Shamsuddin", title = "A Survey of Pattern Recognition Applications in Cancer Diagnosis", booktitle = "International Conference of Soft Computing and Pattern Recognition, SOCPAR '09", year = "2009", month = dec, pages = "448--453", keywords = "genetic algorithms, genetic programming, artificial neural networks, cancer diagnosis, image processing, medical images, pattern recognition applications, wavelet analysis, cancer, medical image processing, pattern recognition", DOI = "doi:10.1109/SoCPaR.2009.93", abstract = "In this paper, some of the image processing and pattern recognition methods that have been used on medical images for cancer diagnosis are reviewed. Previous studies on Artificial Neural Networks, Genetic Programming, and Wavelet Analysis are described with their working process and advantages. The definition of each method is provided in this study, and the acknowledgment is granted for previous related research activities.", notes = "Also known as \cite{5368648}", } @Article{ABBA:2020:JH, author = "S. I. Abba and Sinan Jasim Hadi and Saad Sh. Sammen and Sinan Q. Salih and R. A. Abdulkadir and Quoc Bao Pham and Zaher Mundher Yaseen", title = "Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination", journal = "Journal of Hydrology", volume = "587", pages = "124974", year = "2020", ISSN = "0022-1694", DOI = "doi:10.1016/j.jhydrol.2020.124974", URL = "http://www.sciencedirect.com/science/article/pii/S0022169420304340", keywords = "genetic algorithms, genetic programming, Water quality index, Watershed management, Extreme Gradient Boosting, Extreme Learning Machine, Kinta River", abstract = "Anthropogenic activities affect the water bodies and result in a drastic reduction of river water quality (WQ). The development of a reliable intelligent model for evaluating the suitability of water remains a challenging task facing hydro-environmental engineers. The current study is investigated the applicability of Extreme Gradient Boosting (XGB) and Genetic Programming (GP) in obtaining feature importance, and then abstracted input variables were imposed into the predictive model (the Extreme Learning Machine (ELM)) for the prediction of water quality index (WQI). The stand-alone modeling schema is compared with the proposed hybrid models where the optimum variables are supplied into the GP, XGB, linear regression (LR), stepwise linear regression (SWLR) and ELM models. The WQ data is obtained from the Department of Environment (DoE) (Malaysia), and results are evaluated in terms of determination coefficient (R2) and root mean square error (RMSE). The results demonstrated that the hybrid GPELM and XGBELM models outperformed the standalone GP, XGB, and ELM models for the prediction of WQI at Kinta River basin. A comparison of the hybrid models showed that the predictive skill of GPELM (RMSE = 3.441 training and RMSE = 3.484 testing) over XGBELM improving the accuracy by decreasing the values of RMSE by 5percent and 9percent for training and testing, respectively with regards to XGBELM (RMSE = 3.606 training and RMSE = 3.816 testing). Although regressions are often proposed as reference models (LR and SWLR), when combined with computational intelligence, they still provide satisfactory results in this study. The proposed hybrid GPELM and XGBELM models have improved the prediction accuracy with minimum number of input variables and can therefore serve as reliable predictive tools for WQI at Kinta River basin", } @Article{journals/iajit/AbbasiSA14, author = "Almas Abbasi and Woo Chaw Seng and Imran Shafiq Ahmad", title = "Multi Block based Image Watermarking in Wavelet Domain Using Genetic Programming", journal = "The International Arab Journal of Information Technology", year = "2014", number = "6", volume = "11", pages = "582--589", keywords = "genetic algorithms, genetic programming, Robust watermark, wavelet domain, digital watermarking, HVS", bibdate = "2014-11-03", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/iajit/iajit11.html#AbbasiSA14", URL = "http://ccis2k.org/iajit/?option=com_content&task=blogcategory&id=94&Itemid=364", URL = "https://iajit.org/PDF/vol.11,no.6/6348.pdf", URL = "https://www.semanticscholar.org/paper/Multi-block-based-image-watermarking-in-wavelet-do-Abbasi-Seng/f7172a8a0b6d15ddedf81fc5a98117ff2078a89c", size = "8 pages", abstract = "The increased use of the Internet in sharing and distribution of digital data makes it is very difficult to maintain copyright and ownership of data. Digital watermarking offers a method for authentication and copyright protection. We propose a blind, still image, Genetic Programming (GP) based robust watermark scheme for copyright protection. In this scheme, pseudorandom sequence of real number is used as watermark. It is embedded into perceptually significant blocks of vertical and horizontal sub-band in wavelet domain to achieve robustness. GP is used to structure the watermark for improved imperceptibility by considering the Human Visual System (HVS) characteristics such as luminance sensitivity and self and neighbourhood contrast masking. We also present a GP function which determines the optimal watermark strength for selected coefficients irrespective of the block size. Watermark detection is performed using correlation. Our experiments show that in proposed scheme the watermark resists image processing attack, noise attack, geometric attack and cascading attack. We compare our proposed technique with other two genetic perceptual model based techniques. Comparison results show that our multiblock based technique is approximately 5percent, and 23percent more robust, then the other two compared techniques.", } @InProceedings{DBLP:conf/ssci/AbbasiAW21, author = "Muhammad Shabbir Abbasi and Harith Al-Sahaf and Ian Welch", title = "Automated Behavior-based Malice Scoring of Ransomware Using Genetic Programming", booktitle = "IEEE Symposium Series on Computational Intelligence, SSCI 2021", pages = "1--8", publisher = "IEEE", year = "2021", month = dec # " 5-7", address = "Orlando, FL, USA", keywords = "genetic algorithms, genetic programming Symbolic regression, ransomware, malice scoring", isbn13 = "978-1-7281-9049-5", timestamp = "Thu, 03 Feb 2022 09:28:31 +0100", biburl = "https://dblp.org/rec/conf/ssci/AbbasiAW21.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://doi.org/10.1109/SSCI50451.2021.9660009", DOI = "doi:10.1109/SSCI50451.2021.9660009", size = "8 pages", abstract = "Malice or severity scoring models are a technique for detection of maliciousness. A few ransom-ware detection studies use malice scoring models for detection of ransomware-like behaviour. These models rely on the weighted sum of some manually chosen features and their weights by a domain expert. To automate the modelling of malice scoring for ransomware detection, we propose a method based on Genetic Programming (GP) that automatically evolves a behavior-based malice scoring model by selecting appropriate features and functions from the input feature and operator sets. The experimental results show that the best-evolved model correctly assigned a malice score, below the threshold value to over 85percent of the unseen goodware instances, and over the threshold value to more than 99percent of the unseen ransomware instances.", } @Article{Abbaspour:2013:WSE, author = "Akram Abbaspour and Davood Farsadizadeh and Mohammad Ali Ghorbani", title = "Estimation of hydraulic jump on corrugated bed using artificial neural networks and genetic programming", journal = "Water Science and Engineering", volume = "6", number = "2", pages = "189--198", year = "2013", ISSN = "1674-2370", DOI = "doi:10.3882/j.issn.1674-2370.2013.02.007", URL = "http://www.sciencedirect.com/science/article/pii/S1674237015302362", abstract = "Artificial neural networks (ANNs) and genetic programming (GP) have recently been used for the estimation of hydraulic data. In this study, they were used as alternative tools to estimate the characteristics of hydraulic jumps, such as the free surface location and energy dissipation. The dimensionless hydraulic parameters, including jump depth, jump length, and energy dissipation, were determined as functions of the Froude number and the height and length of corrugations. The estimations of the ANN and GP models were found to be in good agreement with the measured data. The results of the ANN model were compared with those of the GP model, showing that the proposed ANN models are much more accurate than the GP models.", keywords = "genetic algorithms, genetic programming, artificial neural networks, corrugated bed, Froude number, hydraulic jump", } @InProceedings{Abbass:2002:WCCI, publisher_address = "Piscataway, NJ, USA", author = "H. Abbass and N. X. Hoai and R. I. (Bob) McKay", booktitle = "Proceedings, 2002 World Congress on Computational Intelligence", DOI = "doi:10.1109/CEC.2002.1004490", notes = "Refereed International Conference Papers", pages = "1654--1666", publisher = "IEEE Press", title = "AntTAG: A New Method to Compose Computer Programs Using Colonies of Ants", URL = "http://sc.snu.ac.kr/PAPERS/TAGACOcec02.pdf", volume = "2", year = "2002", keywords = "genetic algorithms, genetic programming", size = "6 pages", abstract = "Genetic Programming (GP) plays the primary role for the discovery of programs through evolving the program's set of parse trees. In this paper, we present a new technique for constructing programs through Ant Colony Optimisation (ACO) using the tree adjunct grammar (TAG) formalism. We call the method AntTAG and we show that the results are very promising.", } @InProceedings{abbattista:1999:SAGAACS, author = "Fabio Abbattista and Valeria Carofiglio and Mario Koppen", title = "Scout Algorithms and Genetic Algorithms: A Comparative Study", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "769", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems, poster papers", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-803.pdf", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-803.ps", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InProceedings{abbod2007, author = "Maysam F. Abbod and M. Mahfouf and D. A. Linkens and C. M. Sellars", title = "Evolutionary Computing for Metals Properties Modelling", booktitle = "THERMEC 2006", year = "2006", volume = "539", pages = "2449--2454", series = "Materials Science Forum", address = "Vancouver", publisher_address = "Switzerland", month = jul # " 4-8", publisher = "Trans Tech Publications", keywords = "genetic algorithms, genetic programming, strain, alloy materials, modeling, material property, stress", ISSN = "1662-9752", annote = "The Pennsylvania State University CiteSeerX Archives", bibsource = "OAI-PMH server at citeseerx.ist.psu.edu", language = "en", oai = "oai:CiteSeerX.psu:10.1.1.1011.6271", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1011.6271", URL = "http://www.scientific.net/MSF.539-543.2449.pdf", DOI = "doi:10.4028/www.scientific.net/MSF.539-543.2449", size = "6 pages", abstract = "During the last decade Genetic Programming (GP) has emerged as an efficient methodology for teaching computers how to program themselves. This paper presents research work which uses GP for developing mathematical equations for the response surfaces that have been generated using hybrid modelling techniques for predicting the properties of materials under hot deformation. Collected data from the literature and experimental work on aluminium are used as the initial training data for the GP to develop the mathematical models under different deformation conditions and compositions.", notes = "Published Feb 2007 in Materials Science Forum ?", } @InProceedings{Abbona:2020:CEC, author = "Francesca Abbona and Leonardo Vanneschi and Marco Bona and Mario Giacobini", title = "A {GP} Approach for Precision Farming", booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC 2020", year = "2020", editor = "Yaochu Jin", pages = "paper id24248", address = "internet", month = "19-24 " # jul, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, Cows, Precision Livestock Farming, PLF, Cattle Breeding, Piedmontese Bovines", isbn13 = "978-1-7281-6929-3", DOI = "doi:10.1109/CEC48606.2020.9185637", size = "8 pages", abstract = "Livestock is increasingly treated not just as food containers, but as animals that can be susceptible to stress and diseases, affecting, therefore, the production of offspring and the performance of the farm. The breeder needs a simple and useful tool to make the best decisions for his farm, as well as being able to objectively check whether the choices and investments made have improved or worsened its performance. The amount of data is huge but often dispersive: it is therefore essential to provide the farmer with a clear and comprehensible solution, that represents an additional investment. This research proposes a genetic programming approach to predict the yearly number of weaned calves per cow of a farm, namely the measure of its performance. To investigate the efficiency of genetic programming in such a problem, a dataset composed by observations on representative Piedmontese breedings was used. The results show that the algorithm is appropriate, and can perform an implicit feature selection, highlighting important variables and leading to simple and interpretable models.", notes = "Cow calves, north itally. ANABORAPI. perinatal mortality death during weaning (60 days). GPlab Matlab. Kruskal-Wallis stats test. Natural v. artificial insemination. 2017, 2018 data. Crossover, mutation, shrink mutaion swap mutation. mydivide Herd size. GP8 comphrensible evolved model. Time between calve birth and next calf birth. Department of Veterinary Sciences, University of Torino. ANABORAPI, Associazione Nazionale Allevatori Bovini Razza Piemontese https://wcci2020.org/ Also known as \cite{9185637}", } @Article{ABBONA:2020:LS, author = "Francesca Abbona and Leonardo Vanneschi and Marco Bona and Mario Giacobini", title = "Towards modelling beef cattle management with Genetic Programming", journal = "Livestock Science", year = "2020", volume = "241", pages = "104205", keywords = "genetic algorithms, genetic programming, Precision livestock farming, Evolutionary algorithms, Machine learning, Cattle breeding, Piemontese bovines", ISSN = "1871-1413", URL = "https://iris.unito.it/retrieve/e27ce430-63b3-2581-e053-d805fe0acbaa/Abbona2020_LS_OA.pdf", URL = "http://www.sciencedirect.com/science/article/pii/S1871141320302481", DOI = "doi:10.1016/j.livsci.2020.104205", abstract = "Among the Italian Piemontese Beef Breedings, the yearly production of calves weaned per cow, that is the calves that survive during the period of 60 days following birth, is identified as the main target expressing the performance of a farm. modeling farm dynamics in order to predict the value of this parameter is a possible solution to investigate and highlight breeding strengths, and to find alternatives to penalizing factors. The identification of such variables is a complex but solvable task, since the amount of recorded data among livestock is nowadays huge and manageable through Machine Learning techniques. Besides, the evaluation of the effectiveness of the type of management allows the breeder to consolidate the ongoing processes or, on the contrary, to adopt new management strategies. To solve this problem, we propose a Genetic Programming approach, a white-box technique suitable for big data management, and with an intrinsic ability to select important variables, providing simple models. The most frequent variables encapsulated in the models built by Genetic Programming are highlighted, and their zoological significance is investigated a posteriori, evaluating the performance of the prediction models. Moreover, two of the final expressions selected only three variables among the 48 given in input, one of which is the best performing among GP models. The expressions were then analyzed in order to propose a zootechnical interpretation of the equations. Comparisons with other common techniques, including also black-box methods, are performed, in order to evaluate the performance of different type of methods in terms of accuracy and generalization ability. The approach entailed constructive and helpful considerations to the addressed task, confirming its key-role in the zootechnical field, especially in the beef breeding management", } @Article{abbona:2022:AS, author = "Francesca Abbona and Leonardo Vanneschi and Mario Giacobini", title = "Towards a Vectorial Approach to Predict Beef Farm Performance", journal = "Applied Sciences", year = "2022", volume = "12", number = "3", keywords = "genetic algorithms, genetic programming", ISSN = "2076-3417", URL = "https://www.mdpi.com/2076-3417/12/3/1137", DOI = "doi:10.3390/app12031137", abstract = "Accurate livestock management can be achieved by means of predictive models. Critical factors affecting the welfare of intensive beef cattle husbandry systems can be difficult to be detected, and Machine Learning appears as a promising approach to investigate the hundreds of variables and temporal patterns lying in the data. In this article, we explore the use of Genetic Programming (GP) to build a predictive model for the performance of Piemontese beef cattle farms. In particular, we investigate the use of vectorial GP, a recently developed variant of GP, that is particularly suitable to manage data in a vectorial form. The experiments conducted on the data from 2014 to 2018 confirm that vectorial GP can outperform not only the standard version of GP but also a number of state-of-the-art Machine Learning methods, such as k-Nearest Neighbors, Generalized Linear Models, feed-forward Neural Networks, and long- and short-term memory Recurrent Neural Networks, both in terms of accuracy and generalizability. Moreover, the intrinsic ability of GP in performing an automatic feature selection, while generating interpretable predictive models, allows highlighting the main elements influencing the breeding performance.", notes = "also known as \cite{app12031137}", } @InProceedings{aicsu-91:abbot, author = "R. J. Abbott", title = "Niches as a GA divide-and-conquer strategy", booktitle = "Proceedings of the Second Annual AI Symposium for the California State University", year = "1991", editor = "Art Chapman and Leonard Myers", pages = "133--136", publisher = "California State University", keywords = "genetic algorithms, genetic programming", } @InProceedings{abbott:2003:OOGP, author = "Russell J. Abbott", title = "Object-Oriented Genetic Programming, An Initial Implementation", booktitle = "Proceedings of the Sixth International Conference on Computational Intelligence and Natural Computing", year = "2003", address = "Embassy Suites Hotel and Conference Center, Cary, North Carolina USA", month = sep # " 26-30", keywords = "genetic algorithms, genetic programming, object-oriented, STGP", URL = "http://abbott.calstatela.edu/PapersAndTalks/OOGP.pdf", size = "4 pages", abstract = "This paper describes oogp, an object-oriented genetic programming system. Oogp provides traditional genetic programming capabilities in an object-oriented framework. Among the advantages of object-oriented genetic programming are: (a) strong typing, (b) availability of existing class libraries for inclusion in generated programs, and (c) straightforward extensibility to include features such as iteration as object-oriented methods. Oogp is written in Java and makes extensive use of Java's reflection capabilities. Oogp includes a relatively straightforward but apparently innovative simplification capability.", notes = "http://axon.cs.byu.edu/Dan/cinc03.html/index.html/ Broken Jan 2013 http://www.ee.duke.edu/JCIS/ parity Assignment-Stmt, Block-Stmt, If-Stmt, and While-Stmt Automatic simplification {"}A limit may be placed on the number of steps allowed. When exceeded, an ExcessiveStepsException is thrown{"} Iteration cites \cite{HPL-2001-327}.", } @InProceedings{abbott:2003:MLMTA, author = "Russ Abbott and Jiang Guo and Behzad Parviz", title = "Guided Genetic Programming", booktitle = "The 2003 International Conference on Machine Learning; Models, Technologies and Applications (MLMTA'03)", year = "2003", address = "las Vegas", month = "23-26 " # jun, publisher = "CSREA Press", keywords = "genetic algorithms, genetic programming, guided genetic programming", URL = "http://abbott.calstatela.edu/PapersAndTalks/Guided%20Genetic%20Programming.pdf", size = "7 pages", abstract = "We argue that genetic programming has not made good on its promise to generate computer programs automatically. It then describes an approach that would allow that promise to be fulfilled by running a genetic programming engine under human guidance.", notes = "http://www.ashland.edu/~iajwa/conferences/2003/MLMTA/ Oogp Java. Sort (all ArrayList methods and iterate() loop and insertAsc()). Guided GP 3 populations (coevolution) {"}The user contributes...a top-down analysis{"}. {"}Allowing a user to suggest building blocks may be a reasonable compromise{"}. Cites \cite{langdon:book} \cite{HPL-2001-327} \cite{ppsn92:oReilly} \cite{icga93:kinnear}", } @InProceedings{DBLP:conf/icai/AbbottPS04, author = "Russ Abbott and Behzad Parviz and Chengyu Sun", title = "Genetic Programming Reconsidered", year = "2004", pages = "1113--1116", bibsource = "DBLP, http://dblp.uni-trier.de", editor = "Hamid R. Arabnia and Youngsong Mun", publisher = "CSREA Press", booktitle = "Proceedings of the International Conference on Artificial Intelligence, IC-AI '04, Volume 2 {\&} Proceedings of the International Conference on Machine Learning; Models, Technologies {\&} Applications, MLMTA '04", volume = "2", address = "Las Vegas, Nevada, USA", month = jun # " 21-24", keywords = "genetic algorithms, genetic programming, evolutionary pathway, fitness function, teleological evolution, adaptive evolution", ISBN = "1-932415-32-7", URL = "http://abbott.calstatela.edu/PapersAndTalks/GeneticProgrammingReconsidered.pdf", URL = "https://dblp.org/rec/conf/icai/AbbottPS04.html?view=bibtex", size = "4 pages", abstract = "Even though the Genetic Programming (GP) mechanism is capable of evolving any computable function, the means through which it does so is inherently flawed: the user must provide the GP engine with an evolutionary pathway toward a solution. Hence Genetic Programming is problematic as a mechanism for generating creative solutions to specific problems.", notes = "sort, fitness function cheat ", } @Article{abdel-kader:2022:Infrastructures, author = "Mohamed Y. Abdel-Kader and Ahmed M. Ebid and Kennedy C. Onyelowe and Ibrahim M. Mahdi and Ibrahim Abdel-Rasheed", title = "{(AI)} in Infrastructure Projects-Gap Study", journal = "Infrastructures", year = "2022", volume = "7", number = "10", pages = "Article No. 137", keywords = "genetic algorithms, genetic programming", ISSN = "2412-3811", URL = "https://www.mdpi.com/2412-3811/7/10/137", DOI = "doi:10.3390/infrastructures7100137", abstract = "Infrastructure projects are usually complicated, expensive, long-term mega projects; accordingly, they are the type of projects that most need optimisation in the design, construction and operation stages. A great deal of earlier research was carried out to optimise the performance of infrastructure projects using traditional management techniques. Recently, artificial intelligence (AI) techniques were implemented in infrastructure projects to improve their performance and efficiency due to their ability to deal with fuzzy, incomplete, inaccurate and distorted data. The aim of this research is to collect, classify, analyse and review all of the available previous research related to implementing AI techniques in infrastructure projects to figure out the gaps in the previous studies and the recent trends in this research area. A total of 159 studies were collected since the beginning of the 1990s until the end of 2021. This database was classified based on publishing date, infrastructure subject and the used AI technique. The results of this study show that implementing AI techniques in infrastructure projects is rapidly increasing. They also indicate that transportation is the first and the most AI-using project and that both artificial neural networks (ANN) and particle swarm optimisation (PSO) are the most implemented techniques in infrastructure projects. Finally, the study presented some opportunities for farther research, especially in natural gas projects.", notes = "also known as \cite{infrastructures7100137}", } @Article{ABDELALEEM:2022:tws, author = "Basem H. AbdelAleem and Mohamed K. Ismail and May Haggag and Wael El-Dakhakhni and Assem A. A. Hassan", title = "Interpretable soft computing predictions of elastic shear buckling in tapered steel plate girders", journal = "Thin-Walled Structures", volume = "176", pages = "109313", year = "2022", ISSN = "0263-8231", DOI = "doi:10.1016/j.tws.2022.109313", URL = "https://www.sciencedirect.com/science/article/pii/S026382312200235X", keywords = "genetic algorithms, genetic programming, Data-driven models, Elastic shear buckling strength, Multi-gene genetic programming, Variable importance, Partial dependence plots, Tapered end web panel", abstract = "The complexity of the shear buckling in tapered plate girders has motivated researchers to conduct experimental and numerical investigations to understand the underlying mechanisms controlling such phenomenon, and subsequently develop related design-oriented expressions. However, existing predictive models have been developed and validated using limited datasets and/or traditional regression techniques-restricting both the model utility, when considering a wider range of design parameters, and the model generalizability, due to associated uncertainties. To address these issues, the present study employed a powerful soft computing technique-multi-gene genetic programming (MGGP), to develop design expressions to predict the elastic shear buckling strength of tapered end plate girder web panels. A dataset of 427 experimental and experimentally validated numerical results was used in training, validating, and testing the developed MGGP models. Guided by mechanics and findings from previous studies, the key parameters controlling the strength were identified, and MGGP were employed to reveal the interdependence between such parameters and subsequently develop interpretable predictive models. The prediction accuracy of the developed models was evaluated against that of other existing models using various statistical measures. Several filter and embedded variable importance techniques were used to rank the model input parameters according to their significance in predicting the elastic shear buckling strength. These techniques include the variable importance random forest and the relative influence gradient boosting techniques. Moreover, partial dependence plots were employed to explore the effect of the input variables on the strength. The results obtained from this study demonstrated the robustness of the developed MGGP expression for predicting the elastic shear buckling strength of tapered plate girder end web panel. The developed model also exhibited a superior prediction accuracy and generalizability compared to currently existing ones. Furthermore, the developed partial dependence plots facilitated interpreting the influence of all input variables on the predicted elastic shear buckling strength", } @InProceedings{Abdelaziz:2012:SEMCCO, author = "Almoataz Y. Abdelaziz and S. F. Mekhamer and H. M. Khattab and M. L. A. Badr and Bijaya Ketan Panigrahi", title = "Gene Expression Programming Algorithm for Transient Security Classification", booktitle = "Proceedings of the Third International Conference on Swarm, Evolutionary, and Memetic Computing, SEMCCO 2012", year = "2012", editor = "Bijaya Ketan Panigrahi and Swagatam Das and Ponnuthurai Nagaratnam Suganthan and Pradipta Kumar Nanda", volume = "7677", series = "Lecture Notes in Computer Science", pages = "406--416", address = "Bhubaneswar, India", month = dec # " 20-22", publisher = "Springer", keywords = "genetic algorithms, genetic programming, gene expression programming", isbn13 = "978-3-642-35379-6", DOI = "doi:10.1007/978-3-642-35380-2_48", bibsource = "OAI-PMH server at works.bepress.com", oai = "oai:works.bepress.com:almoataz_abdelaziz-1083", URL = "http://works.bepress.com/almoataz_abdelaziz/42", size = "11 pages", abstract = "In this paper, a gene expression programming (GEP) based algorithm is implemented for power system transient security classification. The GEP algorithms as evolutionary algorithms for pattern classification have recently received attention for classification problems because they can perform global searches. The proposed methodology applies the GEP for the first time in transient security assessment and classification problems of power systems. The proposed algorithm is examined using different IEEE standard test systems. Power system three phase short circuit contingency has been used to test the proposed algorithm. The algorithm checks the static security status of the power system then classifies the transient security of the power system as secure or not secure. Performance of the algorithm is compared with other neural network based classification algorithms to show its superiority for transient security classification.", } @Article{Abdelbaky:2018:IJACSA, author = "Ibrahim Z. Abdelbaky and Ahmed F. Al-Sadek and Amr A. Badr", title = "Applying Machine Learning Techniques for Classifying Cyclin-Dependent Kinase Inhibitors", journal = "International Journal of Advanced Computer Science and Applications", year = "2018", number = "11", volume = "9", pages = "229--235", keywords = "genetic algorithms, genetic programming, cdk inhibitors, random forest classification", publisher = "The Science and Information (SAI) Organization", bibsource = "OAI-PMH server at thesai.org", language = "eng", oai = "oai:thesai.org:10.14569/IJACSA.2018.091132", URL = "http://thesai.org/Downloads/Volume9No11/Paper_32-Applying_Machine_Learning_Techniques.pdf", DOI = "doi:10.14569/IJACSA.2018.091132", size = "7 pages", abstract = "The importance of protein kinases made them a target for many drug design studies. They play an essential role in cell cycle development and many other biological processes. Kinases are divided into different subfamilies according to the type and mode of their enzymatic activity. Computational studies targeting kinase inhibitors identification is widely considered for modelling kinase-inhibitor. This modelling is expected to help in solving the selectivity problem arising from the high similarity between kinases and their binding profiles. In this study, we explore the ability of two machine-learning techniques in classifying compounds as inhibitors or non-inhibitors for two members of the cyclin-dependent kinases as a subfamily of protein kinases. Random forest and genetic programming were used to classify CDK5 and CDK2 kinases inhibitors. This classification is based on calculated values of chemical descriptors. In addition, the response of the classifiers to adding prior information about compounds promiscuity was investigated. The results from each classifier for the datasets were analysed by calculating different accuracy measures and metrics. Confusion matrices, accuracy, ROC curves, AUC values, F1 scores, and Matthews correlation, were obtained for the outputs. The analysis of these accuracy measures showed a better performance for the RF classifier in most of the cases. In addition, the results show that promiscuity information improves the classification accuracy, but its significant effect was notably clear with GP classifiers.", } @InProceedings{Abdelbar:aspgp03, author = "Ashraf M. Abdelbar and Sherif Ragab and Sara Mitri", title = "Applying Co-Evolutionary Particle Swam Optimization to the Egyptian Board Game Seega", booktitle = "Proceedings of The First Asian-Pacific Workshop on Genetic Programming", year = "2003", editor = "Sung-Bae Cho and Nguyen Xuan Hoai and Yin Shan", pages = "9--15", address = "Rydges (lakeside) Hotel, Canberra, Australia", month = "8 " # dec, keywords = "Particle Swarm Optimisation, Co-evolution, Game", ISBN = "0-9751724-0-9", URL = "http://infoscience.epfl.ch/record/90539/", URL = "http://infoscience.epfl.ch/record/90539/files/abdelbar03applyingParticle.pdf", abstract = "Seega is an ancient Egyptian two-phase board game that, in certain aspects, is more difficult than chess. The two-player game is played on either a 5 x 5, 7 x 7, or 9 x 9 board. In the first and more difficult phase of the game, players take turns placing one disk each on the board until the board contains only one empty cell. In the second phase players take turns moving disks of their colour; a disk that becomes surrounded by disks of the opposite color is captured and removed from the board. We have developed a Seega program that employs co-evolutionary particle swarm optimisation in the generation of feature evaluation scores. Two separate swarms are used to evolve White players and Black players, respectively; each particle represents feature weights for use in the position evaluation. Experimental results are presented and the performance of the full game engine is discussed.", notes = "PSO, Not GP \cite{aspgp03}", } @InProceedings{Abdelbari:2017:ICCMS, author = "Hassan Abdelbari and Kamran Shafi", title = "A Genetic Programming Ensemble Method for Learning Dynamical System Models", booktitle = "Proceedings of the 8th International Conference on Computer Modeling and Simulation", year = "2017", pages = "47--51", address = "Canberra, Australia", publisher = "ACM", keywords = "genetic algorithms, genetic programming, complex dynamical systems, modelling and simulation, symbolic regression", isbn13 = "978-1-4503-4816-4", URL = "http://doi.acm.org/10.1145/3036331.3036336", DOI = "doi:10.1145/3036331.3036336", acmid = "3036336", abstract = "Modelling complex dynamical systems plays a crucial role to understand several phenomena in different domains such as physics, engineering, biology and social sciences. In this paper, a genetic programming ensemble method is proposed to learn complex dynamical systems underlying mathematical models, represented as differential equations, from system time series observations. The proposed method relies on decomposing the modelling space based on given variable dependencies. An ensemble of learners is then applied in this decomposed space and their output is combined to generate the final model. Two examples of complex dynamical systems are used to test the performance of the proposed methodology where the standard genetic programming method has struggled to find matching model equations. The empirical results show the effectiveness of the proposed methodology in learning closely matching structure of almost all system equations.", notes = "conf/iccms/AbdelbariS17", } @Article{abdelbari:2019:Systems, author = "Hassan Abdelbari and Kamran Shafi", title = "A System Dynamics Modeling Support System Based on Computational Intelligence", journal = "Systems", year = "2019", volume = "7", number = "4", keywords = "genetic algorithms, genetic programming", ISSN = "2079-8954", URL = "https://www.mdpi.com/2079-8954/7/4/47", DOI = "doi:10.3390/systems7040047", abstract = "System dynamics (SD) is a complex systems modelling and simulation approach with wide ranging applications in various science and engineering disciplines. While subject matter experts lead most of the model building, recent advances have attempted to bring system dynamics closer to fast growing fields such as data sciences. This may prove promising for the development of novel support methods that augment human cognition and improve efficiencies in the model building process. A few different directions have been explored recently to support individual modelling stages, such as the generation of model structure, model calibration and policy optimisation. However, an integrated approach that supports across the board modelling process is still missing. In this paper, a prototype integrated modelling support system is presented for the purpose of supporting the modellers at each stage of the process. The proposed support system facilitates data-driven inferring of causal loop diagrams (CLDs), stock-flow diagrams (SFDs), model equations and the estimation of model parameters using computational intelligence (CI) techniques. The ultimate goal of the proposed system is to support the construction of complex models, where the human power is not enough. With this goal in mind, we demonstrate the working and utility of the proposed support system. We have used two well-known synthetic reality case studies with small models from the system dynamics literature, in order to verify the support system performance. The experimental results showed the effectiveness of the proposed support system to infer close model structures to target models directly from system time-series observations. Future work will focus on improving the support system so that it can generate complex models on a large scale.", notes = "also known as \cite{systems7040047}", } @Article{Abdelmalek:2009:JAMDS, title = "Selecting the Best Forecasting-Implied Volatility Model Using Genetic Programming", author = "Wafa Abdelmalek and Sana {Ben Hamida} and Fathi Abid", journal = "Journal of Applied Mathematics and Decision Sciences", year = "2009", publisher = "Hindawi Publishing Corporation", keywords = "genetic algorithms, genetic programming", URL = "http://downloads.hindawi.com/journals/ads/2009/179230.pdf", URL = "http://www.hindawi.com/journals/ads/2009/179230.html", DOI = "doi:10.1155/2009/179230", ISSN = "11739126", bibsource = "OAI-PMH server at www.doaj.org", language = "eng", oai = "oai:doaj-articles:b3bc3b339d2f713819080ff9b253312a", abstract = "The volatility is a crucial variable in option pricing and hedging strategies. The aim of this paper is to provide some initial evidence of the empirical relevance of genetic programming to volatility's forecasting. By using real data from S\&P500 index options, the genetic programming's ability to forecast Black and Scholes-implied volatility is compared between time series samples and moneyness-time to maturity classes. Total and out-of-sample mean squared errors are used as forecasting's performance measures. Comparisons reveal that the time series model seems to be more accurate in forecasting-implied volatility than moneyness time to maturity models. Overall, results are strongly encouraging and suggest that the genetic programming approach works well in solving financial problems.", notes = "Article ID 179230 1RU: MODESFI, Faculty of Economics and Business, Road of the Airport Km 4, 3018 Sfax, Tunisia 2Laboratory of Intelligent IT Engineering, Higher School of Technology and Computer Science, 2035 Charguia, Tunisia", } @Article{Abdelmutalab:2016:PC, author = "Ameen Abdelmutalab and Khaled Assaleh and Mohamed El-Tarhuni", title = "Automatic modulation classification based on high order cumulants and hierarchical polynomial classifiers", journal = "Physical Communication", volume = "21", pages = "10--18", year = "2016", ISSN = "1874-4907", DOI = "doi:10.1016/j.phycom.2016.08.001", URL = "http://www.sciencedirect.com/science/article/pii/S1874490716301094", abstract = "In this paper, a Hierarchical Polynomial (HP) classifier is proposed to automatically classify M-PSK and M-QAM signals in Additive White Gaussian Noise (AWGN) and slow flat fading environments. The system uses higher order cumulants (HOCs) of the received signal to distinguish between the different modulation types. The proposed system divides the overall modulation classification problem into several hierarchical binary sub-classifications. In each binary sub-classification, the HOCs are expanded into a higher dimensional space in which the two classes are linearly separable. It is shown that there is a significant improvement when using the proposed Hierarchical polynomial structure compared to the conventional polynomial classifier. Moreover, simulation results are shown for different block lengths (number of received symbols) and at different SNR values. The proposed system showed an overall improvement in the probability of correct classification that reaches 100percent using only 512 received symbols at 20 dB compared to 98percent and 98.33percent when using more complicated systems like Genetic Programming with KNN classifier (GP-KNN) and Support Vector Machines (SVM) classifiers, respectively.", keywords = "genetic algorithms, genetic programming, Modulation classification, Hierarchical polynomial classifiers, High order cumulants, Adaptive modulation", } @InProceedings{Abdelwhab:2018:SICE, author = "Mohamed Abdelwhab and A. A. Abouelsoud and Ahmed M. R. Fath Elbab", booktitle = "2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)", title = "Tackling Dead End Scenarios by Improving Follow Gap Method with Genetic Programming", year = "2018", pages = "1566--1571", address = "Nara, Japan", abstract = "In this paper the problem of local minimum in obstacle avoidance is solved using improved follow gap method (FGM) through combination with genetic programming (GP). Two stages of controller are proposed and applied on Robotino mobile robot equipped with nine infra-red sensors. The first stage implements FGM when there is a gap between front obstacles whereas the second stage deals with the case of no front gap through the use of GP. Simulation and experimental work prove the effectiveness of the proposed method.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.23919/SICE.2018.8492687", month = sep, notes = "Egypt-Japan University of Science and Technology. Also known as \cite{8492687}", } @PhdThesis{AbdGaus:thesis, author = "Yona Falinie {Abd Gaus}", title = "Artificial Intelligence System for Continuous Affect Estimation from Naturalistic Human Expressions", school = "Brunel University", year = "2018", address = "London, UK", month = jan, keywords = "genetic algorithms, genetic programming", URL = "http://bura.brunel.ac.uk/handle/2438/16348", URL = "https://bura.brunel.ac.uk/bitstream/2438/16348/1/FulltextThesis.pdf", size = "165 pages", abstract = "The analysis and automatic affect estimation system from human expression has been acknowledged as an active research topic in computer vision community. Most reported affect recognition systems, however, only consider subjects performing well-defined acted expression, in a very controlled condition, so they are not robust enough for real-life recognition tasks with subject variation, acoustic surrounding and illumination change. In this thesis, an artificial intelligence system is proposed to continuously (represented along a continuum e.g., from -1 to +1) estimate affect behaviour in terms of latent dimensions (e.g., arousal and valence) from naturalistic human expressions. To tackle the issues, feature representation and machine learning strategies are addressed. In feature representation, human expression is represented by modalities such as audio, video, physiological signal and text modality. Hand- crafted features is extracted from each modality per frame, in order to match with consecutive affect label. However, the features extracted maybe missing information due to several factors such as background noise or lighting condition. Haar Wavelet Transform is employed to determine if noise cancellation mechanism in feature space should be considered in the design of affect estimation system. Other than hand-crafted features, deep learning features are also analysed in terms of the layer-wise; convolutional and fully connected layer. Convolutional Neural Network such as AlexNet, VGGFace and ResNet has been selected as deep learning architecture to do feature extraction on top of facial expression images. Then, multimodal fusion scheme is applied by fusing deep learning feature and hand-crafted feature together to improve the performance. In machine learning strategies, two-stage regression approach is introduced. In the first stage, baseline regression methods such as Support Vector Regression are applied to estimate each affect per time. Then in the second stage, subsequent model such as Time Delay Neural Network, Long Short-Term Memory and Kalman Filter is proposed to model the temporal relationships between consecutive estimation of each affect. In doing so, the temporal information employed by a subsequent model is not biased by high variability present in consecutive frame and at the same time, it allows the network to exploit the slow changing dynamic between emotional dynamic more efficiently. Following of two-stage regression approach for unimodal affect analysis, fusion information from different modalities is elaborated. Continuous emotion recognition in-the-wild is leveraged by investigating mathematical modelling for each emotion dimension. Linear Regression, Exponent Weighted Decision Fusion and Multi-Gene Genetic Programming are implemented to quantify the relationship between each modality. In summary, the research work presented in this thesis reveals a fundamental approach to automatically estimate affect value continuously from naturalistic human expression. The proposed system, which consists of feature smoothing, deep learning feature, two-stage regression framework and fusion using mathematical equation between modalities is demonstrated. It offers strong basis towards the development artificial intelligent system on estimation continuous affect estimation, and more broadly towards building a real-time emotion recognition system for human-computer interaction.", notes = "Supervisor: Hongying Meng", } @InProceedings{AbdGaus:2018:ieeeFG, author = "Yona Falinie A. Gaus and Hongying Meng", booktitle = "2018 13th IEEE International Conference on Automatic Face Gesture Recognition (FG 2018)", title = "Linear and Non-Linear Multimodal Fusion for Continuous Affect Estimation In-the-Wild", year = "2018", pages = "492--498", abstract = "Automatic continuous affect recognition from multiple modality in the wild is arguably one of the most challenging research areas in affective computing. In addressing this regression problem, the advantages of the each modality, such as audio, video and text, have been frequently explored but in an isolated way. Little attention has been paid so far to quantify the relationship within these modalities. Motivated to leverage the individual advantages of each modality, this study investigates behavioural modelling of continuous affect estimation, in multimodal fusion approaches, using Linear Regression, Exponent Weighted Decision Fusion and Multi-Gene Genetic Programming. The capabilities of each fusion approach are illustrated by applying it to the formulation of affect estimation generated from multiple modality using classical Support Vector Regression. The proposed fusion methods were applied in the public Sentiment Analysis in the Wild (SEWA) multi-modal dataset and the experimental results indicate that employing proper fusion can deliver a significant performance improvement for all affect estimation. The results further show that the proposed systems is competitive or outperform the other state-of-the-art approaches.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/FG.2018.00079", month = may, notes = "Also known as \cite{8373872}", } @InProceedings{4983280, author = "I. Abd Latiff and M. O. Tokhi", title = "Fast convergence strategy for Particle Swarm Optimization using spread factor", booktitle = "Evolutionary Computation, 2009. CEC '09. IEEE Congress on", year = "2009", month = may, pages = "2693--2700", keywords = "PSO velocity equation, fast convergence strategy, inertia weight, particle swarm optimization, spread factor, convergence, particle swarm optimisation", DOI = "doi:10.1109/CEC.2009.4983280", notes = "Not on GP", } @Article{journals/nca/AbdolahzareM18, title = "Nonlinear mathematical modeling of seed spacing uniformity of a pneumatic planter using genetic programming and image processing", author = "Zahra Abdolahzare and Saman Abdanan Mehdizadeh", journal = "Neural Computing and Applications", year = "2018", number = "2", volume = "29", pages = "363--375", keywords = "genetic algorithms, genetic programming", bibdate = "2018-01-25", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/nca/nca29.html#AbdolahzareM18", DOI = "doi:10.1007/s00521-016-2450-1", } @Article{Abdollahzadeh:2016:CC, author = "Gholamreza Abdollahzadeh and Ehsan Jahani and Zahra Kashir", title = "Predicting of compressive strength of recycled aggregate concrete by genetic programming", journal = "Computers and Concrete", year = "2016", volume = "18", number = "2", pages = "155--163", month = aug, keywords = "genetic algorithms, genetic programming, gene expression programming, recycled aggregate concrete, silica fume, compressive strength", ISSN = "1598-8198", DOI = "doi:10.12989/CAC.2016.18.2.155", size = "20 pages", abstract = "This paper, proposes 20 models for predicting compressive strength of recycled aggregate concrete (RAC) containing silica fume by using gene expression programming (GEP). To construct the models, experimental data of 228 specimens produced from 61 different mixtures were collected from the literature. 80% of data sets were used in the training phase and the remained 20% in testing phase. Input variables were arranged in a format of seven input parameters including age of the specimen, cement content, water content, natural aggregates content, recycled aggregates content, silica fume content and amount of superplasticizer. The training and testing showed the models have good conformity with experimental results for predicting the compressive strength of recycled aggregate concrete containing silica fume.", notes = "admin@techno-press.com Department of Civil Engineering, Babol University of Technology, Babol, Iran", } @Article{Abdou200911402, author = "Hussein A. Abdou", title = "Genetic programming for credit scoring: The case of Egyptian public sector banks", journal = "Expert Systems with Applications", volume = "36", number = "9", pages = "11402--11417", year = "2009", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2009.01.076", URL = "http://www.sciencedirect.com/science/article/B6V03-4VJSRWK-1/2/a3b8516f289c76c474c6a1eb9d26d7ec", URL = "http://results.ref.ac.uk/Submissions/Output/2691591", keywords = "genetic algorithms, genetic programming, Credit scoring, Weight of evidence, Egyptian public sector banks", abstract = "Credit scoring has been widely investigated in the area of finance, in general, and banking sectors, in particular. Recently, genetic programming (GP) has attracted attention in both academic and empirical fields, especially for credit problems. The primary aim of this paper is to investigate the ability of GP, which was proposed as an extension of genetic algorithms and was inspired by the Darwinian evolution theory, in the analysis of credit scoring models in Egyptian public sector banks. The secondary aim is to compare GP with probit analysis (PA), a successful alternative to logistic regression, and weight of evidence (WOE) measure, the later a neglected technique in published research. Two evaluation criteria are used in this paper, namely, average correct classification (ACC) rate criterion and estimated misclassification cost (EMC) criterion with different misclassification cost (MC) ratios, in order to evaluate the capabilities of the credit scoring models. Results so far revealed that GP has the highest ACC rate and the lowest EMC. However, surprisingly, there is a clear rule for the WOE measure under EMC with higher MC ratios. In addition, an analysis of the dataset using Kohonen maps is undertaken to provide additional visual insights into cluster groupings.", uk_research_excellence_2014 = "D - Journal article", } @PhdThesis{2009AbdouEthosPhD, author = "Hussein Ali Hussein Abdou", title = "Credit Scoring Models for Egyptian Banks: Neural Nets and Genetic Programming versus Conventional Techniques", school = "Plymouth Business School, University of Plymouth", year = "2009", address = "UK", month = apr, keywords = "genetic algorithms, genetic programming", URL = "https://pearl.plymouth.ac.uk/bitstream/handle/10026.1/379/2009AbdouEthosPhD.pdf", URL = "http://hdl.handle.net/10026.1/379", URL = "http://ethos.bl.uk/OrderDetails.do?did=55&uin=uk.bl.ethos.494192", size = "452 pages", abstract = "Credit scoring has been regarded as a core appraisal tool of banks during the last few decades, and has been widely investigated in the area of finance, in general, and banking sectors, in particular. In this thesis, the main aims and objectives are: to identify the currently used techniques in the Egyptian banking credit evaluation process; and to build credit scoring models to evaluate personal bank loans. In addition, the subsidiary aims are to evaluate the impact of sample proportion selection on the Predictive capability of both advanced scoring techniques and conventional scoring techniques, for both public banks and a private banking case-study; and to determine the key characteristics that affect the personal loans' quality (default risk). The stages of the research comprised: firstly, an investigative phase, including an early pilot study, structured interviews and a questionnaire; and secondly, an evaluative phase, including an analysis of two different data-sets from the Egyptian private and public banks applying average correct classification rates and estimated misclassification costs as criteria. Both advanced scoring techniques, namely, neural nets (probabilistic neural nets and multi-layer feed-forward nets) and genetic programming, and conventional techniques, namely, a weight of evidence measure, multiple discriminant analysis, probit analysis and logistic regression were used to evaluate credit default risk in Egyptian banks. In addition, an analysis of the data-sets using Kohonen maps was undertaken to provide additional visual insights into cluster groupings. From the investigative stage, it was found that all public and the vast majority of private banks in Egypt are using judgemental approaches in their credit evaluation. From the evaluative stage, clear distinctions between the conventional techniques and the advanced techniques were found for the private banking case-study; and the advanced scoring techniques (such as powerful neural nets and genetic programming) were superior to the conventional techniques for the public sector banks. Concurrent loans from other banks and guarantees by the corporate employer of the loan applicant, which have not been used in other reported studies, are identified as key variables and recommended in the specific environment chosen, namely Egypt. Other variables, such as a feasibility study and the Central Bank of Egypt report also play a contributory role in affecting the loan quality.", notes = "Supervisor John Pointon uk.bl.ethos.494192", } @InProceedings{Abdulhamid:2011:ICARA, author = "Fahmi Abdulhamid and Kourosh Neshatian and Mengjie Zhang", title = "Genetic programming for evolving programs with loop structures for classification tasks", booktitle = "5th International Conference on Automation, Robotics and Applications (ICARA 2011)", year = "2011", month = "6-8 " # dec, pages = "202--207", address = "Wellington, New Zealand", size = "6 pages", abstract = "Object recognition and classification are important tasks in robotics. Genetic Programming (GP) is a powerful technique that has been successfully used to automatically generate (evolve) classifiers. The effectiveness of GP is limited by the expressiveness of the functions used to evolve programs. It is believed that loop structures can considerably improve the quality of GP programs in terms of both performance and interpretability. This paper proposes five new loop structures using which GP can evolve compact programs that can perform sophisticated processing. The use of loop structures in GP is evaluated against GP with no loops for both image and non-image classification tasks. Evolved programs using the proposed loop structures are analysed in several problems. The results show that loop structures can increase classification accuracy compared to GP with no loops.", keywords = "genetic algorithms, genetic programming, evolving program, image classification task, nonimage classification task, object classification task, object recognition task, program loop structure, robotics, image classification, learning (artificial intelligence), object recognition, robot vision", DOI = "doi:10.1109/ICARA.2011.6144882", notes = "Also known as \cite{6144882}", } @InProceedings{Abdulhamid:2012:CEC, title = "Evolving Genetic Programming Classifiers with Loop Structures", author = "Fahmi Abdulhamid and Andy Song and Kourosh Neshatian and Mengjie Zhang", pages = "2710--2717", booktitle = "Proceedings of the 2012 IEEE Congress on Evolutionary Computation", year = "2012", editor = "Xiaodong Li", month = "10-15 " # jun, DOI = "doi:10.1109/CEC.2012.6252877", address = "Brisbane, Australia", ISBN = "0-7803-8515-2", keywords = "genetic algorithms, genetic programming, Conflict of Interest Papers, Classification, clustering, data analysis and data mining", abstract = "Loop structure is a fundamental flow control in programming languages for repeating certain operations. It is not widely used in Genetic Programming as it introduces extra complexity in the search. However in some circumstances, including a loop structure may enable GP to find better solutions. This study investigates the benefits of loop structures in evolving GP classifiers. Three different loop representations are proposed and compared with other GP methods and a set of traditional classification methods. The results suggest that the proposed loop structures can outperform other methods. Additionally the evolved classifiers can be small and simple to interpret. Further analysis on a few classifiers shows that they indeed have captured genuine characteristics from the data for performing classification.", notes = "WCCI 2012. CEC 2012 - A joint meeting of the IEEE, the EPS and the IET.", } @Article{abdulkarimova:2019:ajhpc, author = "Ulviya Abdulkarimova and Anna {Ouskova Leonteva} and Christian Rolando and Anne Jeannin-Girardon and Pierre Collet", title = "The {PARSEC} machine: a non-{Newtonian} supra-linear super-computer", journal = "Azerbaijan Journal of High Performance Computing", year = "2019", volume = "2", number = "2", pages = "122--140", month = dec, keywords = "genetic algorithms, genetic programming, beowulf cluster, relative space-time, supra-linear acceleration, qualitative acceleration, GPGPU, loosely coupled machines, artificial evolution, transfer learning, harmonic analysis, super-resolution,non-uniform sampling, fourier transform.", URL = "https://publis.icube.unistra.fr/docs/14472/easeaHPC.pdf", URL = "https://azjhpc.org/index.php/archives/15-paper/52-the-parsec-machine-a-non-newtonian-supra-linear-supercomputer", URL = "http://azjhpc.com//issue4/doi.org:10.32010:26166127.2019.2.2.122.140.pdf", DOI = "doi:10.32010/26166127.2019.2.2.122.140", size = "19 pages", abstract = "transfer-learning can turn a Beowulf cluster into a full super-computer with supra-linear qualitative acceleration. Harmonic Analysis is used as a real-world example to show the kind of result that can be achieved with the proposed super-computer architecture, that locally exploits absolute space-time parallelism on each machine (SIMD parallelism) and loosely-coupled relative space-time parallelisation between different machines (loosely coupled MIMD)", } @PhdThesis{abdulkarimova:tel-03700035, author = "Ulviya Abdulkarimova", title = "{SINUS-IT}: an evolutionary approach to harmonic analysis", title_fr = "SINUS-IT : une approche evolutionnaire de l'analyse harmonique", school = "Universite de Strasbourg", year = "2021", address = "France", month = "2 " # sep, keywords = "genetic algorithms, genetic programming, EASEA, NVIDA, CUDA, Artificial evolution, Evolution strategies, QAES, Fourier transform, FFT, Harmonic analysis, FT-ICR, Isotopic structure, GPU, GPGPU parallelisation, Island-based parallelization, Glutathione, binary radians, Brad2rad, Rad2brad, global random sampling, GRS", number = "2021STRAD018", hal_id = "tel-03700035", hal_version = "v1", URL = "https://theses.hal.science/tel-03700035/", URL = "https://theses.hal.science/tel-03700035/document", URL = "https://theses.hal.science/tel-03700035/file/ABDULKARIMOVA_Ulviya_2021_ED269.pdf", size = "185 pages", abstract = "This PhD project is about harmonic analysis of signals coming from Fourier Transform Ion Cyclotron Resonance (FT-ICR) mass spectrometer. The analysis of these signals is usually done using Fourier Transform (FT) method. However, there are several limitations of this method, one of which is not being able to find the phase parameter. Mass spectrometers are used to determine the chemical composition of compounds. It is known that if the phase component is known, it would yield an improvement in mass accuracy and mass resolving power which would help to determine the composition of a given compound more accurately. In this PhD work we use evolutionary algorithm to overcome the limitations of the FT method. We explore different sampling, speed optimization and algorithm improvement methods. We show that our proposed method outperforms the FT method as it uses short transients to resolve the peaks and it automatically yields phase values.", notes = "Some mention of GP. In English. https://icube.unistra.fr/actualites-agenda/agenda/evenement/?tx_ttnews%5Btt_news%5D=23221&cHash=58d32af8fd94c8ff397921898600e7cd MSAP Page 149--159 Appendix A, Resume en francais de la these Thesis supervisors: Pierre Collet and Christian Rolando", } @PhdThesis{Abdullah:thesis, author = "Norliza Binti Abdullah", title = "Android Malware Detection System using Genetic Programming", school = "Computer Science, University of York", year = "2019", address = "UK", month = mar, keywords = "genetic algorithms, genetic programming, Supervised Learning, Multi-objective Genetic Algorithm, SPEA2, MOGP, Android Malware", URL = "https://etheses.whiterose.ac.uk/29027/", URL = "https://etheses.whiterose.ac.uk/29027/6/Abdullah_201051902.pdf", size = "165 pages", abstract = "Nowadays, smartphones and other mobile devices are playing a significant role in the way people engage in entertainment, communicate, network, work, and bank and shop online. As the number of mobile phones sold has increased dramatically worldwide, so have the security risks faced by the users, to a degree most do not realise. One of the risks is the threat from mobile malware. In this research, we investigate how supervised learning with evolutionary computation can be used to synthesise a system to detect Android mobile phone attacks. The attacks include malware, ransomware and mobile botnets. The datasets used in this research are publicly downloadable, available for use with appropriate acknowledgement. The primary source is Drebin. We also used ransomware and mobile botnet datasets from other Android mobile phone researchers. The research in this thesis uses Genetic Programming (GP) to evolve programs to distinguish malicious and non-malicious applications in Android mobile datasets. It also demonstrates the use of GP and Multi-Objective Evolutionary Algorithms (MOEAs) together to explore functional (detection rate) and non-functional (execution time and power consumption) trade-offs. Our results show that malicious and non-malicious applications can be distinguished effectively using only the permissions held by applications recorded in the application's Android Package (APK). Such a minimalist source of features can serve as the basis for highly efficient Android malware detection. Non-functional tradeoffs are also highlight.", notes = "Also known as \cite{wreo29027} uk.bl.ethos.832567", } @InProceedings{Abdul-Rahim:2006:ccis, author = "A. B. {Abdul rahim} and J. Teo and A. Saudi", title = "An Empirical Comparison of Code Size Limit in Auto-Constructive Artificial Life", booktitle = "2006 IEEE Conference on Cybernetics and Intelligent Systems", year = "2006", pages = "1--6", address = "Bangkok", month = jun, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Push, Breve, ALife, PushGP", ISBN = "1-4244-0023-6", DOI = "doi:10.1109/ICCIS.2006.252308", abstract = "This paper presents an evolving swarm system of flying agents simulated as a collective intelligence within the Breve auto-constructive artificial life environment. The behaviour of each agent is governed by genetically evolved program codes expressed in the Push programming language. There are two objectives in this paper, that is to investigate the effects of firstly code size limit and secondly two different versions of the Push genetic programming language on the auto-constructive evolution of artificial life. We investigated these genetic programming code elements on reproductive competence using a measure based on the self-sustainability of the population. Self-sustainability is the point in time when the current population's agents are able to reproduce enough offspring to maintain the minimum population size without any new agents being randomly injected from the system. From the results, we found that the Push2 implementation showed slightly better evolvability than Push3 in terms of achieving self-sufficiency. In terms of code size limit, the reproductive competence of the collective swarm was affected quite significantly at certain parameter settings", notes = "Sch. of Eng. & Inf. Technol., Univ. Malaysia Sabah", } @Article{Abdulrahman:2020:IJCA, author = "Hadeel Abdulrahman and Mohamed Khatib", title = "Classification of Retina Diseases from {OCT} using Genetic Programming", journal = "International Journal of Computer Applications", year = "2020", volume = "177", number = "45", pages = "41--46", month = mar, keywords = "genetic algorithms, genetic programming, feature extraction, Optical Coherence Tomography, OCT image classification, OCT feature extraction", publisher = "Foundation of Computer Science (FCS), NY, USA", address = "New York, USA", ISSN = "0975-8887", URL = "https://www.ijcaonline.org/archives/volume177/number45/abdulrahman-2020-ijca-919973.pdf", URL = "http://www.ijcaonline.org/archives/volume177/number45/31212-2020919973", DOI = "doi:10.5120/ijca2020919973", size = "6 pages", abstract = "a fully automated method for feature extraction and classification of retina diseases is implemented. The main idea is to find a method that can extract the important features from the Optical Coherence Tomography (OCT) image, and acquire a higher classification accuracy. The using of genetic programming (GP) can achieve that aim. Genetic programming is a good way to choose the best combination of feature extraction methods from a set of feature extraction methods and determine the proper parameters for each one of the selected extraction methods. 800 OCT images are used in the proposed method, of the most three popular retinal diseases: Choroidal neovascularization (CNV), Diabetic Macular Edema (DME) and Drusen, beside the normal OCT images. While the set of the feature extraction methods that is used in this paper contains: Gabor filter, Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), histogram of the image, and Speed Up Robust Filter (SURF). These methods are used for the both of global and local feature extraction. After that the classification process is achieved by the Support Vector Machine (SVM). The proposed method performed high accuracy as compared with the traditional methods.", notes = "Also known as \cite{10.5120/ijca2020919973,} www.ijcaonline.org Department of Artificial Intelligence, Faculty of Informatics Engineering, Aleppo University, Syria", } @InProceedings{Abednego:2011:ICEEI, author = "Luciana Abednego and Dwi Hendratmo", title = "Genetic programming hyper-heuristic for solving dynamic production scheduling problem", booktitle = "International Conference on Electrical Engineering and Informatics (ICEEI 2011)", year = "2011", month = "17-19 " # jul, pages = "K3--2", address = "Bandung, Indonesia", size = "4 pages", abstract = "This paper investigates the potential use of genetic programming hyper-heuristics for solution of the real single machine production problem. This approach operates on a search space of heuristics rather than directly on a search space of solutions. Genetic programming hyper-heuristics generate new heuristics from a set of potential heuristic components. Real data from production department of a metal industries are used in the experiments. Experimental results show genetic programming hyper-heuristics outperforms other heuristics including MRT, SPT, LPT, EDD, LDD, dan MON rules with respect to minimum tardiness and minimum flow time objectives. Further results on sensitivity to changes indicate that GPHH designs are robust. Based on experiments, GPHH outperforms six other benchmark heuristics with number of generations 50 and number of populations 50. Human designed heuristics are result of years of work by a number of experts, while GPHH automate the design of the heuristics. As the search process is automated, this would largely reduce the cost of having to create a new set of heuristics.", keywords = "genetic algorithms, genetic programming, cost reduction, dynamic production scheduling problem, genetic programming hyper heuristics, metal industries, minimum flow time, minimum tardiness, single machine production problem, cost reduction, dynamic scheduling, heuristic programming, lead time reduction, metallurgical industries, single machine scheduling", DOI = "doi:10.1109/ICEEI.2011.6021768", ISSN = "2155-6822", notes = "Also known as \cite{6021768}", } @InCollection{abernathy:2000:UGASBCRB, author = "Neil Abernathy", title = "Using a Genetic Algorithm to Select Beam Configurations for Radiosurgery of the Brain", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 2000", year = "2000", editor = "John R. Koza", pages = "1--7", address = "Stanford, California, 94305-3079 USA", month = jun, publisher = "Stanford Bookstore", keywords = "genetic algorithms", notes = "part of \cite{koza:2000:gagp}", } @Article{Abhishek:2014:PMS, author = "Kumar Abhishek and Biranchi Narayan Panda and Saurav Datta and Siba Sankar Mahapatra", title = "Comparing Predictability of Genetic Programming and {ANFIS} on Drilling Performance Modeling for {GFRP} Composites", journal = "Procedia Materials Science", volume = "6", pages = "544--550", year = "2014", note = "3rd International Conference on Materials Processing and Characterisation (ICMPC 2014)", ISSN = "2211-8128", DOI = "doi:10.1016/j.mspro.2014.07.069", URL = "http://www.sciencedirect.com/science/article/pii/S2211812814004349", abstract = "Drilling of glass fibre reinforced polymer (GFRP) composite material is substantially complicated from the metallic materials due to its high structural stiffness (of the composite) and low thermal conductivity of plastics. During drilling of GFRP composites, problems generally arise like fibre pull out, delamination, stress concentration, swelling, burr, splintering and micro cracking etc. which reduces overall machining performance. Now-a-days hybrid approaches have been received remarkable attention in order to model machining process behaviour and to optimise machining performance towards subsequent improvement of both quality and productivity, simultaneously. In the present research, spindle speed, feed rate, plate thickness and drill bit diameter have been considered as input parameters; and the machining yield characteristics have been considered in terms of thrust and surface roughness (output responses) of the drilled composite product. The study illustrates the applicability of genetic programming with the help of GPTIPS as well as Adaptive Neuro Fuzzy Inference System (ANFIS) towards generating prediction models for better understanding of the process behavior and for improving process performances in drilling of GFRP composites.", keywords = "genetic algorithms, genetic programming, Glass fibre reinforced polymer (GFRP), Adaptive Neuro Fuzzy Inference System (ANFIS), GPTIPS.", notes = "PhD thesis (2015) http://ethesis.nitrkl.ac.in/6916/ Experimental Investigations on Machining of CFRP Composites: Study of Parametric Influence and Machining Performance Optimization. PhD thesis. does not seem to be on GP", } @InCollection{Abid:2012:GPnew, author = "Fathi Abid and Wafa Abdelmalek and Sana {Ben Hamida}", title = "Dynamic Hedging Using Generated Genetic Programming Implied Volatility Models", booktitle = "Genetic Programming - New Approaches and Successful Applications", publisher = "InTech", year = "2012", editor = "Sebastian Ventura", chapter = "7", pages = "141--172", keywords = "genetic algorithms, genetic programming", isbn13 = "978-953-51-0809-2", DOI = "doi:10.5772/48148", size = "32 pages", notes = "Part of \cite{Ventura:2012:GPnew}. Open access book CC BY 3.0 license", } @Article{ABOELELA:2022:RE, author = "Abdelrahman E. Aboelela and Ahmed M. Ebid and Ayman L. Fayed", title = "Estimating the subgrade reaction at deep braced excavation bed in dry granular soil using genetic programming ({GP)}", journal = "Results in Engineering", volume = "13", pages = "100328", year = "2022", ISSN = "2590-1230", DOI = "doi:10.1016/j.rineng.2021.100328", URL = "https://www.sciencedirect.com/science/article/pii/S2590123021001298", keywords = "genetic algorithms, genetic programming, Deep braced excavation, Modulus of subgrade reaction", abstract = "Modulus of subgrade reaction (Ks) is a simplified and approximated approach to present the soil-structure interaction. It is widely used in designing combined and raft foundations due to its simplicity. (Ks) is not a soil propriety, its value depends on many factors including soil properties, shape, dimensions and stiffness of footing and even time (for saturated cohesive soils). Many earlier formulas were developed to estimate the (Ks) value. This research is concerned in studying the effect of de-stressing and shoring rigidity of deep excavation on the (Ks) value. A parametric study was carried out using 27 FEM models with different configurations to generate a database, then a well-known {"}Genetic Programming{"} technique was applied on the database to develop a formula to correlate the (Ks) value with the deep excavation configurations. The results indicated that (Ks) value increased with increasing the diaphragm wall stiffness and decreases with increasing the excavation depth", } @Article{Abooali:2014:JNGSE, author = "Danial Abooali and Ehsan Khamehchi", title = "Estimation of dynamic viscosity of natural gas based on genetic programming methodology", journal = "Journal of Natural Gas Science and Engineering", volume = "21", pages = "1025--1031", year = "2014", keywords = "genetic algorithms, genetic programming, Natural gas, Dynamic viscosity, Correlation", ISSN = "1875-5100", DOI = "doi:10.1016/j.jngse.2014.11.006", URL = "http://www.sciencedirect.com/science/article/pii/S1875510014003394", abstract = "Investigating the behaviour of natural gas can contribute to a detailed understanding of hydrocarbon reservoirs. Natural gas, alone or in association with oil in reservoirs, has a large impact on reservoir fluid properties. Thus, having knowledge about gas characteristics seems to be necessary for use in estimation and prediction purposes. In this project, dynamic viscosity of natural gas (mu_g), as an important quantity, was correlated with pseudo-reduced temperature (Tpr), pseudo-reduced pressure (Ppr), apparent molecular weight (Ma) and gas density (rhog) by operation of the genetic programming method on a large dataset including 1938 samples. The squared correlation coefficient (R2), average absolute relative deviation percent (AARDpercent) and average absolute error (AAE) are 0.999, 2.55percent and 0.00084 cp, respectively. The final results show that the obtained simple-to-use model can predict viscosity of natural gases with high accuracy and confidence.", notes = "GPTIPS", } @Article{ABOOALI:2019:JPSE, author = "Danial Abooali and Mohammad Amin Sobati and Shahrokh Shahhosseini and Mehdi Assareh", title = "A new empirical model for estimation of crude oil/brine interfacial tension using genetic programming approach", journal = "Journal of Petroleum Science and Engineering", volume = "173", pages = "187--196", year = "2019", keywords = "genetic algorithms, genetic programming, Interfacial tension, Correlation, Crude oil, Brine, Genetic programming (GP)", ISSN = "0920-4105", DOI = "doi:10.1016/j.petrol.2018.09.073", URL = "http://www.sciencedirect.com/science/article/pii/S0920410518308283", abstract = "Detailed understanding of the behavior of crude oils and their interactions with reservoir formations and other in-situ fluids can help the engineers to make better decisions about the future of oil reservoirs. As an important property, interfacial tension (IFT) between crude oil and brine has great impacts on the oil production efficiency in different recovery stages due to its effects on the capillary number and residual oil saturation. In the present work, a new mathematical model has been developed to estimate IFT between crude oil and brine on the basis of a number of physical properties of crude oil (i.e., specific gravity, and total acid number) and the brine (i.e., pH, NaCl equivalent salinity), temperature, and pressure. Genetic programming (GP) methodology has been implemented on a data set including 560 experimental data to develop the IFT correlation. The correlation coefficient (R2a =a 0.9745), root mean square deviation (RMSDa =a 1.8606a mN/m), and average absolute relative deviation (AARDa =a 3.3932percent) confirm the acceptable accuracy of the developed correlation for the prediction of IFT", } @Article{ABOOALI:2020:Fuel, author = "Danial Abooali and Reza Soleimani and Saeed Gholamreza-Ravi", title = "Characterization of physico-chemical properties of biodiesel components using smart data mining approaches", journal = "Fuel", volume = "266", pages = "117075", year = "2020", ISSN = "0016-2361", DOI = "doi:10.1016/j.fuel.2020.117075", URL = "http://www.sciencedirect.com/science/article/pii/S0016236120300703", keywords = "genetic algorithms, genetic programming, Fatty acid ester, Density, Speed of sound, Isentropic and isothermal compressibility, Stochastic gradient boosting", abstract = "Biodiesels are the most probable future alternatives for petroleum fuels due to their easy accessibility and extraction, comfortable transportation and storage and lower environmental pollutions. Biodiesels have wide range of molecular structures including various long chain fatty acid methyl esters (FAMEs) and fatty acid ethyl esters (FAEEs) with different thermos-physical properties. Therefore, reliable methods estimating the ester properties seems necessary to choose the appropriate one for a special diesel engine. In the present study, the effort was developing a set of novel and robust methods for estimation of four important properties of common long chain fatty acid methyl and ethyl esters including density, speed of sound, isentropic and isothermal compressibility, directly from a number of basic effective variables (i.e. temperature, pressure, molecular weight and normal melting point). Stochastic gradient boosting (SGB) and genetic programming (GP) as innovative and powerful mathematical approaches in this area were applied and implemented on large datasets including 2117, 1048, 483 and 310 samples for density, speed of sound, isentropic and isothermal compressibility, respectively. Statistical assessments revealed high applicability and accuracy of the new developed models (R2 > 0.99 and AARD < 1.7percent) and the SGB models yield more accurate and confident predictions", } @Article{DBLP:journals/nca/AbooaliK19, author = "Danial Abooali and Ehsan Khamehchi", title = "New predictive method for estimation of natural gas hydrate formation temperature using genetic programming", journal = "Neural Comput. Appl.", volume = "31", number = "7", pages = "2485--2494", year = "2019", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.1007/s00521-017-3208-0", DOI = "doi:10.1007/s00521-017-3208-0", timestamp = "Thu, 10 Sep 2020 01:00:00 +0200", biburl = "https://dblp.org/rec/journals/nca/AbooaliK19.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @InProceedings{abraham:2003:CEC, author = "Ajith Abraham and Vitorino Ramos", title = "Web Usage Mining Using Artificial Ant Colony Clustering and Genetic Programming", booktitle = "Proceedings of the 2003 Congress on Evolutionary Computation CEC2003", editor = "Ruhul Sarker and Robert Reynolds and Hussein Abbass and Kay Chen Tan and Bob McKay and Daryl Essam and Tom Gedeon", pages = "1384--1391", year = "2003", publisher = "IEEE Press", address = "Canberra", publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331, USA", month = "8-12 " # dec, organisation = "IEEE Neural Network Council (NNC), Engineers Australia (IEAust), Evolutionary Programming Society (EPS), Institution of Electrical Engineers (IEE)", keywords = "genetic algorithms, genetic programming, Web Usage Mining, Ant Systems, Stigmergy, Data-Mining, Linear Genetic Programming, Adaptive control, Ant colony optimization, Artificial intelligence, Communication system traffic control, Decision support systems, Knowledge management, Marketing management, Programmable control, Traffic control, Internet, artificial life, data mining, decision support systems, electronic commerce, self-organising feature maps, statistical analysis, Web site management, Web usage mining, artificial ant colony clustering algorithm, decision support systems, distributed adaptive organisation, distributed control problems, e-commerce, intelligent marketing strategies, knowledge discovery, knowledge retrieval, network traffic flow analysis, self-organizing map", ISBN = "0-7803-7804-0", URL = "http://alfa.ist.utl.pt/~cvrm/staff/vramos/Vramos-CEC03b.pdf", URL = "http://arxiv.org/abs/cs/0412071", DOI = "doi:10.1109/CEC.2003.1299832", size = "8 pages", abstract = "The rapid e-commerce growth has made both business community and customers face a new situation. Due to intense competition on one hand and the customer's option to choose from several alternatives business community has realized the necessity of intelligent marketing strategies and relationship management. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Web usage mining has become very critical for effective Web site management, creating adaptive Web sites, business and support services, personalization, network traffic flow analysis and so on. The study of ant colonies behavior and their self-organizing capabilities is of interest to knowledge retrieval/management and decision support systems sciences, because it provides models of distributed adaptive organization, which are useful to solve difficult optimization, classification, and distributed control problems, among others. In this paper, we propose an ant clustering algorithm to discover Web usage patterns (data clusters) and a linear genetic programming approach to analyze the visitor trends. Empirical results clearly shows that ant colony clustering performs well when compared to a self-organizing map (for clustering Web usage patterns) even though the performance accuracy is not that efficient when comparared to evolutionary-fuzzy clustering (i-miner) approach.", notes = "CEC 2003 - A joint meeting of the IEEE, the IEAust, the EPS, and the IEE.", } @TechReport{abraham:2004:0405046, author = "Ajith Abraham and Ravi Jain", title = "Soft Computing Models for Network Intrusion Detection Systems", institution = "OSU", year = "2004", month = "13 " # may # " 2004", note = "Journal-ref: Soft Computing in Knowledge Discovery: Methods and Applications, Saman Halgamuge and Lipo Wang (Eds.), Studies in Fuzziness and Soft Computing, Springer Verlag Germany, Chapter 16, 20 pages, 2004", keywords = "genetic algorithms, genetic programming, Cryptography and Security", URL = "http://www.softcomputing.net/saman2.pdf", URL = "http://arxiv.org/abs/cs/0405046", abstract = "Security of computers and the networks that connect them is increasingly becoming of great significance. Computer security is defined as the protection of computing systems against threats to confidentiality, integrity, and availability. There are two types of intruders: external intruders, who are unauthorised users of the machines they attack, and internal intruders, who have permission to access the system with some restrictions. This chapter presents a soft computing approach to detect intrusions in a network. Among the several soft computing paradigms, we investigated fuzzy rule-based classifiers, decision trees, support vector machines, linear genetic programming and an ensemble method to model fast and efficient intrusion detection systems. Empirical results clearly show that soft computing approach could play a major role for intrusion detection.", notes = "ACM-class: K.6.5 cs.CR/0405046", size = "20 pages", } @Article{Abraham:2003:JIKM, author = "Ajith Abraham", title = "Business Intelligence from Web Usage Mining", journal = "Journal of Information \& Knowledge Management", year = "2003", volume = "2", number = "4", pages = "375--390", keywords = "genetic algorithms, genetic programming, Web mining, knowledge discovery, business intelligence, hybrid soft computing, neuro-fuzzy-genetic system", URL = "http://www.softcomputing.net/jikm.pdf", DOI = "doi:10.1142/S0219649203000565", size = "16 pages", abstract = "The rapid e-commerce growth has made both business community and customers face a new situation. Due to intense competition on the one hand and the customer's option to choose from several alternatives, the business community has realized the necessity of intelligent marketing strategies and relationship management. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Web usage mining has become very critical for effective Web site management, creating adaptive Web sites, business and support services, personalization, network traffic flow analysis and so on. This paper presents the important concepts of Web usage mining and its various practical applications. Further a novel approach called {"}intelligent-miner{"} (i-Miner) is presented. i-Miner could optimize the concurrent architecture of a fuzzy clustering algorithm (to discover web data clusters) and a fuzzy inference system to analyze the Web site visitor trends. A hybrid evolutionary fuzzy clustering algorithm is proposed to optimally segregate similar user interests. The clustered data is then used to analyze the trends using a Takagi-Sugeno fuzzy inference system learned using a combination of evolutionary algorithm and neural network learning. Proposed approach is compared with self-organizing maps (to discover patterns) and several function approximation techniques like neural networks, linear genetic programming and Takagi?Sugeno fuzzy inference system (to analyze the clusters). The results are graphically illustrated and the practical significance is discussed in detail. Empirical results clearly show that the proposed Web usage-mining framework is efficient.", notes = "see also \cite{oai:arXiv.org:cs/0405030} http://www.worldscinet.com/jikm/jikm.shtml http://ajith.softcomputing.net Department of Computer Science, Oklahoma State University, 700 N Greenwood Avenue, Tulsa, Oklahoma 74106-0700, USA", } @Misc{oai:arXiv.org:cs/0405030, title = "Business Intelligence from Web Usage Mining", author = "Ajith Abraham", year = "2004", month = may # "~06", keywords = "genetic algorithms, genetic programming", abstract = "The rapid e-commerce growth has made both business community and customers face a new situation. Due to intense competition on one hand and the customer's option to choose from several alternatives business community has realized the necessity of intelligent marketing strategies and relationship management. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Web usage mining has become very critical for effective Web site management, creating adaptive Web sites, business and support services, personalization, network traffic flow analysis and so on. In this paper, we present the important concepts of Web usage mining and its various practical applications. We further present a novel approach 'intelligent-miner' (i-Miner) to optimize the concurrent architecture of a fuzzy clustering algorithm (to discover web data clusters) and a fuzzy inference system to analyze the Web site visitor trends. A hybrid evolutionary fuzzy clustering algorithm is proposed in this paper to optimally segregate similar user interests. The clustered data is then used to analyze the trends using a Takagi-Sugeno fuzzy inference system learned using a combination of evolutionary algorithm and neural network learning. Proposed approach is compared with self-organizing maps (to discover patterns) and several function approximation techniques like neural networks, linear genetic programming and Takagi-Sugeno fuzzy inference system (to analyze the clusters). The results are graphically illustrated and the practical significance is discussed in detail. Empirical results clearly show that the proposed Web usage-mining framework is efficient.", identifier = "Journal of Information \& Knowledge Management (JIKM), World Scientific Publishing Co., Singapore, Vol. 2, No. 4, pp. 375-390, 2003", oai = "oai:arXiv.org:cs/0405030", URL = "http://arXiv.org/abs/cs/0405030", notes = "see also \cite{Abraham:2003:JIKM}", } @InCollection{abraham:2004:ECDM, author = "Ajith Abraham", title = "Evolutionary Computation in Intelligent Network Management", booktitle = "Evolutionary Computing in Data Mining", publisher = "Springer", year = "2004", editor = "Ashish Ghosh and Lakhmi C. Jain", volume = "163", series = "Studies in Fuzziness and Soft Computing", chapter = "9", pages = "189--210", keywords = "genetic algorithms, genetic programming, Linear Genetic Programming, LGP, intrusion detection, ANN, www, fuzzy clustering, fuzzy inference, computer security, RIPPER, demes (ring topology), steady state 32-bit FPU machine code GP, SVM, decision trees, i-miner", ISBN = "3-540-22370-3", URL = "http://www.softcomputing.net/ec_web-chapter.pdf", URL = "http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-175-22-33980376-0,00.html", abstract = "Data mining is an iterative and interactive process concerned with discovering patterns, associations and periodicity in real world data. This chapter presents two real world applications where evolutionary computation has been used to solve network management problems. First, we investigate the suitability of linear genetic programming (LGP) technique to model fast and efficient intrusion detection systems, while comparing its performance with artificial neural networks and classification and regression trees. Second, we use evolutionary algorithms for a Web usage-mining problem. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Evolutionary algorithm is used to optimise the concurrent architecture of a fuzzy clustering algorithm (to discover data clusters) and a fuzzy inference system to analyse the trends. Empirical results clearly shows that evolutionary algorithm could play a major rule for the problems considered and hence an important data mining tool.", size = "22 pages", } @InCollection{intro:2006:GSP, author = "Ajith Abraham and Nadia Nedjah and Luiza {de Macedo Mourelle}", title = "Evolutionary Computation: from Genetic Algorithms to Genetic Programming", year = "2006", booktitle = "Genetic Systems Programming: Theory and Experiences", pages = "1--20", volume = "13", series = "Studies in Computational Intelligence", editor = "Nadia Nedjah and Ajith Abraham and Luiza {de Macedo Mourelle}", publisher = "Springer", address = "Germany", keywords = "genetic algorithms, genetic programming, cartesian genetic programming", ISBN = "3-540-29849-5", URL = "http://www.softcomputing.net/gpsystems.pdf", DOI = "doi:10.1007/3-540-32498-4_1", abstract = "Evolutionary computation, offers practical advantages to the researcher facing difficult optimisation problems. These advantages are multi-fold, including the simplicity of the approach, its robust response to changing circumstance, its flexibility, and many other facets. The evolutionary approach can be applied to problems where heuristic solutions are not available or generally lead to unsatisfactory results. As a result, evolutionary computation have received increased interest, particularly with regards to the manner in which they may be applied for practical problem solving. we review the development of the field of evolutionary computations from standard genetic algorithms to genetic programming, passing by evolution strategies and evolutionary programming. For each of these orientations, we identify the main differences from the others. We also, describe the most popular variants of genetic programming. These include linear genetic programming (LGP), gene expression programming (GEP), multi-expression programming (MEP), Cartesian genetic programming (CGP), traceless genetic programming (TGP), gramatical evolution (GE) and genetic algorithm for deriving software (GADS).", notes = "http://www.springer.com/sgw/cda/frontpage/0,11855,5-146-22-92733168-0,00.html", size = "21 pages", } @InCollection{abraham:2006:GSP, author = "Ajith Abraham and Crina Grosan", title = "Evolving Intrusion Detection Systems", year = "2006", booktitle = "Genetic Systems Programming: Theory and Experiences", pages = "57--79", volume = "13", series = "Studies in Computational Intelligence", editor = "Nadia Nedjah and Ajith Abraham and Luiza {de Macedo Mourelle}", publisher = "Springer", address = "Germany", email = "ajith.abraham@ieee.org", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-29849-5", URL = "http://falklands.globat.com/~softcomputing.net/ids-chapter.pdf", DOI = "doi:10.1007/3-540-32498-4_3", abstract = "An Intrusion Detection System (IDS) is a program that analyses what happens or has happened during an execution and tries to find indications that the computer has been misused. An IDS does not eliminate the use of preventive mechanism but it works as the last defensive mechanism in securing the system. We evaluate the performances of two Genetic Programming techniques for IDS namely Linear Genetic Programming (LGP) and Multi-Expression Programming (MEP). Results are then compared with some machine learning techniques like Support Vector Machines (SVM) and Decision Trees (DT). Empirical results clearly show that GP techniques could play an important role in designing real time intrusion detection systems.", notes = "http://www.springer.com/sgw/cda/frontpage/0,11855,5-146-22-92733168-0,00.html", } @InProceedings{abraham:2005:CEC, author = "Ajith Abraham and Crina Grosan", title = "Genetic Programming Approach for Fault Modeling of Electronic Hardware", booktitle = "Proceedings of the 2005 IEEE Congress on Evolutionary Computation", year = "2005", editor = "David Corne and Zbigniew Michalewicz and Marco Dorigo and Gusz Eiben and David Fogel and Carlos Fonseca and Garrison Greenwood and Tan Kay Chen and Guenther Raidl and Ali Zalzala and Simon Lucas and Ben Paechter and Jennifier Willies and Juan J. Merelo Guervos and Eugene Eberbach and Bob McKay and Alastair Channon and Ashutosh Tiwari and L. Gwenn Volkert and Dan Ashlock and Marc Schoenauer", volume = "2", pages = "1563--1569", address = "Edinburgh, UK", publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331, USA", month = "2-5 " # sep, organisation = "IEEE Computational Intelligence Society, Institution of Electrical Engineers (IEE), Evolutionary Programming Society (EPS)", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, MEP, ANN, LGP", ISBN = "0-7803-9363-5", URL = "http://www.softcomputing.net/cec05.pdf", DOI = "doi:10.1109/CEC.2005.1554875", size = "7 pages", abstract = "presents two variants of Genetic Programming (GP) approaches for intelligent online performance monitoring of electronic circuits and systems. Reliability modelling of electronic circuits can be best performed by the stressor - susceptibility interaction model. A circuit or a system is deemed to be failed once the stressor has exceeded the susceptibility limits. For on-line prediction, validated stressor vectors may be obtained by direct measurements or sensors, which after preprocessing and standardisation are fed into the GP models. Empirical results are compared with artificial neural networks trained using backpropagation algorithm. The performance of the proposed method is evaluated by comparing the experiment results with the actual failure model values. The developed model reveals that GP could play an important role for future fault monitoring systems.", notes = "CEC2005 - A joint meeting of the IEEE, the IEE, and the EPS.", } @Article{journals/jikm/AbrahamG06, author = "Ajith Abraham and Crina Grosan", title = "Decision Support Systems Using Ensemble Genetic Programming", journal = "Journal of Information \& Knowledge Management (JIKM)", year = "2006", volume = "5", number = "4", pages = "303--313", month = dec, note = "Special topic: Knowledge Discovery Using Advanced Computational Intelligence Tools", keywords = "genetic algorithms, genetic programming, gene expression programming, Decision support systems, ensemble systems, evolutionary multi-objective optimisation", ISSN = "0219-6492", DOI = "doi:10.1142/S0219649206001566", abstract = "This paper proposes a decision support system for tactical air combat environment using a combination of unsupervised learning for clustering the data and an ensemble of three well-known genetic programming techniques to classify the different decision regions accurately. The genetic programming techniques used are: Linear Genetic programming (LGP), Multi-Expression Programming (MEP) and Gene Expression Programming (GEP). The clustered data are used as the inputs to the genetic programming algorithms. Some simulation results demonstrating the difference of these techniques are also performed. Test results reveal that the proposed ensemble method performed better than the individual GP approaches and that the method is efficient.", bibdate = "2008-06-20", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/jikm/jikm5.html#AbrahamG06", } @Article{Abraham:2007:JNCS, author = "Ajith Abraham and Ravi Jain and Johnson Thomas and Sang Yong Han", title = "D-SCIDS: Distributed soft computing intrusion detection system", journal = "Journal of Network and Computer Applications", year = "2007", volume = "30", number = "1", pages = "81--98", month = jan, keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1016/j.jnca.2005.06.001", abstract = "An Intrusion Detection System (IDS) is a program that analyses what happens or has happened during an execution and tries to find indications that the computer has been misused. A Distributed IDS (DIDS) consists of several IDS over a large network (s), all of which communicate with each other, or with a central server that facilitates advanced network monitoring. In a distributed environment, DIDS are implemented using co-operative intelligent agents distributed across the network(s). This paper evaluates three fuzzy rule-based classifiers to detect intrusions in a network. Results are then compared with other machine learning techniques like decision trees, support vector machines and linear genetic programming. Further, we modelled Distributed Soft Computing-based IDS (D-SCIDS) as a combination of different classifiers to model lightweight and more accurate (heavy weight) IDS. Empirical results clearly show that soft computing approach could play a major role for intrusion detection.", } @InProceedings{Abraham:2008:ieeeISI, author = "Ajith Abraham", title = "Real time intrusion prediction, detection and prevention programs", booktitle = "IEEE International Conference on Intelligence and Security Informatics, ISI 2008", year = "2008", month = jun, pages = "xli--xlii", note = "IEEE ISI 2008 Invited Talk (VI)", keywords = "genetic algorithms, genetic programming, distributed intrusion detection systems, hidden Markov model, intrusion detection program, online risk assessment, real time intrusion detection, real time intrusion prediction, real time intrusion prevention, hidden Markov models, risk management, security of data", DOI = "doi:10.1109/ISI.2008.4565018", size = "1.1 pages", abstract = "An intrusion detection program (IDP) analyzes what happens or has happened during an execution and tries to find indications that the computer has been misused. In this talk, we present some of the challenges in designing efficient intrusion detection systems (IDS) using nature inspired computation techniques, which could provide high accuracy, low false alarm rate and reduced number of features. Then we present some recent research results of developing distributed intrusion detection systems using genetic programming techniques. Further, we illustrate how intruder behavior could be captured using hidden Markov model and predict possible serious intrusions. Finally we illustrate the role of online risk assessment for intrusion prevention systems and some associated results.", notes = "Also known as \cite{4565018}", } @InProceedings{Abraham:2009:UKSIM, author = "Ajith Abraham and Crina Grosan and Vaclav Snasel", title = "Programming Risk Assessment Models for Online Security Evaluation Systems", booktitle = "11th International Conference on Computer Modelling and Simulation, UKSIM '09", year = "2009", month = "25-27 " # mar, pages = "41--46", keywords = "genetic algorithms, genetic programming, genetic programming methods, human reasoning, online security evaluation systems, perception process, programming risk assessment models, risk management, security of data", DOI = "doi:10.1109/UKSIM.2009.75", isbn13 = "978-0-7695-3593-7", abstract = "Risk assessment is often done by human experts, because there is no exact and mathematical solution to the problem.Usually the human reasoning and perception process cannot be expressed precisely. This paper propose a genetic programming approach for risk assessment. Preliminary results indicate that genetic programming methods are robust and suitable for this problem when compared to other risk assessment models.", notes = "Also known as \cite{4809735}", } @InProceedings{Abraham:2009:IAS, author = "Ajith Abraham and Crina Grosan and Hongbo Liu and Yuehui Chen", title = "Hierarchical {Takagi-Sugeno} Models for Online Security Evaluation Systems", booktitle = "Fifth International Conference on Information Assurance and Security, IAS '09", year = "2009", month = aug, volume = "1", pages = "687--692", keywords = "genetic algorithms, genetic programming, hierarchical Takagi-Sugeno models, human perception, human reasoning, intrusion detection, neuro-fuzzy programming, online security evaluation systems, risk assessment, fuzzy reasoning, hierarchical systems, human factors, interactive programming, risk management, security of data", DOI = "doi:10.1109/IAS.2009.348", abstract = "Risk assessment is often done by human experts, because there is no exact and mathematical solution to the problem. Usually the human reasoning and perception process cannot be expressed precisely. This paper propose a light weight risk assessment system based on an Hierarchical Takagi-Sugeno model designed using evolutionary algorithms. Performance comparison is done with neuro-fuzzy and genetic programming methods. Empirical results indicate that the techniques are robust and suitable for developing light weight risk assessment models, which could be integrated with intrusion detection and prevention systems.", notes = "Also known as \cite{5283215}", } @InCollection{abrams:2000:CSAMPR, author = "Zoe Abrams", title = "Complimentary Selection as an Alternative Method for Population Reproduction", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 2000", year = "2000", editor = "John R. Koza", pages = "8--15", address = "Stanford, California, 94305-3079 USA", month = jun, publisher = "Stanford Bookstore", keywords = "genetic algorithms, genetic programming", notes = "part of \cite{koza:2000:gagp}", } @InProceedings{abramson:1996:cccGP, author = "Myriam Abramson and Lawrence Hunter", title = "Classification using Cultural Co-Evolution and Genetic Programming", booktitle = "Genetic Programming 1996: Proceedings of the First Annual Conference", editor = "John R. Koza and David E. Goldberg and David B. Fogel and Rick L. Riolo", year = "1996", month = "28--31 " # jul, keywords = "genetic algorithms, genetic programming", pages = "249--254", address = "Stanford University, CA, USA", publisher = "MIT Press", broken = "ftp://lhc.nlm.nih.gov/pub/hunter/gp96.ps", size = "6 pages", URL = "http://cognet.mit.edu/sites/default/files/books/9780262315876/pdfs/9780262315876_chap30.pdf", URL = "http://cognet.mit.edu/library/books/view?isbn=0262611279", notes = "GP-96", } @Article{Abu-Romoh:2018:ieeeCL, author = "M. Abu-Romoh and A. Aboutaleb and Z. Rezki", journal = "IEEE Communications Letters", title = "Automatic Modulation Classification Using Moments And Likelihood Maximization", year = "2018", abstract = "Motivated by the fact that moments of the received signal are easy to compute and can provide a simple way to automatically classify the modulation of the transmitted signal, we propose a hybrid method for automatic modulation classification that lies in the intersection between likelihood-based and feature-based classifiers. Specifically, the proposed method relies on statistical moments along with a maximum likelihood engine. We show that the proposed method offers a good tradeoff between classification accuracy and complexity relative to the Maximum Likelihood (ML) classifier. Furthermore, our classifier outperforms state-of-the-art machine learning classifiers, such as genetic programming-based K-nearest neighbour (GP-KNN) classifiers, the linear support vector machine classifier (LSVM) and the fold-based Kolmogorov-Smirnov (FB-KS) algorithm.", keywords = "genetic algorithms, genetic programming, Feature extraction, Machine learning algorithms, Modulation, Probability density function, Receivers, Signal to noise ratio, Support vector machines", DOI = "doi:10.1109/LCOMM.2018.2806489", ISSN = "1089-7798", notes = "Also known as \cite{8292836}", } @InProceedings{Abubakar:2016:ICCOINS, author = "Mustapha Yusuf Abubakar and Low Tang Jung and Mohamed Nordin Zakaria and Ahmed Younesy and Abdel-Haleem Abdel-Atyz", booktitle = "2016 3rd International Conference on Computer and Information Sciences (ICCOINS)", title = "New universal gate library for synthesizing reversible logic circuit using genetic programming", year = "2016", pages = "316--321", abstract = "We newly formed universal gate library, that includes NOT, CNOT (Feyman), Toffoli, Fredkin, Swap, Peres gates and a special gate called G gate. The gate G on its own is a universal gate, but using it alone in a library will result in large circuit realization. G gate combines the operations of Generalized Toffoli gates. For example a gate called G3 combines the operations of NOT, CNOT and T3 (3 - bit Toffoli) gates all in one place. The new library was used in synthesizing reversible circuits. The experiment was done using Genetic programming algorithm that is capable of allowing the choice of any type of gate library and optimising the circuit. The results were promising because the gate complexity in the circuits were drastically reduced compared to previously attempted synthesis.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/ICCOINS.2016.7783234", month = aug, notes = "Also known as \cite{7783234}", } @Article{journals/qip/AbubakarJZYA17, author = "Mustapha Yusuf Abubakar and Low Tang Jung and Nordin Zakaria and Ahmed Younes and Abdel-Haleem Abdel-Aty", title = "Reversible circuit synthesis by genetic programming using dynamic gate libraries", journal = "Quantum Information Processing", year = "2017", number = "6", volume = "16", pages = "160", keywords = "genetic algorithms, genetic programming", bibdate = "2017-05-26", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/qip/qip16.html#AbubakarJZYA17", DOI = "doi:10.1007/s11128-017-1609-8", } @InProceedings{Abubakar:2018:ICCOINS, author = "Mustapha Yusuf Abubakar and Low {Tang Jung}", booktitle = "2018 4th International Conference on Computer and Information Sciences (ICCOINS)", title = "Synthesis of Reversible Logic Using Enhanced Genetic Programming Approach", year = "2018", abstract = "A new enhanced reversible logic circuit synthesis method was developed using reversible gates that include NOT, CNOT (Feynman), Toffoli, Fredkin, Swap, and Peres gates. The synthesis method was done using newly developed genetic programming. Usually previous synthesis methods that uses genetic algorithms or other similar evolutionary algorithms suffers a problem known as blotting which is a sudden uncontrolled growth of an individual (circuit), which may render the synthesis inefficient because of memory usage, making the algorithm difficult to continue running and eventually stack in a local minima, there for an optimized reversible circuit may not be generated. In this method the algorithm used was blot free, the blotting was carefully controlled by fixing a suitable length and size of the individuals in the population. Following this approach, the cost of generating circuits was greatly reduced giving the algorithm to reach the end of the last designated generation to give out optimal or near optimal results. The results of the circuits generated using this method were compared with some of the results already in the literature, and in many cases, our results appeared to be better in terms of gate count and quantum cost metrics.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/ICCOINS.2018.8510602", month = aug, notes = "Also known as \cite{8510602}", } @Article{Abud-Kappel:2016:Measurement, author = "Marco Andre {Abud Kappel} and Ricardo Fabbri and Roberto P. Domingos and Ivan N. Bastos", title = "Novel electrochemical impedance simulation design via stochastic algorithms for fitting equivalent circuits", journal = "Measurement", year = "2016", volume = "94", pages = "344--354", keywords = "genetic algorithms, genetic programming, Differential evolution, Electrochemical impedance, Impedance measurements, Corrosion, Optimization, Stochastic methods", ISSN = "0263-2241", URL = "https://www.sciencedirect.com/science/article/pii/S0263224116304699", DOI = "doi:10.1016/j.measurement.2016.08.008", abstract = "Electrochemical impedance spectroscopy (EIS) is of great value to corrosion studies because it is sensitive to transient changes that occur in the metal-electrolyte interface. A useful way to link the results of electrochemical impedance spectroscopy to corrosion phenomena is by simulating equivalent circuits. Equivalent circuit models are very attractive because of their relative simplicity, enabling the monitoring of electrochemical systems that have a complex physical mechanism. In this paper, the stochastic algorithm Differential Evolution is proposed to fit an equivalent circuit to the EIS results for a wide potential range. EIS is often limited to the corrosion potential despite being widely used. This greatly hinders the analysis regarding the effect of the applied potential, which strongly affects the interface, as shown, for example, in polarization curves. Moreover, the data from both the EIS and the DC values were used in the proposed scheme, allowing the best fit of the model parameters. The approach was compared to the standard Simplex square residual minimization of EIS data. In order to manage the large amount of generated data, the EIS-Mapper software package, which also plots the 2D/3D diagrams with potential, was used to fit the equivalent circuit of multiple diagrams. Furthermore, EIS-Mapper also computed all simulations. The results of 67 impedance diagrams of stainless steel in a 3.5percent NaCl medium at 25C obtained in steps of 10mV, and the respective values of the fitted parameters of the equivalent circuit are reported. The present approach conveys new insight to the use of electrochemical impedance and bridges the gap between polarization curves and equivalent electrical circuits.", } @PhdThesis{Tese_MarcoAndreAbudKappel, author = "Marco Andre Abud Kappel", title_pt = "Emprego de tecnicas computacionais estocasticas para simulacao de diagramasde espectroscopia de impedancia eletroquimica", title = "Stochastic computational techniques applied to the simulation of electrochemical impedance spectroscopy diagrams", school = "Centro de Tecnologia e Ciencias, Instituto Politecnico, Universidadedo Estado do Rio de Janeiro", year = "2016", address = "Nova Friburgo, Brazil", month = "8 " # apr, keywords = "genetic algorithms, genetic programming, Electrochemical impedance spectroscopy, Corrosion, Complex nonlinear optimization, Equivalent electrical circuit, Stochastic methods", URL = "http://www.bdtd.uerj.br/handle/1/13692", URL = "https://www.bdtd.uerj.br:8443/bitstream/1/13692/1/Tese_MarcoAndreAbudKappel.pdf", size = "169 pages", abstract = "Electrochemical impedance spectroscopy is a widely used technique in electrochemical systems characterization. With applications in several areas, the technique is very useful in the study of corrosion because it is sensitive to transient changes that occur in the metal interface. The results from the technique can be expressed and interpreted in different ways, allowing different modeling and analysis methods, such as the use of kinetic models or equivalent circuits. In corrosion, the technique is usually applied only in a few specific potentials, such as the corrosion potential, the most important. With the motivation of improving the impedance modeling and analysis process, taking into consideration that the electrochemical phenomena are strongly linked to the potential, this work introduces the possibility to express the impedance data in a wide potential range, and use them to equivalent circuits fitting. Thus, different phenomena can be modeled adequately by equivalent circuits corresponding to different potentials. For this purpose, the related inverse problem is solved for each potential through a complex nonlinear optimization process. In addition to the transient data obtained by the spectroscopy, stationary data are also used in the optimization as a regularisation factor, supporting a consistent solution to the physical phenomena involved, from the maximum experimental frequency to theoretical zero frequency. An analysis, modeling and simulation software was developed with the following features: 1) validation of experimental data, through the Kramers-Kronig relations; 2) simultaneous visualization of impedance results for a wide potential range; 3) fitting different equivalent circuits for different ranges using transient and stationary experimental data, in conjunction with deterministic or stochastic methods; 4) generation of confidence regions for the estimated parameters, making them statistically significant; 5) simulations using the fitted equivalent circuits in computer cluster; 6) parameter sensitivity analysis according to the applied potential, revealing important physical characteristics involved in the electrochemical processes. Finally, experimental fitting results and the corresponding simulations are shown and discussed. Results show that the use of a population-based stochastic optimization method not only increases the odds of finding the global optimum, but also enables the generation of confidence regions around the found values. Furthermore, only the circuit fitted with the new objective function has equivalence with both transient data and stationary data for the entire potential range involved.", resumo = "A espectroscopia de impedancia eletroquimica e uma tecnica amplamente utilizada na caracterizacao de sistemas eletroquimicos. Alem de possuir aplicacoes em diversas areas, a tecnica tem grande utilidade no estudo dacorrosao, pois e sensivel as variacoes transientes que ocorrem na interface metalica. Os resultados provenientes da tecnica podem ser expressos e interpretados de diversas formas, possibilitando diferentes metodologias de modelagem e analise, como o uso de modelos cineticos ou circuitos eletricos equivalentes. Em corrosao, a tecnica e aplicada, normalmente, em poucos potenciais especificos, como o de corrosao, o de maior importancia. Com a motivacao de aprimoraro procedimento de modelagem e analise de dados de impedancia, levando em consideracaoque os fenomenos eletroquimicos estao fortemente ligadosao potencial, este trabalho introduz a possibilidadede expressar os dados de impedancia em uma ampla faixa de potencial, e utiliza-los para ajuste de circuitos equivalentes. Assim, os diferentes fenomenos podem ser modelados, adequadamente, por circuitos eletricosequivalentes correspondentes a diferentes potenciais. Com esta finalidade, oproblema inverso associado eresolvidopara cada potencial, por meio de um processo de otimizacao complexa nao-linear. Alem dos dados transientes obtidos pela espectroscopia, dados estacionariossao utilizados na otimizacao de forma original, como uma regularizacao do problema, ajudando a garantir a obtencao de uma solucao coerente com os fenomenos fisicos envolvidos,desde a frequencia maxima do ensaio ate a frequencia nula. Um software de analise, modelagem e simulacao foi desenvolvido, com as seguintes funcionalidades: 1) validacaodos dados experimentais, por meio das relacoes de Kramers-Kronig; 2) visualizacao simultanea dos dados de impedanciapara ampla faixa de potencial; 3) ajuste dediferentes circuitos equivalentes para diferentes faixas,utilizando dados experimentais transientes e estacionarios, em conjunto com metodosdeterministicosou estocasticos; 4) geracao deregioes de confianca para os parametros ajustados, tornando-os estatisticamente significativos; 5) simulacoes utilizando os circuitos equivalentesajustadosem cluster de computador; 6) apresentacao de analise de sensibilidade dos parametros de acordo com o potencialaplicado, revelando caracteristicas fisicasimportantes envolvidas nos processos eletroquimicos. Por fim, resultados experimentaisdosajustes e das simulacoes correspondentes sao mostrados e discutidos.Os resultados obtidos mostram que a utilizacao de um metodo de otimizacao estocastico populacional nao apenas aumenta as probabilidades de se encontrar uma solucao melhor, como tambem possibilita a geracao das regioes de confianca em torno dos valores encontrados. Alem disso, apenas o circuito ajustado com a nova funcao objetivo possui equivalencia tanto com os dados transientes quanto com os dados estacionarios, para toda a faixa de potencial envolvida.", notes = "In Portuguese. Supervisors: Ivan Napoleao Bastos and Roberto Pinheiro Domingos", } @Article{Abud-Kappel:2017:ASC, author = "Marco Andre {Abud Kappel} and Fernando Cunha Peixoto and Gustavo Mendes Platt and Roberto Pinheiro Domingos and Ivan Napoleao Bastos", title = "A study of equivalent electrical circuit fitting to electrochemical impedance using a stochastic method", journal = "Applied Soft Computing", year = "2017", volume = "50", pages = "183--193", month = jan, keywords = "genetic algorithms, genetic programming, Differential evolution, Electrochemical impedance, Optimization, Stochastic method, Statistical analysis", ISSN = "1568-4946", URL = "https://www.sciencedirect.com/science/article/pii/S1568494616305993", DOI = "doi:10.1016/j.asoc.2016.11.030", size = "11 pages", abstract = "Modeling electrochemical impedance spectroscopy is usually done using equivalent electrical circuits. These circuits have parameters that need to be estimated properly in order to make possible the simulation of impedance data. Despite the fitting procedure is an optimization problem solved recurrently in the literature, rarely statistical significance of the estimated parameters is evaluated. In this work, the optimization process for the equivalent electrical circuit fitting to the impedance data is detailed. First, a mathematical development regarding the minimization of residual least squares is presented in order to obtain a statistically valid objective function of the complex nonlinear regression problem. Then, the optimization method used in this work is presented, the Differential Evolution, a global search stochastic method. Furthermore, it is shown how a population-based stochastic method like this can be used directly to obtain confidence regions to the estimated parameters. A sensitivity analysis was also conducted. Finally, the equivalent circuit fitting is done to model synthetic experimental data, in order to demonstrate the adopted procedure.", } @InProceedings{Abud-Kappel:2018:EngOpt, title = "Cartesian Genetic Programing Applied to Equivalent Electric Circuit Identification", author = "Marco Andre {Abud Kappel} and Roberto Pinheiro Domingos and Ivan Napoleao Bastos", booktitle = "Proceedings of the 6th International Conference on Engineering Optimization. EngOpt 2018", year = "2018", editor = "H. C. Rodrigues and J. Herskovits and C. M. {Mota Soares} and A. L. Araujo and J. M. Guedes and J. O. Folgado and F. Moleiro and J. F. A. Madeira", pages = "913--925", address = "Lisbon, Portugal", month = "17-19 " # sep, organisation = "Instituto Superior Tecnico", publisher = "Springer", keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, Differential Evolution, Complex nonlinear optimization, Equivalent electric circuit identification", isbn13 = "978-3-319-97773-7", DOI = "doi:10.1007/978-3-319-97773-7_79", abstract = "Equivalent electric circuits are widely used in electrochemical impedance spectroscopy (EIS) data modeling. EIS modeling involves the identification of an electrical circuit physically equivalent to the system under analysis. This equivalence is based on the assumption that each phenomenon of the electrode interface and the electrolyte is represented by electrical components such as resistors, capacitors and inductors. This analogy allows impedance data to be used in simulations and predictions related to corrosion and electrochemistry. However, when no prior knowledge of the inner workings of the process under analysis is available, the identification of the circuit model is not a trivial task. The main objective of this work is to improve both the equivalent circuit topology identification and the parameter estimation by using a different approach than the usual Genetic Programming. In order to accomplish this goal, a methodology was developed to unify the application of Cartesian Genetic Programming to tackle system topology identification and Differential Evolution for optimization of the circuit parameters. The performance and effectiveness of this methodology were tested by performing the circuit identification on four different known systems, using numerically simulated impedance data. Results showed that the applied methodology was able to identify with satisfactory precision both the circuits and the values of the components. Results also indicated the necessity of using a stochastic method in the optimization process, since more than one electric circuit can fit the same dataset. The use of evolutionary adaptive metaheuristics such as the Cartesian Genetic Programming allows not only the estimation of the model parameters, but also the identification of its optimal topology. However, due to the possibility of multiple solutions, its application must be done with caution. Whenever possible, restrictions on the search space should be added, bearing in mind the correspondence of the model to the studied physical phenomena.", notes = "XVI Encontro de Modelagem Computacional ?", } @InProceedings{Abud-Kappel:2019:BRACIS, author = "Marco Andre {Abud Kappel}", booktitle = "2019 8th Brazilian Conference on Intelligent Systems (BRACIS)", title = "Action Scheduling Optimization using Cartesian Genetic Programming", year = "2019", pages = "293--298", month = oct, keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming", ISSN = "2643-6264", DOI = "doi:10.1109/BRACIS.2019.00059", abstract = "Action scheduling optimisation is a problem that involves chronologically organizing a set of actions, jobs or commands in order to accomplish a pre-established goal. This kind of problem can be found in a number of areas, such as production planning, delivery logistic organization, robot movement planning and behavior programming for intelligent agents in games. Despite being a recurrent problem, selecting the appropriate time and order to execute each task is not trivial, and typically involves highly complex techniques. The main objective of this work is to provide a simple alternative to tackle the action scheduling problem, by using Cartesian Genetic Programming as an approach. The proposed solution involves the application of two simple main steps: defining the set of available actions and specifying an objective function to be optimized. Then, by the means of the evolutionary algorithm, an automatically generated schedule will be revealed as the most fitting to the goal. The effectiveness of this methodology was tested by performing an action schedule optimization on two different problems involving virtual agents walking in a simulated environment. In both cases, results showed that, throughout the evolutionary process, the simulated agents naturally chose the most efficient sequential and parallel combination of actions to reach greater distances. The use of evolutionary adaptive metaheuristics such as Cartesian Genetic Programming allows the identification of the best possible schedule of actions to solve a problem.", notes = "Also known as \cite{8923702}", } @InProceedings{AbuDalhoum:2005:ESM, author = "Abdel Latif {Abu Dalhoum} and Moh'd {Al Zoubi} and Marina {de la Cruz} and Alfonso Ortega and Manuel Alfonseca", title = "A Genetic Algorithm for Solving the P-Median Problem", booktitle = "European Simulation and Modeling Conference ESM'2005", year = "2005", editor = "J. Manuel Feliz Teixeira and A. E.{Carvalho Brito}", pages = "141--145", address = "Porto, Portugal", month = oct # " 24-26", organisation = "Eurosim, The European Multidisciplinary Society for Modelling and Simulation Technology", publisher = "http://www.eurosis.org", keywords = "genetic algorithms, genetic programming, grammatical evolution, Christiansen grammar, location allocation, p-median model, grammar evolution", ISBN = "90-77381-22-8", URL = "http://arantxa.ii.uam.es/~alfonsec/docs/confint/pmedian.pdf", URL = "https://www.eurosis.org/cms/files/proceedings_full/ESM2005.deel2.pdf", size = "5 pages", abstract = "One of the most popular location-allocation models among researchers is the p-median. Most of the algorithmic research on these models has been devoted to developing heuristic solution procedures. The major drawback of heuristic methods is that the time required finding solutions can become unmanageable. In this paper, we propose a new algorithm, using different variants of grammar evolution, to solve the p-median problem.", notes = "Title may be listed as 'A Genetic Algorithm for solving the P-Medium Problem'. http://www.eurosis.org/cms/files/proceedings/ESM/ESM2005contents.pdf", } @Article{ABYANI:2022:oceaneng, author = "Mohsen Abyani and Mohammad Reza Bahaari and Mohamad Zarrin and Mohsen Nasseri", title = "Predicting failure pressure of the corroded offshore pipelines using an efficient finite element based algorithm and machine learning techniques", year = "2022", journal = "Ocean Engineering", volume = "254", pages = "111382", month = "15 " # jun, keywords = "genetic algorithms, genetic programming, Offshore pipelines, Corrosion, Artificial neural network, ANN, Genetic programing, Support vector machine, SVM, Random forest, Gaussian process regression", ISSN = "0029-8018", DOI = "doi:10.1016/j.oceaneng.2022.111382", URL = "https://www.sciencedirect.com/science/article/pii/S0029801822007697", abstract = "This paper aims to predict the failure pressure of corroded offshore pipelines, employing different machine learning techniques. To this end, an efficient finite element based algorithm is programmed to numerically estimate the failure pressure of offshore pipelines, subjected to internal corrosion. In this process, since the computational effort of such numerical assessment is very high, the application of reliable machine learning methods is used as an alternative solution. Thus, 1815 realizations of four variables are generated, and each one is keyed into the numerical model of a sample pipeline. Thereafter, the machine learning models are constructed based on the results of the numerical analyses, and their performance are compared with each other. The results indicate that Gaussian Process Regression (GPR) and MultiLayer Perceptron (MLP) have the best performance among all the chosen models. Considering the testing dataset, the squared correlation coefficient and Root Mean Squared Error (RMSE) values of GPR and MLP models are 0.535, 0.545 and 0.993 and 0.992, respectively. Moreover, the Maximum Von-Mises Stress (MVMS) of the pipeline increases as the water depth grows at low levels of Internal Pressure (IP). Inversely, increase in water depth leads to reduction in the MVMS values at high IP levels", notes = "Also known as \cite{ABYANI2022111382}", } @TechReport{AcarM05tr, author = "Aybar C. Acar and Amihai Motro", title = "Intensional Encapsulations of Database Subsets by Genetic Programming", institution = "Information and Software Engineering Department, The Volgenau School of Information Technology and Engineering, George Mason University", year = "2005", number = "ISE-TR-05-01", month = feb, keywords = "genetic algorithms, genetic programming", URL = "http://ise.gmu.edu/techrep/2005/05_01.pdf", abstract = "Finding intensional encapsulations of database subsets is the inverse of query evaluation. Whereas query evaluation transforms an intensional expression (the query) to its extension (a set of data values), intensional encapsulation assigns an intensional expression to a given set of data values. We describe a method for deriving intensional representations of subsets of records in large database tables. Our method is based on the paradigm of genetic programming. It is shown to achieve high accuracy and maintain compact expression size, while requiring cost that is acceptable to all applications, but those that require instantaneous results. Intensional encapsulation has a broad range of applications including cooperative answering, information integration, security and data mining.", notes = "See \cite{conf/dexa/AcarM05}", size = "17 pages", } @InProceedings{conf/dexa/AcarM05, title = "Intensional Encapsulations of Database Subsets via Genetic Programming", author = "Aybar C. Acar and Amihai Motro", year = "2005", pages = "365--374", editor = "Kim Viborg Andersen and John K. Debenham and Roland Wagner", publisher = "Springer", series = "Lecture Notes in Computer Science", volume = "3588", booktitle = "Database and Expert Systems Applications, 16th International Conference, DEXA 2005, Proceedings", address = "Copenhagen, Denmark", month = aug # " 22-26", bibdate = "2005-11-03", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/dexa/dexa2005.html#AcarM05", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-28566-0", DOI = "doi:10.1007/11546924_36", size = "10 pages", abstract = "Finding intensional encapsulations of database subsets is the inverse of query evaluation. Whereas query evaluation transforms an intensional expression (the query) to its extension (a set of data values), intensional encapsulation assigns an intensional expression to a given set of data values. We describe a method for deriving intensional representations of subsets of records in large database tables. Our method is based on the paradigm of genetic programming. It is shown to achieve high accuracy and maintain compact expression size, while requiring cost that is acceptable to all applications, but those that require instantaneous results. Intensional encapsulation has a broad range of applications including cooperative answering, information integration, security and data mining.", notes = "See also \cite{AcarM05tr}", } @PhdThesis{Acar:thesis, author = "Aybar C. Acar", title = "Query Consolidation: Interpreting Queries Sent to Independent Heterogenous Databases", school = "The Volgenau School of Information Technology and Engineering, George Mason University", year = "2008", address = "Fairfax, VA, USA", month = "23 " # jul, keywords = "genetic algorithms, genetic programming, Databases, Information Integration, Query Processing, Machine Learning", URL = "http://hdl.handle.net/1920/3223", URL = "http://digilib.gmu.edu:8080/dspace/bitstream/1920/3223/1/Acar_Aybar.pdf", size = "182 pages", abstract = "This dissertation introduces the problem of query consolidation, which seeks to interpret a set of disparate queries submitted to independent databases with a single global query. The problem has multiple applications, from improving virtual database design, to aiding users in information retrieval, to protecting against inference of sensitive data from a seemingly innocuous set of apparently unrelated queries. The problem exhibits attractive duality with the much-researched problem of query decomposition, which has been addressed intensively in the context of multidatabase environments: How to decompose a query submitted to a virtual database into a set of local queries that are evaluated in individual databases. The new problem is set in the architecture of a canonical multidatabase system, using it in the reverse direction. The reversal is built on the assumption of conjunctive queries and source descriptions. A rational and efficient query decomposition strategy is also assumed, and this decomposition is reversed to arrive at the original query by analyzing the decomposed components. The process incorporates several steps where a number of solutions must be considered, due to the fact that query decomposition is not injective. Initially, the problem of finding the most likely join plan between component queries is investigated. This is accomplished by leveraging the referential constraints available in the underlying multidatabase, or by approximating these constraints from the data when not available. This approximation is done using the information theoretic concept of conditional entropy. Furthermore, the most likely join plans are enhanced by the expansion of their projections and adding precision to their selection constraints by estimating the selection constraints that would be applied to these consolidations offline. Additionally, the extraction of a set of queries related to the same retrieval task from an ongoing sequence of incoming queries is investigated. A conditional random field model is trained to segment and label incoming query sequences. Finally, the candidate consolidations are re-encapsulated with a genetic programming approach to find simpler intentional descriptions that are extensionally equivalent to discover the original intent of the query. The dissertation explains and discusses all of the above operations and validates the methods developed with experimentation on synthesised and real-world data. The results are highly encouraging and verify that the accuracy, time performance, and scalability of the methods would make it possible to exploit query consolidation in production environments.", notes = "GP chapters 7, 8", } @Article{ACEVEDO:2020:ESA, author = "Nicolas Acevedo and Carlos Rey and Carlos Contreras-Bolton and Victor Parada", title = "Automatic design of specialized algorithms for the binary knapsack problem", journal = "Expert Systems with Applications", year = "2020", volume = "141", pages = "112908", keywords = "genetic algorithms, genetic programming, Automatic generation of algorithms, Binary knapsack problem, Hyperheuristic, Generative design of algorithms", ISSN = "0957-4174", URL = "http://www.sciencedirect.com/science/article/pii/S0957417419306268", DOI = "doi:10.1016/j.eswa.2019.112908", abstract = "Not all problem instances of a difficult combinatorial optimization problem have the same degree of difficulty for a given algorithm. Surprisingly, apparently similar problem instances may require notably different computational efforts to be solved. Few studies have explored the case that the algorithm that solves a combinatorial optimization problem is automatically designed. In consequence, the generation of the best algorithms may produce specialized algorithms according to the problem instances used during the constructive step. Following a constructive process based on genetic programming that combines heuristic components with an exact method, new algorithms for the binary knapsack problem are produced. We found that most of the automatically designed algorithms have better performance when solving instances of the same type used during construction, although the algorithms also perform well with other types of similar instances. The rest of the algorithms are partially specialized. We also found that the exact method that only solves a small knapsack problem has a key role in such results. When the algorithms are produced without considering such a method, the errors are higher. We observed this fact when the algorithms were constructed with a combination of instances from different types. These results suggest that the better the pre-classification of the instances of an optimization problem, the more specific and more efficient are the algorithms produced by the automatic generation of algorithms. Consequently, the method described in this article accelerates the search for efficient methods for NP-hard optimization problems", } @Article{ACHARYA:2020:PRL, author = "Divya Acharya and Shivani Goel and Rishi Asthana and Arpit Bhardwaj", title = "A novel fitness function in genetic programming to handle unbalanced emotion recognition data", journal = "Pattern Recognition Letters", volume = "133", pages = "272--279", year = "2020", ISSN = "0167-8655", DOI = "doi:10.1016/j.patrec.2020.03.005", URL = "http://www.sciencedirect.com/science/article/pii/S0167865520300830", keywords = "genetic algorithms, genetic programming, Emotion recognition, Fitness function, EEG, Fast Fourier transformation", abstract = "In the area of behavioral psychology, real-time emotion recognition by using physiological stimuli is an active topic of interest. This research considers the recognition of two class of emotions i.e., positive and negative emotions using EEG signals in response to happy, horror, sad, and neutral genres. In a noise-free framework for data acquisition of 50 participants, NeuroSky MindWave 2 is used. The dataset collected is unbalanced i.e., there are more instances of positive classes than negative ones. Therefore, accuracy is not a useful metric to assess the results of the unbalanced dataset because of biased results. So, the primary goal of this research is to address the issue of unbalanced emotion recognition dataset classification, for which we are proposing a novel fitness function known as Gap score (G score), which learns about both the classes by giving them equal importance and being unbiased. The genetic programming (GP) framework in which we implemented G score is named as G-score GP (GGP). The second goal is to assess how distinct genres affect human emotion recognition process and to identify an age group that is more active emotionally when their emotions are elicited. Experiments were conducted on EEG data acquired with a single-channel EEG device. We have compared the performance of GGP for the classification of emotions with state-of-the-art methods. The analysis shows that GGP provides 87.61percent classification accuracy by using EEG. In compliance with the self-reported feelings, brain signals of 26 to 35 years of age group provided the highest emotion recognition rate", } @Article{ACHARYA:2020:AA, author = "Divya Acharya and Anosh Billimoria and Neishka Srivastava and Shivani Goel and Arpit Bhardwaj", title = "Emotion recognition using fourier transform and genetic programming", journal = "Applied Acoustics", year = "2020", volume = "164", pages = "107260", month = jul, keywords = "genetic algorithms, genetic programming, Electroencephalogram, Fast Fourier Transform, Emotion recognition, Movie clips, Cinema Films", ISSN = "0003-682X", URL = "http://lrcdrs.bennett.edu.in:80/handle/123456789/1183", URL = "http://www.sciencedirect.com/science/article/pii/S0003682X19306954", DOI = "doi:10.1016/j.apacoust.2020.107260", abstract = "In cognitive science, the real-time recognition of humans emotional state is pertinent for machine emotional intelligence and human-machine interaction. Conventional emotion recognition systems use subjective feedback questionnaires, analysis of facial features from videos, and online sentiment analysis. This research proposes a system for real-time detection of emotions in response to emotional movie clips. These movie clips elicitate emotions in humans, and during that time, we have recorded their brain signals using Electroencephalogram (EEG) device and analyze their emotional state. This research work considered four class of emotions (happy, calm, fear, and sadness). This method leverages Fast Fourier Transform (FFT) for feature extraction and Genetic Programming (GP) for classification of EEG data. Experiments were conducted on EEG data acquired with a single dry electrode device NeuroSky Mind Wave 2. To collect data, a standardized database of 23 emotional Hindi film clips were used. All clips individually induce different emotions, and data collection was done based on these emotions elicited as the clips contain emotionally inductive scenes. Twenty participants took part in this study and volunteered for data collection. This system classifies four discrete emotions which are: happy, calm, fear, and sadness with an average of 89.14percent accuracy. These results demonstrated improvements in state-of-the-art methods and affirmed the potential use of our method for recognising these emotions", notes = "Also known as \cite{ACHARYA2020107260}", } @Article{ACHARYA:2021:ESA, author = "Divya Acharya and Nandana Varshney and Anindiya Vedant and Yashraj Saxena and Pradeep Tomar and Shivani Goel and Arpit Bhardwaj", title = "An enhanced fitness function to recognize unbalanced human emotions data", journal = "Expert Systems with Applications", volume = "166", pages = "114011", year = "2021", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2020.114011", URL = "https://www.sciencedirect.com/science/article/pii/S0957417420307843", keywords = "genetic algorithms, genetic programming, Emotion recognition, Fitness function, EEG, Fast Fourier Transformation, Unbalanced dataset", abstract = "In cognitive science and human-computer interaction, automatic human emotion recognition using physiological stimuli is a key technology. This research considers two-class (positive and negative) of emotions recognition using electroencephalogram (EEG) signals in response to an emotional clip from the genres happy, amusement, sad, and horror. This paper introduces an enhanced fitness function named as eD-score to recognize emotions using EEG signals. The primary goal of this research is to assess how genres affect human emotions. We also analyzed human behaviour based on age and gender responsiveness. We have compared the performance of Multilayer Perceptron (MLP), K-nearest neighbors (KNN), Support Vector Machine (SVM), D-score Genetic Programming (DGP), and enhanced D-score Genetic Programming (eDGP) for classification of emotions. The analysis shows that for two class of emotion eDGP provides classification accuracy as 83.33percent, 84.69percent, 85.88percent, and 87.61percent for 50-50, 60-40, 70-30, and 10-fold cross-validations. Generalizability and reliability of this approach is evaluated by applying the proposed approach to publicly available EEG datasets DEAP and SEED. When participants in this research are exposed to amusement genre, their reaction is positive emotion. In compliance with the self-reported feelings, brain signals of 26-35 years of age group provided the highest emotional identification. Among genders, females are more emotionally active as compared to males. These results affirmed the potential use of our method for recognizing emotions", } @InProceedings{Ackling:2011:GECCO, author = "Thomas Ackling and Bradley Alexander and Ian Grunert", title = "Evolving patches for software repair", booktitle = "GECCO '11: Proceedings of the 13th annual conference on Genetic and evolutionary computation", year = "2011", editor = "Natalio Krasnogor and Pier Luca Lanzi and Andries Engelbrecht and David Pelta and Carlos Gershenson and Giovanni Squillero and Alex Freitas and Marylyn Ritchie and Mike Preuss and Christian Gagne and Yew Soon Ong and Guenther Raidl and Marcus Gallager and Jose Lozano and Carlos Coello-Coello and Dario Landa Silva and Nikolaus Hansen and Silja Meyer-Nieberg and Jim Smith and Gus Eiben and Ester Bernado-Mansilla and Will Browne and Lee Spector and Tina Yu and Jeff Clune and Greg Hornby and Man-Leung Wong and Pierre Collet and Steve Gustafson and Jean-Paul Watson and Moshe Sipper and Simon Poulding and Gabriela Ochoa and Marc Schoenauer and Carsten Witt and Anne Auger", isbn13 = "978-1-4503-0557-0", pages = "1427--1434", keywords = "genetic algorithms, genetic programming, genetic improvement, APR, SBSE, Debugging, fault-repair, Python", month = "12-16 " # jul, organisation = "SIGEVO", address = "Dublin, Ireland", URL = "https://hdl.handle.net/2440/70777", DOI = "doi:10.1145/2001576.2001768", publisher = "ACM", publisher_address = "New York, NY, USA", size = "8 pages", abstract = "Defects are a major concern in software systems. Unsurprisingly, there are many tools and techniques to facilitate the removal of defects through their detection and localisation. However, there are few tools that attempt to repair defects. To date, evolutionary tools for software repair have evolved changes directly in the program code being repaired. In this work we describe an implementation: pyEDB, that encodes changes as a series of code modifications or patches. These modifications are evolved as individuals. We show pyEDB to be effective in repairing some small errors, including variable naming errors in Python programs. We also demonstrate that evolving patches rather than whole programs simplifies the removal of spurious errors.", notes = "Sofware bugs cost 2 10**10 dollar pa. Repairs 5 relational operators and wrong name. AST. tracing program execution. mod-tables like gramatical evolution. Tarantula. 32 bit GA. Examples: middleFunc and Facebook smallworld. Also known as \cite{2001768} GECCO-2011 A joint meeting of the twentieth international conference on genetic algorithms (ICGA-2011) and the sixteenth annual genetic programming conference (GP-2011)", } @Article{journals/ijprai/Acosta-MendozaMEA14, title = "Learning to Assemble Classifiers via Genetic Programming", author = "Niusvel Acosta-Mendoza and Alicia Morales-Reyes and Hugo Jair Escalante and Andres Gago Alonso", journal = "IJPRAI", year = "2014", number = "7", volume = "28", keywords = "genetic algorithms, genetic programming", bibdate = "2014-10-20", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/ijprai/ijprai28.html#Acosta-MendozaMEA14", URL = "http://dx.doi.org/10.1142/S0218001414600052", } @InCollection{Adamatzky:2017:miller, author = "Andrew Adamatzky and Simon Harding and Victor Erokhin and Richard Mayne and Nina Gizzie and Frantisek Baluska and Stefano Mancuso and Georgios Ch. Sirakoulis", title = "Computers from Plants We Never Made: Speculations", booktitle = "Inspired by Nature: Essays Presented to Julian F. Miller on the Occasion of his 60th Birthday", publisher = "Springer", year = "2017", editor = "Susan Stepney and Andrew Adamatzky", volume = "28", series = "Emergence, Complexity and Computation", chapter = "17", pages = "357--387", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-319-67996-9", DOI = "doi:10.1007/978-3-319-67997-6_17", abstract = "Plants are highly intelligent organisms. They continuously make distributed processing of sensory information, concurrent decision making and parallel actuation. The plants are efficient green computers per se. Outside in nature, the plants are programmed and hardwired to perform a narrow range of tasks aimed to maximize the plants ecological distribution, survival and reproduction. To persuade plants to solve tasks outside their usual range of activities, we must either choose problem domains which homomorphic to the plants natural domains or modify biophysical properties of plants to make them organic electronic devices. We discuss possible designs and prototypes of computing systems that could be based on morphological development of roots, interaction of roots, and analogue electrical computation with plants, and plant-derived electronic components. In morphological plant processors data are represented by initial configuration of roots and configurations of sources of attractants and repellents; results of computation are represented by topology of the roots network. Computation is implemented by the roots following gradients of attractants and repellents, as well as interacting with each other. Problems solvable by plant roots, in principle, include shortest-path, minimum spanning tree, Voronoi diagram, alpha-shapes, convex subdivision of concave polygons. Electrical properties of plants can be modified by loading the plants with functional nanoparticles or coating parts of plants of conductive polymers. Thus, we are in position to make living variable resistors, capacitors, operational amplifiers, multipliers, potentiometers and fixed-function generators. The electrically modified plants can implement summation, integration with respect to time, inversion, multiplication, exponentiation, logarithm, division. Mathematical and engineering problems to be solved can be represented in plant root networks of resistive or reaction elements. Developments in plant-based computing architectures will trigger emergence of a unique community of biologists, electronic engineering and computer scientists working together to produce living electronic devices which future green computers will be made of.", notes = "part of \cite{miller60book} https://link.springer.com/bookseries/10624", } @InProceedings{adamopoulos:1999:FMEPUGONN, author = "Adam V. Adamopoulos and Efstratios F. Georgopoulos and Spiridon D. Likothanassis and Photios A. Anninos", title = "Forecasting the MagnetoEncephaloGram (MEG) of Epileptic Patients Using Genetically Optimized Neural Networks", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "2", pages = "1457--1462", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "real world applications", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/RW-767.pdf", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/RW-767.ps", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InCollection{adams:2002:CSDPSAGP, author = "Thomas P. Adams", title = "Creation of Simple, Deadline, and Priority Scheduling Algorithms using Genetic Programming", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 2002", year = "2002", editor = "John R. Koza", pages = "1--10", address = "Stanford, California, 94305-3079 USA", month = jun, publisher = "Stanford Bookstore", keywords = "genetic algorithms, genetic programming", URL = "http://www.genetic-programming.org/sp2002/Adams.pdf", notes = "part of \cite{koza:2002:gagp} memory, SETMO..SETM4 ECJ8, iteration (over job queue) branch and selection branch, communicate via memory. Run time used throughout (ie by functions and terminals) to identify jobs (ie scheduling tasks). 32 tasks shortest job first", } @InProceedings{Addis:2014:IACAP, author = "Mark Addis and Peter D. Sozou and Peter C. Lane and Fernand Gobet", title = "Computational Scientific Discovery and Cognitive Science Theories", booktitle = "Computing and Philosophy: Selected Papers from IACAP 2014", year = "2016", editor = "Vincent C. Mueller", pages = "83--97", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-319-23291-1", URL = "http://eprints.lse.ac.uk/66168/", URL = "https://doi.org/10.1007/978-3-319-23291-1_6", DOI = "doi:10.1007/978-3-319-23291-1_6", abstract = "This study is concerned with processes for discovering new theories in science. It considers a computational approach to scientific discovery, as applied to the discovery of theories in cognitive science. The approach combines two ideas. First, a process-based scientific theory can be represented as a computer program. Second, an evolutionary computational method, genetic programming, allows computer programs to be improved through a process of computational trial and error. Putting these two ideas together leads to a system that can automatically generate and improve scientific theories. The application of this method to the discovery of theories in cognitive science is examined. Theories are built up from primitive operators. These are contained in a theory language that defines the space of possible theories. An example of a theory generated by this method is described. These results support the idea that scientific discovery can be achieved through a heuristic search process, even for theories involving a sequence of steps. However, this computational approach to scientific discovery does not eliminate the need for human input. Human judgement is needed to make reasonable prior assumptions about the characteristics of operators used in the theory generation process, and to interpret and provide context for the computationally generated theories.", notes = "http://www.lse.ac.uk/philosophy/events/rethinking-theory-construction-in-social-science/", } @InProceedings{Adegboye:2017:ieeeSSCI), author = "Adesola Adegboye and Michael Kampouridis and Colin G. Johnson", booktitle = "2017 IEEE Symposium Series on Computational Intelligence (SSCI)", title = "Regression genetic programming for estimating trend end in foreign exchange market", year = "2017", address = "Honolulu, HI, USA", month = "27 " # nov # "-1 " # dec, keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-5386-2727-3", DOI = "doi:10.1109/SSCI.2017.8280833", abstract = "Most forecasting algorithms use a physical time scale for studying price movement in financial markets, making the flow of physical time discontinuous. The use of a physical time scale can make companies oblivious to significant activities in the market, which poses a risk. Directional changes is a different and newer approach, which uses an event-based time scale. This approach summarises data into alternating trends called upward directional change and downward directional change. Each of these trends are further dismembered into directional change (DC) event and overshoot (OS) event. We present a genetic programming (GP) algorithm that evolves equations that express linear and non-linear relationships between the length of DC and OS events in a given dataset. This allows us to have an expectation when a trend will reverse, which can lead to increased profitability. This novel trend reversal estimation approach is then used as part of a DC-based trading strategy. We aim to appraise whether the new knowledge can lead to greater excess return. We assess the efficiency of the modified trading strategy on 250 different directional changes datasets from five different thresholds and five different currency pairs, consisting of intraday data from the foreign exchange (Forex) spot market. Results show that our algorithm is able to return profitable trading strategies and statistically outperform state-of-the-art financial trading strategies, such as technical analysis, buy and hold and other DC-based trading strategies.", notes = "Also known as \cite{8280833} https://www.ele.uri.edu/ieee-ssci2017/", } @Article{ADEGBOYE:2021:ESA, author = "Adesola Adegboye and Michael Kampouridis", title = "Machine learning classification and regression models for predicting directional changes trend reversal in {FX} markets", journal = "Expert Systems with Applications", year = "2021", volume = "173", month = "1 " # jul, pages = "114645", keywords = "genetic algorithms, genetic programming, Directional changes, Regression, Classification, Forex/FX, Machine learning", ISSN = "0957-4174", URL = "https://kar.kent.ac.uk/89886/1/Adegboye-INT2021_preprint.pdf", URL = "https://www.sciencedirect.com/science/article/pii/S0957417421000865", DOI = "doi:10.1016/j.eswa.2021.114645", code_url = "https://github.com/adesolaadegboye/SymbolicRegression", size = "15 pages", abstract = "Most forecasting algorithms in financial markets use physical time for studying price movements, making the flow of time discontinuous. The use of physical time scale can make traders oblivious to significant activities in the market, which poses a risk. Directional changes (DC) is an alternative approach that uses event-based time to sample data. In this work, we propose a novel DC-based framework, which uses machine learning algorithms to predict when a trend will reverse. This allows traders to be in a position to take an action before this happens and thus increase their profitability. We combine our approach with a novel DC-based trading strategy and perform an in-depth investigation, by applying it to 10-min data from 20 foreign exchange markets over a 10-month period. The total number of tested datasets is 1,000, which allows us to argue that our results can be generalised and are widely applicable. We compare our results to ten benchmarks (both DC and non-DC based, such as technical analysis and buy-and-hold). Our findings show that our proposed approach is able to return a significantly higher profit, as well as reduced risk, and statistically outperform the other trading strategies in a number of different performance metrics", notes = "School of Computing, University of Kent, Medway ME4 4AG, UK", } @PhdThesis{Adegboye:thesis, author = "Adesola Tolulope Noah Adegboye", title = "Estimating Directional Changes Trend Reversal in {Forex} Using Machine Learning", school = "University of Kent", year = "2022", address = "UK", month = mar, keywords = "genetic algorithms, genetic programming", URL = "https://kar.kent.ac.uk/94107/", URL = "https://kar.kent.ac.uk/94107/1/174thesis.pdf", DOI = "doi:10.22024/UniKent/01.02.94107", size = "209 pages", abstract = "Most forecasting algorithms use a physical time scale data to study price movement in financial markets by taking snapshots in fixed schedule, making the flow of time discontinuous. The use of a physical time scale can make traders oblivious to significant activities in the market, which poses risks. For example, currency risk, the risk that exchange rate will change. Directional changes is a different and newer approach of taking snapshot of the market, which uses an event-based time scale. This approach summarises data into alternating trends called upward directional change and downward directional change according to a change in price a trader considers to be significant, which is expressed as a threshold. The trends in the summary are split into directional change (DC) and overshoot (OS) events. In this work, we propose a novel DC-based framework, which uses machine learning algorithms to forecast when the next, alternate trend is expected to begin. First, we present a genetic programming (GP) algorithm that evolves equations that express linear and non-linear relationships between the length of DC and OS events in a given dataset. Awareness of DC event and OS event lengths provide traders with an idea of when DC trends are expected to reverse and thus take appropriate action to increase profit or mitigate risk. Second, DC trends can be categorised into two distinct types: (1) trends with OS events; and (2) trends without OS events(i.e. OS event length is 0). Trends with OS events are those that continue beyond a period when they were first observed and trends without OS event are others that ends as soon as they were observed. To further improve trend reversal estimation accuracy, we identified these two categorises using classification techniques and estimated OS event length for trends that belong in the first category. We appraised whether this new knowledge could lead to an even greater excess return. Third, our novel trend reversal estimation approach was then used as part of a novel genetic algorithm (GA) based trading strategy. The strategy embedded an optimised trend reversal forecasting algorithm that was based on trend reversal point forecasted by multiple thresholds. We assessed the efficiency of our framework (i.e., a novel trend reversal approach and an optimised trading strategy) by performing an in-depth investigation. To assess our approach and evaluate the extent to which it could be generalised in Forex markets, we used five tailored thresholds to create 1000 DC datasets from 10, monthly 10 minute physical time data of 20 major Forex markets (i.e 5 thresholds * 10 months * 20 currency pairs). We compared our results to six benchmarks techniques, both DC and non-DC based, such as technical analysis and buy-and-hold. Our findings showed that our proposed approach can return a significantly higher profit at reduced risk, and statistically outperformed the other trading strategies compareds in a number of different performance metrics.", notes = "KAR id:94107 p156 'using symbolic regression GP approach ... to discover more complex relationship ... led to improvements in DC trend reversal forecasting accuracy' 'increased trading returns at reduced risk' Supervisor: Fernando Otero and Michael Kampouridis (Essex)", } @Article{ADEYI:2021:AIEPR, author = "Abiola John Adeyi and Oladayo Adeyi and Emmanuel Olusola Oke and Olusegun Abayomi Olalere and Seun Oyelami and Akinola David Ogunsola", title = "Effect of varied fiber alkali treatments on the tensile strength of Ampelocissus cavicaulis reinforced polyester composites: Prediction, optimization, uncertainty and sensitivity analysis", journal = "Advanced Industrial and Engineering Polymer Research", volume = "4", number = "1", pages = "29--40", year = "2021", ISSN = "2542-5048", DOI = "doi:10.1016/j.aiepr.2020.12.002", URL = "https://www.sciencedirect.com/science/article/pii/S2542504820300580", keywords = "genetic algorithms, genetic programming, Response surface methodology, Multigene genetic programming, Oracle crystal ball, Uncertainty and sensitivity analysis", abstract = "Studies on modeling and optimization of alkali treatment, investigation of experimental uncertainty and sensitivity analysis of alkali treatment factors of natural fibers are important to effective natural fiber reinforced polymer composite development. In this contribution, response surface methodology (RSM) was employed to investigate and optimize the effect of varied treatment factors (sodium hydroxide concentration (NaOH) and soaking time (ST)) of the alkali treatment of Ampelocissus cavicaulis natural fiber (ACNF) on the tensile strength (TS) of alkali treated ACNF reinforced polyester composite. RSM and multi gene genetic programming (MGGP) were comparatively employed to model the alkali treatment. The best model was applied in Oracle Crystal Ball (OCB) to investigate the uncertainty of the treatment results and sensitivity of the treatment factors. Results showed that increased NaOH and ST increased the TS of the alkali treated ACNF reinforced polyester composite up to 28.3500 MPa before TS decreased. The coefficient of determination (R2) and root mean square error (RMSE) of RSM model were 0.8920 and 0.6528 while that of MGGP were 0.9144 and 0.5812. The optimum alkali treatment established by RSM was 6.23percent of NaOH at 41.99 h of ST to give a TS of 28.1800 MPa with a desirability of 0.9700. The TS of the validated optimum alkali treatment condition was 28.2200 MPa. The certainty of the experimental results was 71.2580percent. TS was 13.8000percent sensitive to NaOH and 86.2000percent sensitive to ST. This work is useful for effective polymer composite materials production to reduce the enormous material and energy losses that usually accompany the process", } @Article{ADEYI:2022:AEJ, author = "Oladayo Adeyi and Abiola J. Adeyi and Emmanuel O. Oke and Bernard I. Okolo and Abayomi O. Olalere and John A. Otolorin and Samuel Okhale and Abiola E. Taiwo and Sunday O. Oladunni and Kelechi N. Akatobi", title = "Process integration for food colorant production from Hibiscus sabdariffa calyx: A case of multi-gene genetic programming ({MGGP)} model and techno-economics", journal = "Alexandria Engineering Journal", volume = "61", number = "7", pages = "5235--5252", year = "2022", ISSN = "1110-0168", DOI = "doi:10.1016/j.aej.2021.10.049", URL = "https://www.sciencedirect.com/science/article/pii/S1110016821006931", keywords = "genetic algorithms, genetic programming, Heat assisted technology based process, Multi-gene genetic programming, Annual production rate, Unit production cost, Techno-economics, calyx", abstract = "This work presents an integrated heat-assisted extraction process for the production of crude anthocyanins powder (CAnysP) from Hibiscus sabdariffa calyx using SuperPro Designer. The influence of process scale-up (0.04 -1000L) and variables (temperature, time and ethanol proportion in solvent) were investigated by adopting a circumscribed central composite design on techno-economic parameters such as annual production rate (APR) and unit production cost (UPC) CAnysP. The individual runs in the CCCD were taken as different process scenario and simulated independently. Multi-gene genetic programming (MGGP) was further used to develop robust predictive models. The robustness of the model and sensitivity analysis were ascertained using the Monte Carlo simulation. The process scenario at 30 min, 30 degreeC, 50percent and 1000 L possessed the highest CAnysP APR and lowest UPC. MGGP- models predicted R2 = 0.9984 for CAnysP APR and R2 = 0.9643 for UPC and certainty (99.98percent for CAnysP APR and 98.47percent for UPC)", } @InProceedings{adhikari:2019:SCDA, author = "Alok Adhikari and Nibedita Adhikari and K. C. Patra", title = "Shear Force Analysis and Modeling for Discharge Estimation Using Numerical and {GP} for Compound Channels", booktitle = "Soft Computing in Data Analytics", year = "2019", publisher = "Springer", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/chapter/10.1007/978-981-13-0514-6_32", DOI = "doi:10.1007/978-981-13-0514-6_32", } @Article{adhikari:JIEIa, author = "Alok Adhikari and N. Adhikari and K. C. Patra", title = "Genetic Programming: A Complementary Approach for Discharge Modelling in Smooth and Rough Compound Channels", journal = "Journal of The Institution of Engineers (India): Series A", year = "2019", volume = "100", number = "3", pages = "395--405", month = sep, keywords = "genetic algorithms, genetic programming, FIS, ANFIS, GP", ISSN = "2250-2149", URL = "http://link.springer.com/article/10.1007/s40030-019-00367-x", DOI = "doi:10.1007/s40030-019-00367-x", size = "11 pages", abstract = "Use of genetic programming (GP) in the field of river engineering is rare. During flood when the water overflows beyond its main course known as floodplain encounters various obstacles through rough materials and vegetation. Again the flow behaviour becomes more complex in a compound channel section due to shear at different regions. Discharge results from the experimental channels for varying roughness surfaces, along with data from a compound river section, are used in the GP. Model equations are derived for prediction of discharge in the compound channel using five hydraulic parameters. Derived models are tested and compared with other soft computing techniques. Few performance parameters are used to evaluate all the approaches taken for analysis. From the sensitivity analysis, the effects of parameters responsible for the flow behaviour are inferred. GP is found to give the most potential results with the highest level of accuracy. This work aims to benefit the researchers studying machine learning approaches for application in stream flow analysis.", } @Article{vu29881, author = "Sajal Kumar Adhikary and Nitin Muttil and Abdullah Yilmaz", title = "Genetic programming-based ordinary Kriging for spatial interpolation of rainfall", journal = "Journal of Hydrologic Engineering", year = "2016", volume = "21", number = "2", month = feb, keywords = "genetic algorithms, genetic programming, rainfall data, management of water resource systems, missing values, programming", publisher = "American Society of Civil Engineers", URL = "https://vuir.vu.edu.au/29881/", URL = "https://ascelibrary.org/doi/10.1061/%28ASCE%29HE.1943-5584.0001300", DOI = "doi:10.1061/(ASCE)HE.1943-5584.0001300", abstract = "Rainfall data provide an essential input for most hydrologic analyses and designs for effective management of water resource systems. However, in practice, missing values often occur in rainfall data that can ultimately influence the results of hydrologic analysis and design. Conventionally, stochastic interpolation methods such as Kriging are the most frequently used approach to estimate the missing rainfall values where the variogram model that represents spatial correlations among data points plays a vital role and significantly impacts the performance of the methods. In the past, the standard variogram models in ordinary kriging were replaced with the universal function approximator-based variogram models, such as artificial neural networks (ANN). In the current study, applicability of genetic programming (GP) to derive the variogram model and use of this GP-derived variogram model within ordinary kriging for spatial interpolation was investigated. Developed genetic programming-based ordinary kriging (GPOK) was then applied for estimating the missing rainfall data at a rain gauge station using the historical rainfall data from 19 rain gauge stations in the Middle Yarra River catchment of Victoria, Australia. The results indicated that the proposed GPOK method outperformed the traditional ordinary kriging as well as the ANN-based ordinary kriging method for spatial interpolation of rainfall. Moreover, the GP-derived variogram model is shown to have advantages over the standard and ANN-derived variogram models. Therefore, the GP-derived variogram model seems to be a potential alternative to variogram models applied in the past and the proposed GPOK method is recommended as a viable option for spatial interpolation.", } @PhdThesis{vu35054, author = "Sajal Kumar Adhikary", title = "Optimal Design of a Rain Gauge Network to Improve Streamflow Forecasting", school = "College of Engineering and Science, Victoria University", year = "2017", address = "Melbourne, Australia", month = "20 " # mar, note = "This thesis includes 1 published article for which access is restricted due to copyright (Chapters 3, 4 (first paper). Details of access to these papers have been inserted in the thesis, replacing the articles themselves.", keywords = "genetic algorithms, genetic programming, rivers, water basins, streams, stream-flow simulation, modeling, water supply, spatial interpolation, genetic programming-based ordinary kriging, thesis by publication", URL = "https://vuir.vu.edu.au/35054/", URL = "https://vuir.vu.edu.au/35054/7/ADHIKARY%20Sajal-thesis_Redacted.pdf", size = "225 pages", abstract = "Enhanced streamflow forecasting has always been an important task for researchers and water resources managers. However, streamflow forecasting is often challenging owing to the complexity of hydrologic systems. The accuracy of streamflow forecasting mainly depends on the input data, especially rainfall as it constitutes the key input in transforming rainfall into runoff. This emphasizes the need for incorporating accurate rainfall input in streamflow forecasting models in order to achieve enhanced streamflow forecasting. Based on past research, it is well-known that an optimal rain gauge network is necessary to provide high quality rainfall estimates. Therefore, this study focused on the optimal design of a rain gauge network and integration of the optimal network-based rainfall input in artificial neural network (ANN) models to enhance the accuracy of streamflow forecasting. The Middle Yarra River catchment in Victoria, Australia was selected as the case study catchment, since the management of water resources in the catchment is of great importance to the majority of Victorians. The study had three components. First, an evaluation of existing Kriging methods and universal function approximation techniques such as genetic programming (GP) and ANN were performed in terms of their potentials and suitability for the enhanced spatial estimation of rainfall. The evaluation confirmed that the fusion of GP and ordinary kriging is highly effective for the improved estimation of rainfall and the ordinary cokriging using elevation can enhance the spatial estimation of rainfall. Second, the design of an optimal rain gauge network was undertaken for the case study catchment using the kriging-based geostatistical approach based on the variance reduction framework. It is likely that an existing rain gauge network may consist of redundant stations, which have no contribution to the network performance for providing quality rainfall estimates. Therefore, the optimal network was achieved through optimal placement of additional stations (network augmentation) as well as eliminating or optimally relocating of redundant stations (network rationalization). In order to take the rainfall variability caused by climatic factors like El Nino Southern Oscillation into account, the network was designed using rainfall records for both El Nino and La Nina periods. The rain gauge network that gives the improved estimates of areal average and point rainfalls for both the El Nino and La Nina periods was selected as the optimal network. It was found that the optimal network outperformed the existing one in estimating the spatiotemporal estimates of areal average and point rainfalls. Additionally, optimal positioning of redundant stations was found to be highly effective to achieve the optimal rain gauge network. Third, an ANN-based enhanced streamflow forecasting approach was demonstrated, which incorporated the optimal rain gauge network-based input instead of using input from an existing non-optimal network to achieve the enhanced streamflow forecasting. The approach was found to be highly effective in improving the accuracy of stream-flow forecasting, particularly when the current operational rain gauge network is not an optimal one. For example, it was found that use of the optimal rain gauge network-based input results in the improvement of streamflow forecasting accuracy by 7.1percent in terms of normalised root mean square error (NRMSE) compared to the current rain gauge network based-input. Further improvement in streamflow forecasting was achieved through augmentation of the optimal network by incorporating additional fictitious rain gauge stations. The fictitious stations were added in sub-catchments that were delineated based on the digital elevation model. It was evident from the results that 18.3percent improvement in streamflow forecasting accuracy was achieved in terms of NRMSE using the augmented optimal rain gauge network-based input compared to the current rain gauge network-based input. The ANN-based input selection technique that was employed in this study for streamflow forecasting offers a viable technique for significant input variables selection as this technique is capable of learning problems involving very non-linear and complex data.", notes = "pii 'The evaluation confirmed that the fusion of GP and ordinary kriging is highly effective for the improved estimation of rainfall' Supervisor: Nitin Muttil", } @Article{Adib:2021:WRM, author = "Arash Adib and Arash Zaerpour and Ozgur Kisi and Morteza Lotfirad", title = "A Rigorous Wavelet-Packet Transform to Retrieve Snow Depth from {SSMIS} Data and Evaluation of its Reliability by Uncertainty Parameters", journal = "Water Resources Management", year = "2021", volume = "35", pages = "2723--2740", month = jul, keywords = "genetic algorithms, genetic programming, gene expression programming, passive microwave, special sensor microwave imager sounder, snow depth retrieval, discrete wavelet transform, wavelet-packet transform", publisher = "springer", bibsource = "OAI-PMH server at oai.repec.org", identifier = "RePEc:spr:waterr:v:35:y:2021:i:9:d:10.1007_s11269-021-02863-x", oai = "oai:RePEc:spr:waterr:v:35:y:2021:i:9:d:10.1007_s11269-021-02863-x", URL = "http://link.springer.com/10.1007/s11269-021-02863-x", DOI = "doi:10.1007/s11269-021-02863-x", abstract = "This study demonstrates the application of wavelet transform comprising discrete wavelet transform, maximum overlap discrete wavelet transform (MODWT), and multiresolution-based MODWT (MODWT-MRA), as well as wavelet packet transform (WP), coupled with artificial intelligence (AI)-based models including multi-layer perceptron, radial basis function, adaptive neuro-fuzzy inference system (ANFIS), and gene expression programming to retrieve snow depth (SD) from special sensor microwave imager sounder obtained from the national snow and ice data center. Different mother wavelets were applied to the passive microwave (PM) frequencies; afterward, the dominant resultant decomposed subseries comprising low frequencies (approximations) and high frequencies (details) were detected and inserted into the AI-based models. The results indicated that the WP coupled with ANFIS (WP-ANFIS) outperformed the other studied models with the determination coefficient of 0.988, root mean square error of 3.458 cm, mean absolute error of 2.682 cm, and Nash--Sutcliffe efficiency of 0.987 during testing period. The final verification also confirmed that the WP is a promising pre-processing technique to improve the accuracy of the AI-based models in SD evaluation from PM data.", } @InProceedings{Adkins:2023:evomusart, author = "Sara Adkins and Pedro Sarmento and Mathieu Barthet", title = "{LooperGP}: A Loopable Sequence Model for Live Coding Performance using GuitarPro Tablature", booktitle = "12th International Conference on Artificial Intelligence in Music, Sound, Art and Design, EvoMusArt 2023", year = "2023", month = apr # " 12-14", editor = "Colin Johnson and Nereida Rodriguez-Fernandez and Sergio M. Rebelo", series = "LNCS", volume = "13988", publisher = "Springer Verlag", address = "Brno, Czech Republic", pages = "3--19", organisation = "EvoStar, Species", keywords = "genetic algorithms, genetic programming, Controllable Music Generation, Sequence Models, Live Coding, Transformers, AI Music, Loops, Guitar Tabs", isbn13 = "978-3-031-29956-8", DOI = "doi:10.1007/978-3-031-29956-8_1", data_url = "https://github.com/dada-bots/dadaGP", size = "17 pages", abstract = "Despite their impressive offline results, deep learning models for symbolic music generation are not widely used in live performances due to a deficit of musically meaningful control parameters and a lack of structured musical form in their outputs. To address these issues we introduce LooperGP, a method for steering a Transformer-XL model towards generating loopable musical phrases of a specified number of bars and time signature, enabling a tool for live coding performances. We show that by training LooperGP on a dataset of 93681 musical loops extracted from the DadaGP dataset [Data GuitarPro], we are able to steer its generative output towards generating three times as many loopable phrases as our baseline. In a subjective listening test conducted by 31 participants, LooperGP loops achieved positive median ratings in originality, musical coherence and loop smoothness, demonstrating its potential as a performance tool.", notes = "http://www.evostar.org/2023/ EvoMusArt2023 held in conjunction with EuroGP'2023, EvoCOP2023 and EvoApplications2023", } @Misc{adler2021improving, author = "Felix Adler and Gordon Fraser and Eva Gruendinger and Nina Koerber and Simon Labrenz and Jonas Lerchenberger and Stephan Lukasczyk and Sebastian Schweikl", title = "Improving Readability of {Scratch} Programs with Search-based Refactoring", howpublished = "arXiv", year = "2021", month = "16 " # aug, keywords = "genetic algorithms, genetic programming, genetic improvement, SBSE", eprint = "2108.07114", URL = "https://arxiv.org/abs/2108.07114", size = "13 pages", abstract = "Block-based programming languages like Scratch have become increasingly popular as introductory languages for novices. These languages are intended to be used with a tinkering approach which allows learners and teachers to quickly assemble working programs and games, but this often leads to low code quality. Such code can be hard to comprehend, changing it is error-prone, and learners may struggle and lose interest. The general solution to improve code quality is to refactor the code. However, Scratch lacks many of the common abstraction mechanisms used when refactoring programs written in higher programming languages. In order to improve Scratch code, we therefore propose a set of atomic code transformations to optimise readability by (1) rewriting control structures and (2) simplifying scripts using the inherently concurrent nature of Scratch programs. By automating these transformations it is possible to explore the space of possible variations of Scratch programs. In this paper, we describe a multi-objective search-based approach that determines sequences of code transformations which improve the readability of a given Scratch program and therefore form refactorings. Evaluation on a random sample of 1000 Scratch programs demonstrates that the generated refactorings reduce complexity and entropy in 70.4percent of the cases, and 354 projects are improved in at least one metric without making any other metric worse. The refactored programs can help both novices and their teachers to improve their code.", notes = "p4 'we need the search to evolve sequences of refactorings that explain the changes' p10 'Solutions are transformed 10.1 times on average, and the most common transformations are Swap Statements, Merge Scripts and Split Scripts' p10 'our modification operators are designed to preserve the program semantics' Published as \cite{DBLP:conf/scam/AdlerFGKLLLS21} University of Passau, Germany", } @InProceedings{DBLP:conf/scam/AdlerFGKLLLS21, author = "Felix Adler and Gordon Fraser and Eva Gruendinger and Nina Koerber and Simon Labrenz and Jonas Lerchenberger and Stephan Lukasczyk and Sebastian Schweikl", title = "Improving Readability of {Scratch} Programs with Search-based Refactoring", booktitle = "21st IEEE International Working Conference on Source Code Analysis and Manipulation, SCAM 2021", year = "2021", pages = "120--130", address = "Luxembourg", month = sep # " 27-28", note = "16000 GP entry", keywords = "genetic algorithms, genetic programming, genetic improvement, grammatical evolution, SBSE, NSGA-II, LitterBox, JSON, refactoring, Java", isbn13 = "978-1-6654-4898-7", timestamp = "Sat, 09 Apr 2022 12:45:31 +0200", biburl = "https://dblp.org/rec/conf/scam/AdlerFGKLLLS21.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://arxiv.org/abs/2108.07114", URL = "https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9610643", DOI = "doi:10.1109/SCAM52516.2021.00023", code_url = "https://github.com/se2p/artifact-scam2021", video_url = "https://youtu.be/9ndMZvgEOVg", size = "11 pages", abstract = "Block-based programming languages like SCRATCH have become increasingly popular as introductory languages for novices. These languages are intended to be used with a tinkering approach which allows learners and teachers to quickly assemble working programs and games, but this often leads to low code quality. Such code can be hard to comprehend, changing it is error-prone, and learners may struggle and lose interest. The general solution to improve code quality is to refactor the code. However, SCRATCH lacks many of the common abstraction mechanisms used when refactoring programs written in higher programming languages. In order to improve SCRATCH code, we therefore propose a set of atomic code transformations to optimise readability by (1) rewriting control structures and (2) simplifying scripts using the inherently concurrent nature of SCRATCH programs. By automating these transformations it is possible to explore the space of possible variations of SCRATCH programs. In this paper, we describe a multi-objective search-based approach that determines sequences of code transformations which improve the readability of a given SCRATCH program and therefore form refactorings. Evaluation on a random sample of 1000 SCRATCH programs demonstrates that the generated refactorings reduce complexity and entropy in 70.4% of the cases, and 354 projects are improved in at least one metric without making any other metric worse. The refactored programs can help both novices and their teachers to improve their code.", notes = "Also known as \cite{ImprovingReadabilityScratch}. See also \cite{adler2021improving} '26 atomic code transformations' [to the AST]. 'We evaluate an implementation of this approach on a random sample of 1000 learners program'. '704 are improved with respect to complexity and entropy, and 354...' size, Halstead complexity, and Shannon entropy (based on program syntax). p122 'Inverse transformation' of the AST. control dependence graph. data dependence graph. 'forward-may dataflow analysis to identify which statements are time-dependent on which other statements' p124 'integer representation inspired by grammatical evolution' p126 'verify that the code transformations preserve the semantics' 'Applicable code transformations were found for all but 28 [of 1000] projects in our dataset.' Many uses of swap. p129 'The number of code transformations that do not change the program semantics found by our search is substantial' 'neutral program space'. 'explainability central' SCAM 2021 Also known as \cite{9610643}", } @InProceedings{adorni:1998:cpapc, author = "Giovanni Adorni and Federico Bergenti and Stefano Cagnoni", title = "A cellular-programming approach to pattern classification", booktitle = "Proceedings of the First European Workshop on Genetic Programming", year = "1998", editor = "Wolfgang Banzhaf and Riccardo Poli and Marc Schoenauer and Terence C. Fogarty", volume = "1391", series = "LNCS", pages = "142--150", address = "Paris", publisher_address = "Berlin", month = "14-15 " # apr, publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-64360-5", DOI = "doi:10.1007/BFb0055934", abstract = "In this paper we discuss the capability of the cellular programming approach to produce non-uniform cellular automata performing two-dimensional pattern classification. More precisely, after an introduction to the evolutionary cellular automata model, we describe a general approach suitable for designing cellular classifiers. The approach is based on a set of non-uniform cellular automata performing specific classification tasks, which have been designed by means of a cellular evolutionary algorithm. The proposed approach is discussed together with some preliminary results obtained on a benchmark data set consisting of car-plate digits.", notes = "EuroGP'98", affiliation = "University of Parma Department of Computer Engineering viale delle Scienze 43100 Parma Italy viale delle Scienze 43100 Parma Italy", } @InProceedings{adorni:1999:GPgkcsrcmsc, author = "Giovanni Adorni and Stefano Cagnoni and Monica Mordonini", title = "Genetic Programming of a Goal-Keeper Control Strategy for the RoboCup Middle Size Competition", booktitle = "Genetic Programming, Proceedings of EuroGP'99", year = "1999", editor = "Riccardo Poli and Peter Nordin and William B. Langdon and Terence C. Fogarty", volume = "1598", series = "LNCS", pages = "109--119", address = "Goteborg, Sweden", publisher_address = "Berlin", month = "26-27 " # may, organisation = "EvoNet", publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-65899-8", DOI = "doi:10.1007/3-540-48885-5_9", abstract = "In this paper we describe a genetic programming approach to the design of a motion-control strategy for a goalkeeper robot created to compete in the RoboCup99, the robot soccer world championships which have been held yearly since 1997, as part of the Italian middle size robot team (ART, Azzurra Robot Team). The evolved program sends a motion command to the robot, based on the analysis of information received from a human-coded vision sub-system. The preliminary results obtained on a simulator are encouraging. They suggest that even using very simple fitness functions and training sets including only a small sub-set of the situations that the goalkeeper is required to tackle, it is possible to evolve a complex behaviour that permits the goalkeeper to perform well also in more challenging real-world conditions.", notes = "EuroGP'99, part of \cite{poli:1999:GP} Robot goalkeeper (.4m) controlled by twin cameras using GP. Able to intercept football sometimes.", } @InProceedings{oai:CiteSeerPSU:539182, author = "Giovanni Adorni and Stefano Cagnoni and Monica Mordonini", title = "Efficient low-level vision program design using Sub-machine-code Genetic Programming", booktitle = "AIIA 2002, Workshop sulla Percezione e Visione nelle Macchine", year = "2002", editor = "Marco Gori", address = "Siena, Italy", month = "10-13 " # sep, keywords = "genetic algorithms, genetic programming", citeseer-isreferencedby = "oai:CiteSeerPSU:127480; oai:CiteSeerPSU:236266; oai:CiteSeerPSU:154480; oai:CiteSeerPSU:124779; oai:CiteSeerPSU:98673; oai:CiteSeerPSU:519310; oai:CiteSeerPSU:493558; oai:CiteSeerPSU:151056; oai:CiteSeerPSU:128026; oai:CiteSeerPSU:195245; oai:CiteSeerPSU:154216; oai:CiteSeerPSU:198970; oai:CiteSeerPSU:98326; oai:CiteSeerPSU:197064; oai:CiteSeerPSU:88615; oai:CiteSeerPSU:200149; oai:CiteSeerPSU:299112", citeseer-references = "oai:CiteSeerPSU:70349; oai:CiteSeerPSU:329358", annote = "The Pennsylvania State University CiteSeer Archives", description = "Sub-machine-code Genetic Programming (SmcGP) is a variant of GP aimed at exploiting the intrinsic parallelism of sequential CPUs.", language = "en", oai = "oai:CiteSeerPSU:539182", rights = "unrestricted", URL = "http://www-dii.ing.unisi.it/aiia2002/paper/PERCEVISIO/adorni-aiia02.pdf", URL = "http://citeseer.ist.psu.edu/539182.html", size = "8 pages", abstract = "Sub-machine-code Genetic Programming (SmcGP) is a variant of GP aimed at exploiting the intrinsic parallelism of sequential CPUs. The paper describes an approach to low-level vision algorithm design for real-time applications by means of Sub-machine-code Genetic Programming(SmcGP), a variant of GP aimed at exploiting the intrinsic parallelism of sequential CPUs. The SmcGPbased design of two processing modules of a license-plate recognition system is taken into consideration as a case study to show the potential of the approach. The paper reports results obtained in recognizing the very low-resolution binary patterns that have to be classified in such an application along with preliminary results obtained using SmcGP to design a license-plate extraction algorithm.", notes = "http://www-dii.ing.unisi.it/aiia2002/paper.htm", } @InProceedings{adorni:2001:wsc6, author = "Giovanni Adorni and Stefano Cagnoni", title = "Design of Explicitly or Implicitly Parallel Low-resolution Character Recognition Algorithms by Means of Genetic Programming", booktitle = "Soft Computing and Industry Recent Applications", year = "2001", editor = "Rajkumar Roy and Mario K{\"o}ppen and Seppo Ovaska and Takeshi Furuhashi and Frank Hoffmann", pages = "387--398", month = "10--24 " # sep, publisher = "Springer-Verlag", note = "Published 2002", keywords = "genetic algorithms, genetic programming", ISBN = "1-85233-539-4", URL = "https://link.springer.com/book/10.1007/978-1-4471-0123-9", URL = "http://www.amazon.co.uk/Soft-Computing-Industry-Recent-Applications/dp/1852335394", notes = "WSC6 March 2020 hardcover out of print, available as softcover. ", } @Misc{oai:arXiv.org:1410.0532, title = "Automated conjecturing of {Frobenius} numbers via grammatical evolution", note = "Comment: 8 pages, 2 tables; added a clear introduction, otherwise reduced text significantly", author = "Nikola Adzaga", year = "2014", month = feb # "~17", keywords = "genetic algorithms, genetic programming, grammatical evolution, mathematics, number theory, mathematics, combinatorics", bibsource = "OAI-PMH server at export.arxiv.org", oai = "oai:arXiv.org:1410.0532", URL = "http://arxiv.org/abs/1410.0532", abstract = "Conjecturing formulae and other symbolic relations occurs frequently in number theory and combinatorics. If we could automate conjecturing, we could benefit not only from speeding up, but also from finding conjectures previously out of our grasp. Grammatical evolution, a genetic programming technique, can be used for automated conjecturing in mathematics. Concretely, this work describes how one can interpret the Frobenius problem as a symbolic regression problem, and then apply grammatical evolution to it. In this manner, a few formulas for Frobenius numbers of specific quadruples were found automatically. The sketch of the proof for one conjectured formula, using lattice point enumeration method, is provided as well. Same method can easily be used on other problems to speed up and enhance the research process.", notes = "See also \cite{Adzaga:2017:EM} Faculty of Civil Engineering, University of Zagreb", } @Article{Adzaga:2017:EM, author = "Nikola Adzaga", title = "Automated Conjecturing of {Frobenius} Numbers via Grammatical Evolution", journal = "Experimental Mathematics", year = "2017", volume = "26", number = "2", pages = "247--252", keywords = "genetic algorithms, genetic programming, grammatical evolution, automated conjecturing, Frobenius problem", ISSN = "1058-6458", publisher = "Taylor \& Francis", DOI = "doi:10.1080/10586458.2016.1175393", size = "6 pages", abstract = "Conjecturing formulas and other symbolic relations occurs frequently in number theory and combinatorics. If we could automate conjecturing, we could benefit not only from faster conjecturing but also from finding conjectures previously out of our grasp. Grammatical evolution (GE), a genetic programming technique, can be used for automated conjecturing in mathematics. Concretely, this work describes how one can interpret the Frobenius problem as a symbolic regression problem, and then apply GE to it. In this manner, a few formulas for Frobenius numbers of specific quadruples were found automatically. The sketch of the proof of one conjectured formula, using lattice point enumeration method, is provided as well. The same method can easily be used on other problems to speed up and enhance the research process.", notes = "See also \cite{oai:arXiv.org:1410.0532} Department of Mathematics, Faculty of Civil Engineering, University of Zagreb, Zagreb, Croatia", } @InProceedings{Aenugu:2019:GECCO, author = "Sneha Aenugu and Lee Spector", title = "Lexicase selection in learning classifier systems", booktitle = "GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference", year = "2019", editor = "Manuel Lopez-Ibanez and Thomas Stuetzle and Anne Auger and Petr Posik and Leslie {Peprez Caceres} and Andrew M. Sutton and Nadarajen Veerapen and Christine Solnon and Andries Engelbrecht and Stephane Doncieux and Sebastian Risi and Penousal Machado and Vanessa Volz and Christian Blum and Francisco Chicano and Bing Xue and Jean-Baptiste Mouret and Arnaud Liefooghe and Jonathan Fieldsend and Jose Antonio Lozano and Dirk Arnold and Gabriela Ochoa and Tian-Li Yu and Holger Hoos and Yaochu Jin and Ting Hu and Miguel Nicolau and Robin Purshouse and Thomas Baeck and Justyna Petke and Giuliano Antoniol and Johannes Lengler and Per Kristian Lehre", isbn13 = "978-1-4503-6111-8", pages = "356--364", address = "Prague, Czech Republic", DOI = "doi:10.1145/3321707.3321828", publisher = "ACM", publisher_address = "New York, NY, USA", month = "13-17 " # jul, organisation = "SIGEVO", keywords = "genetic algorithms, LCS, Learning Classifier Systems, Parent Selection, Lexicase Selection", size = "9 pages", abstract = "The lexicase parent selection method selects parents by considering performance on individual data points in random order instead of using a fitness function based on an aggregated data accuracy. While the method has demonstrated promise in genetic programming and more recently in genetic algorithms, its applications in other forms of evolutionary machine learning have not been explored. In this paper, we investigate the use of lexicase parent selection in Learning Classifier Systems (LCS) and study its effect on classification problems in a supervised setting. We further introduce a new variant of lexicase selection, called batch-lexicase selection, which allows for the tuning of selection pressure. We compare the two lexicase selection methods with tournament and fitness proportionate selection methods on binary classification problems. We show that batch-lexicase selection results in the creation of more generic rules which is favourable for generalization on future data. We further show that batch-lexicase selection results in better generalization in situations of partial or missing data.", notes = "Does not appear to be GP? Also known as \cite{3321828} GECCO-2019 A Recombination of the 28th International Conference on Genetic Algorithms (ICGA) and the 24th Annual Genetic Programming Conference (GP)", } @InProceedings{Affenzeller:2005:ICANNGA, author = "M. Affenzeller and S. Wagner", title = "Offspring Selection: A New Self-Adaptive Selection Scheme for Genetic Algorithms", booktitle = "Proceedings of the seventh International Conference Adaptive and Natural Computing Algorithms", year = "2005", editor = "Bernardete Ribeiro and Rudolf F. Albrecht and Andrej Dobnikar and David W. Pearson and Nigel C. Steele", pages = "218--221", address = "Coimbra, Portugal", month = "21-23 " # mar, publisher = "Springer", keywords = "genetic algorithms, genetic programming, OS-GP", isbn13 = "978-3-211-24934-5", URL = "https://link.springer.com/chapter/10.1007/3-211-27389-1_52", URL = "https://doi.org/10.1007/b138998", DOI = "doi:10.1007/3-211-27389-1_52", abstract = "In terms of goal orientedness, selection is the driving force of Genetic Algorithms (GAs). In contrast to crossover and mutation, selection is completely generic, i.e. independent of the actually employed problem and its representation. GA-selection is usually implemented as selection for reproduction (parent selection). In this paper we propose a second selection step after reproduction which is also absolutely problem independent. This self-adaptive selection mechanism, which will be referred to as offspring selection, is closely related to the general selection model of population genetics. As the problem- and representation-specific implementation of reproduction in GAs (crossover) is often critical in terms of preservation of essential genetic information, offspring selection has proven to be very suited for improving the global solution quality and robustness concerning parameter settings and operators of GAs in various fields of applications. The experimental part of the paper discusses the potential of the new selection model exemplarily on the basis of standardized real-valued test functions in high dimensions", notes = "\cite{DBLP:conf/eurocast/BurlacuAKKW17} gives this as reference for OS-GP http://icannga05.dei.uc.pt/", } @Book{Affenzeller:GAGP, author = "Michael Affenzeller and Stephan Winkler and Stefan Wagner and Andreas Beham", title = "Genetic Algorithms and Genetic Programming: Modern Concepts and Practical Applications", publisher = "CRC Press", year = "2009", series = "Numerical Insights", address = "Singapore", keywords = "genetic algorithms, genetic programming", ISBN = "1-58488-629-3", URL = "http://gagp2009.heuristiclab.com/", URL = "http://www.crcpress.com/product/isbn/9781584886297", abstract = "Genetic Algorithms and Genetic Programming: Modern Concepts and Practical Applications discusses algorithmic developments in the context of genetic algorithms (GAs) and genetic programming (GP). It applies the algorithms to significant combinatorial optimisation problems and describes structure identification using HeuristicLab as a platform for algorithm development. The book focuses on both theoretical and empirical aspects. The theoretical sections explore the important and characteristic properties of the basic GA as well as main characteristics of the selected algorithmic extensions developed by the authors. In the empirical parts of the text, the authors apply GAs to two combinatorial optimisation problems: the traveling salesman and capacitated vehicle routing problems. To highlight the properties of the algorithmic measures in the field of GP, they analyze GP-based nonlinear structure identification applied to time series and classification problems. Written by core members of the HeuristicLab team, this book provides a better understanding of the basic workflow of GAs and GP, encouraging readers to establish new bionic, problem-independent theoretical concepts. By comparing the results of standard GA and GP implementation with several algorithmic extensions, it also shows how to substantially increase achievable solution quality.", notes = "Reviewed in \cite{Pappa:2009:GPEM}. My copy missing pages i to vi. ", size = "379 pages", } @Article{Affenzeller:2010:IJSPM, title = "Effective allele preservation by offspring selection: an empirical study for the {TSP}", author = "Michael Affenzeller and Stefan Wagner and Stephan M. Winkler", journal = "International Journal of Simulation and Process Modelling", year = "2010", month = apr # "~11", volume = "6", number = "1", pages = "29--39", keywords = "genetic algorithms, genetic programming, soft computing, evolutionary computation, GAs selection, self adaptation, population genetics, evolution strategies, modelling, allele preservation, offspring selection, travelling salesman problem", ISSN = "1740-2131", URL = "https://pure.fh-ooe.at/en/publications/effective-allele-preservation-by-offspring-selection-an-empirical-2", URL = "http://www.inderscience.com/link.php?id=32655", DOI = "doi:10.1504/IJSPM.2010.032655", language = "eng", publisher = "Inderscience Publishers", abstract = "The basic selection ideas of the different representatives of evolutionary algorithms are sometimes quite diverse. The selection concept of Genetic Algorithms (GAs) and Genetic Programming (GP) is basically realised by the selection of above-average parents for reproduction, whereas Evolution Strategies (ES) use the fitness of newly evolved offspring as the basis for selection (survival of the fittest due to birth surplus). This contribution considers aspects of population genetics and ES in order to propose an enhanced and generic selection model for GAs which is able to preserve the alleles which are part of a high quality solution. Some selected aspects of these enhanced techniques are discussed exemplary on the basis of the Travelling Salesman Benchmark (TSP) problem instances.", bibsource = "OAI-PMH server at www.inderscience.com", notes = "GA rather than GP? Also http://www.liophant.org/i3m/i3m2008/", } @InProceedings{2453, author = "M. Affenzeller and C. Fischer and G. K. Kronberger and S. M. Winkler and S. Wagner", title = "New Genetic Programming Hypothesis Search Strategies for Improving the Interpretability in Medical Data Mining Applications", booktitle = "Proccedings of 23rd IEEE European Modeling \& Simulation Symposium EMSS 2011", year = "2011", address = "Roma, Italy", month = sep, URL = "http://research.fh-ooe.at/files/publications/2453_EMSS_2011_Affenzeller.pdf", keywords = "genetic algorithms, genetic programming", } @InProceedings{Affenzeller:2012:EMSS, author = "Michael Affenzeller and Stephan M. Winkler and Stefan Forstenlechner and Gabriel Kronberger and Michael Kommenda and Stefan Wagner and Herbert Stekel", title = "Enhanced Confidence Interpretations of GP Based Ensemble Modeling Results", booktitle = "The 24th European Modeling and Simulation Symposium, EMSS 2012", year = "2012", editor = "Emilio Jimenez and Boris Sokolov", pages = "340--345", address = "Vienna, Austria", month = sep # ", 19-21", keywords = "genetic algorithms, genetic programming, data mining, ensemble modelling, medical data analysis", URL = "http://research.fh-ooe.at/en/publication/2935", URL = "http://research.fh-ooe.at/files/publications/2935_EMSS_2012_Affenzeller.pdf", size = "6 pages", abstract = "In this paper we describe the integration of ensemble modelling into genetic programming based classification and discuss concepts how to use genetic programming specific features for achieving new confidence indicators that estimate the trustworthiness of predictions. These new concepts are tested on a real world dataset from the field of medical diagnosis for cancer prediction where the trustworthiness of modeling results is of highest importance", notes = "EMSS_76 http://www.msc-les.org/conf/emss2012/index.htm http://www.m-s-net.org/conf/i3m2012_program.pdf University of Applied Sciences Upper Austria; General Hospital Linz Central Laboratory - Austria", } @InProceedings{Affenzeller:2013:EUROCAST, author = "Michael Affenzeller and Stephan M. Winkler and Herbert Stekel and Stefan Forstenlechner and Stefan Wagner", title = "Improving the Accuracy of Cancer Prediction by Ensemble Confidence Evaluation", booktitle = "Computer Aided Systems Theory - EUROCAST 2013", year = "2013", editor = "Roberto Moreno-Diaz and Franz Pichler and Alexis Quesada-Arencibia", volume = "8111", series = "Lecture Notes in Computer Science", pages = "316--323", address = "Las Palmas de Gran Canaria, Spain", month = feb # " 10-15", publisher = "Springer", note = "Revised Selected Papers, Part I", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-53855-1", language = "English", URL = "http://dx.doi.org/10.1007/978-3-642-53856-8_40", DOI = "doi:10.1007/978-3-642-53856-8_40", size = "8 pages", abstract = "This paper discusses a novel approach for the prediction of breast cancer, melanoma and cancer in the respiratory system using ensemble modelling techniques. For each type of cancer, a set of unequally complex predictors are learnt by symbolic classification based on genetic programming. In addition to standard ensemble modeling, where the prediction is based on a majority voting of the prediction models, two confidence parameters are used which aim to quantify the trustworthiness of each single prediction based on the clearness of the majority voting. Based on the calculated confidence of each ensemble prediction, predictions might be considered uncertain. The experimental part of this paper discusses the increase of accuracy that can be obtained for those samples which are considered trustable depending on the ratio of predictions that are considered trustable.", } @InCollection{Affenzeller:2013:GPTP, author = "Michael Affenzeller and Stephan M. Winkler and Gabriel Kronberger and Michael Kommenda and Bogdan Burlacu and Stefan Wagner", title = "Gaining Deeper Insights in Symbolic Regression", booktitle = "Genetic Programming Theory and Practice XI", year = "2013", series = "Genetic and Evolutionary Computation", editor = "Rick Riolo and Jason H. Moore and Mark Kotanchek", publisher = "Springer", chapter = "10", pages = "175--190", address = "Ann Arbor, USA", month = "9-11 " # may, keywords = "genetic algorithms, genetic programming, Symbolic regression, Algorithm analysis, Population diversity Building block analysis, Genealogy, Variable networks", isbn13 = "978-1-4939-0374-0", DOI = "doi:10.1007/978-1-4939-0375-7_10", abstract = "A distinguishing feature of symbolic regression using genetic programming is its ability to identify complex nonlinear white-box models. This is especially relevant in practice where models are extensively scrutinised in order to gain knowledge about underlying processes. This potential is often diluted by the ambiguity and complexity of the models produced by genetic programming. In this contribution we discuss several analysis methods with the common goal to enable better insights in the symbolic regression process and to produce models that are more understandable and show better generalisation. In order to gain more information about the process we monitor and analyse the progresses of population diversity, building block information, and even more general genealogy information. Regarding the analysis of results, several aspects such as model simplification, relevance of variables, node impacts, and variable network analysis are presented and discussed.", notes = " Part of \cite{Riolo:2013:GPTP} published after the workshop in 2013", } @InProceedings{6339, author = "Michael Affenzeller and Bogdan Burlacu and Stephan M. Winkler and Michael Kommenda and Gabriel K. Kronberger and Stefan Wagner", title = "Offspring Selection Genetic Algorithm Revisited: Improvements in Efficiency by Early Stopping Criteria in the Evaluation of Unsuccessful Individuals", booktitle = "16th International Conference on Computer Aided Systems Theory, EUROCAST 2017", year = "2017", editor = "Roberto Moreno-Diaz and Franz Pichler and Alexis Quesada-Arencibia", volume = "10671", series = "Lecture Notes in Computer Science", pages = "424--431", address = "Las Palmas de Gran Canaria, Spain", month = feb, publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-319-74718-7", DOI = "doi:10.1007/978-3-319-74718-7_51", URL = "https://link.springer.com/chapter/10.1007/978-3-319-74718-7_51", abstract = "This paper proposes some algorithmic extensions to the general concept of offspring selection which itself is an algorithmic extension of genetic algorithms and genetic programming. Offspring selection is characterized by the fact that many offspring solution candidates will not participate in the ongoing evolutionary process if they do not achieve the success criterion. The algorithmic enhancements proposed in this contribution aim to early estimate if a solution candidate will not be accepted based on partial solution evaluation. The qualitative characteristics of offspring selection are not affected by this means. The discussed variant of offspring selection is analysed for several symbolic regression problems with offspring selection genetic programming. The achievable gains in terms of efficiency are remarkable especially for large data-sets.", } @InProceedings{Affenzeller:2017:GECCO, author = "Michael Affenzeller and Stephan M. Winkler and Bogdan Burlacu and Gabriel Kronberger and Michael Kommenda and Stefan Wagner", title = "Dynamic Observation of Genotypic and Phenotypic Diversity for Different Symbolic Regression {GP} Variants", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference Companion", series = "GECCO '17", year = "2017", isbn13 = "978-1-4503-4939-0", address = "Berlin, Germany", pages = "1553--1558", size = "6 pages", URL = "http://doi.acm.org/10.1145/3067695.3082530", DOI = "doi:10.1145/3067695.3082530", acmid = "3082530", publisher = "ACM", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, genetic and phenotypic diversity, offspring selection, population dynamics, symbolic regression", month = "15-19 " # jul, abstract = "Understanding the relationship between selection, genotype-phenotype map and loss of population diversity represents an important step towards more effective genetic programming (GP) algorithms. This paper describes an approach to capture dynamic changes in this relationship. We analyse the frequency distribution of points in the diversity plane defined by structural and semantic similarity measures. We test our methodology using standard GP (SGP) on a number of test problems, as well as Offspring Selection GP (OS-GP), an algorithmic flavour where selection is explicitly focused towards adaptive change. We end with a discussion about the implications of diversity maintenance for each of the tested algorithms. We conclude that diversity needs to be considered in the context of fitness improvement, and that more diversity is not necessarily beneficial in terms of solution quality.", notes = "Also known as \cite{Affenzeller:2017:DOG:3067695.3082530} GECCO-2017 A Recombination of the 26th International Conference on Genetic Algorithms (ICGA-2017) and the 22nd Annual Genetic Programming Conference (GP-2017)", } @InProceedings{DBLP:conf/eurocast/AffenzellerBDDH19, author = "Michael Affenzeller and Bogdan Burlacu and Viktoria Dorfer and Sebastian Dorl and Gerhard Halmerbauer and Tilman Koenigswieser and Michael Kommenda and Julia Vetter and Stephan M. Winkler", title = "White Box vs. Black Box Modeling: On the Performance of Deep Learning, Random Forests, and Symbolic Regression in Solving Regression Problems", booktitle = "17th International Conference, Computer Aided Systems Theory - {EUROCAST} 2019", year = "2019", editor = "Roberto Moreno-Diaz and Franz Pichler and Alexis Quesada-Arencibia", volume = "12013", series = "Lecture Notes in Computer Science", pages = "288--295", address = "Las Palmas de Gran Canaria, Spain", month = feb # " 17-22", publisher = "Springer", note = "Revised Selected Papers, Part {I}", keywords = "genetic algorithms, genetic programming", timestamp = "Mon, 05 Feb 2024 20:28:43 +0100", biburl = "https://dblp.org/rec/conf/eurocast/AffenzellerBDDH19.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://doi.org/10.1007/978-3-030-45093-9_35", DOI = "doi:10.1007/978-3-030-45093-9_35", } @InProceedings{Affenzeller:2022:GPTP, author = "Bogdan Burlacu and Michael Kommenda and Gabriel Kronberger and Stephan M. Winkler and Michael Affenzeller", title = "Symbolic Regression in Materials Science: Discovering Interatomic Potentials from Data", booktitle = "Genetic Programming Theory and Practice XIX", year = "2022", editor = "Leonardo Trujillo and Stephan M. Winkler and Sara Silva and Wolfgang Banzhaf", series = "Genetic and Evolutionary Computation", pages = "1--30", address = "Ann Arbor, USA", month = jun # " 2-4", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-981-19-8459-4", URL = "https://arxiv.org/abs/2206.06422", DOI = "doi:10.1007/978-981-19-8460-0_1", abstract = "Particle-based modeling of materials at atomic scale plays an important role in the development of new materials and the understanding of their properties. The accuracy of particle simulations is determined by interatomic potentials, which allow calculating the potential energy of an atomic system as a function of atomic coordinates and potentially other properties. First-principles-based ab initio potentials can reach arbitrary levels of accuracy, however, their applicability is limited by their high computational cost. Machine learning (ML) has recently emerged as an effective way to offset the high computational costs of ab initio atomic potentials by replacing expensive models with highly efficient surrogates trained on electronic structure data. Among a plethora of current methods, symbolic regression (SR) is gaining traction as a powerful “white-box” approach for discovering functional forms of interatomic potentials. This contribution discusses the role of symbolic regression in Materials Science (MS) and offers a comprehensive overview of current methodological challenges and state-of-the-art results. A genetic programming-based approach for modeling atomic potentials from raw data (consisting of snapshots of atomic positions and associated potential energy) is presented and empirically validated on ab initio electronic structure data.", notes = "Part of \cite{Banzhaf:2022:GPTP} published after the workshop in 2023", } @InProceedings{Affenzeller:2023:GPTP, author = "Michael Affenzeller", title = "{GP} in Prescriptive Analytics", booktitle = "Genetic Programming Theory and Practice XX", year = "2023", editor = "Ting Hu and Charles Ofria and Leonardo Trujillo and Stephan Winkler", series = "Genetic and Evolutionary Computation", address = "Michigan State University, USA", month = jun # " 1-3", keywords = "genetic algorithms, genetic programming", notes = " Part of \cite{Hu:2023:GPTP} Not in published book", } @Article{Afshar:2017:RSE, author = "M. H. Afshar and M. T. Yilmaz", title = "The added utility of nonlinear methods compared to linear methods in rescaling soil moisture products", journal = "Remote Sensing of Environment", volume = "196", pages = "224--237", year = "2017", ISSN = "0034-4257", DOI = "doi:10.1016/j.rse.2017.05.017", URL = "http://www.sciencedirect.com/science/article/pii/S003442571730216X", abstract = "In this study, the added utility of nonlinear rescaling methods relative to linear methods in the framework of creating a homogenous soil moisture time series has been explored. The performances of 31 linear and nonlinear rescaling methods are evaluated by rescaling the Land Parameter Retrieval Model (LPRM) soil moisture datasets to station-based watershed average datasets obtained over four United States Department of Agriculture (USDA) Agricultural Research Service (ARS) watersheds. The linear methods include first-order linear regression, multiple linear regression, and multivariate adaptive regression splines (MARS), whereas the nonlinear methods include cumulative distribution function matching (CDF), artificial neural networks (ANN), support vector machines (SVM), Genetic Programming (GEN), and copula methods. MARS, GEN, SVM, ANN, and the copula methods are also implemented to use lagged observations to rescale the datasets. The results of a total of 31 different methods show that the nonlinear methods improve the correlation and error statistics of the rescaled product compared to the linear methods. In general, the method that yielded the best results using training data improved the validation correlations, on average, by 0.063, whereas ELMAN ANN and GEN, using lagged observations methods, yielded correlation improvements of 0.052 and 0.048, respectively. The lagged observations improved the correlations when they were incorporated into rescaling equations in linear and nonlinear fashions, with the nonlinear methods (particularly SVM and GEN but not ANN and copula) benefitting from these lagged observations more than the linear methods. The overall results show that a large majority of the similarities between the LPRM and watershed average datasets are due to linear relations; however, nonlinear relations clearly exist, and the use of nonlinear rescaling methods clearly improves the accuracy of the rescaled product.", keywords = "genetic algorithms, genetic programming, Soil moisture, Rescaling, Linear, Nonlinear, Remote sensing", } @InProceedings{Timperley:2018:GI, author = "Afsoon Afzal and Jeremy Lacomis and Claire {Le Goues} and Christopher Steven Timperley", title = "A {Turing} Test for Genetic Improvement", booktitle = "GI-2018, ICSE workshops proceedings", year = "2018", editor = "Justyna Petke and Kathryn Stolee and William B. Langdon and Westley Weimer", pages = "17--18", address = "Gothenburg, Sweden", month = "2 " # jun, publisher = "ACM", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, genetic improvement", isbn13 = "978-1-4503-5753-1", URL = "http://dx.doi.org/10.1145/3194810.3194817", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/icse2018/gi2018/papers/Timperley_2018_GI.pdf", URL = "https://afsafzal.github.io/materials/AfzalTuringTest2018.pdf", DOI = "doi:10.1145/3194810.3194817", size = "2 pages", abstract = "Genetic improvement is a research field that aims to develop searchbased techniques for improving existing code. GI has been used to automatically repair bugs, reduce energy consumption, and to improve run-time performance. In this paper, we reflect on the often-overlooked relationship between GI and developers within the context of continually evolving software systems. We introduce a distinction between transparent and opaque patches based on intended lifespan and developer interaction. Finally, we outline a Turing test for assessing the ability of a GI system to produce opaque patches that are acceptable to humans. This motivates research into the role GI systems will play in transparent development contexts.", notes = "Note author order change. GI-2018 http://geneticimprovementofsoftware.com/events/papers#icse2018 part of \cite{Petke:2018:ICSEworkshop}", } @PhdThesis{Afsoon_Afzal:thesis, author = "Afsoon Afzal", title = "Automated Testing of Robotic and Cyberphysical Systems", school = "Institute for Software Research, School of Computer Science, Carnegie Mellon University", year = "2021", address = "Pittsburgh, PA 15213, USA", month = may # " 2021", keywords = "SBSE, testing cyber-physical systems, robotics testing, automated quality assurance, simulation-based testing, challenges of testing, automated oracle inference, automated test generation", URL = "https://afsafzal.github.io/materials/thesis.pdf", size = "142 pages", abstract = "Robotics and cyberphysical systems are increasingly being deployed to settings where they are in frequent interaction with the public. Therefore, failures in these systems can be catastrophic by putting human lives in danger and causing extreme financial loss. Large-scale assessment of the quality of these systems before deployment can prevent these costly damages. Because of the complexity and other special features of these systems, testing,and more specifically automated testing, faces challenges. In this dissertation, I study the unique challenges of testing robotics and cyberphysical systems, and propose an end-to-end automated testing pipeline to provide tools and methods that can help roboticists in large-scale, automated testing of their systems. My key insight is that we can use (low-fidelity) simulation to automatically test robotic and cyber-physical systems, and identify many potentially catastrophic failures in advance at low cost. My core thesis is: Robotic and cyberphysical systems have unique features such as interacting with the physical world and integrating hardware and software components, which creates challenges for automated, large-scale testing approaches. An automated testing framework using software-in-the-loop (low-fidelity) simulation can facilitate automated testing for these systems. This framework can be offered using a clustering approach as an automated oracle, and an evolutionary-based automated test input generation with scenario coverage fitness functions. To support this thesis, I conduct a number of qualitative, quantitative, and mixed method studies that 1) identify main challenges of testing robotic and cyberphysical systems, 2) show that low-fidelity simulation can be an effective approach in detecting bugs and errors with low cost, and 3) identify challenges of using simulators in automated testing. Additionally, I propose automated techniques for creating oracles and generating test inputs to facilitate automated testing of robotic and cyberphysical systems. I present an approach to automatically generate oracles for cyberphysical systems using clustering, which can observe and identify common patterns of system behavior.These patterns can be used to distinguish erroneous behavior of the system and act as an oracle. I evaluate the quality of test inputs for robotic systems with respect to their reliability, and effectiveness in revealing faults in the system. I observe a high rate of non-determinism among test executions that complicates test input generation and evaluation, and show that coverage-based metrics are generally poor indicators of test input quality. Finally, I present an evolutionary-based automated test generation approach with a fitness function that is based on scenario coverage. The automated oracle and automated test input generation approaches contribute to a fully automated testing framework that can perform large-scale, automated testing on robotic and cyberphysical systems in simulation.", notes = "is this GP? CMU-ISR-21-105 Supervisor: Claire Le Goues", } @Article{Afzal:2021:TSE, author = "Afsoon Afzal and Manish Motwani and Kathryn T. Stolee and Yuriy Brun and Claire {Le Goues}", title = "{SOSRepair}: Expressive Semantic Search for Real-World Program Repair", journal = "IEEE Transactions on Software Engineering", year = "2021", volume = "47", number = "10", pages = "2162--2181", keywords = "genetic algorithms, genetic programming, genetic improvement, APR", ISSN = "0098-5589", URL = "https://doi.org/10.1109/TSE.2019.2944914", DOI = "doi:10.1109/TSE.2019.2944914", abstract = "Automated program repair holds the potential to significantly reduce software maintenance effort and cost. However, recent studies have shown that it often produces low-quality patches that repair some but break other functionality. We hypothesize that producing patches by replacing likely faulty regions of code with semantically-similar code fragments, and doing so at a higher level of granularity than prior approaches can better capture abstraction and the intended specification, and can improve repair quality. We create SOSRepair, an automated program repair technique that uses semantic code search to replace candidate buggy code regions with behaviorally-similar (but not identical) code written by humans. SOSRepair is the first such technique to scale to real-world defects in real-world systems. On a subset of the ManyBugs benchmark of such defects, SOSRepair produces patches for 23 (35percent) of the 65 defects, including 3, 5, and 8 defects for which previous state-of-the-art techniques Angelix, Prophet, and GenProg do not, respectively. On these 23 defects, SOSRepair produces more patches (8, 35percent) that pass all independent tests than the prior techniques. We demonstrate a relationship between patch granularity and the ability to produce patches that pass all independent tests. We then show that fault localization precision is a key factor in SOSRepair's success. Manually improving fault localisation allows SOSRepair to patch 24 (37percent) defects, of which 16 (67percent) pass all independent tests. We conclude that (1) higher-granularity, semantic-based patches can improve patch quality, (2) semantic search is promising for producing high-quality real-world defect repairs, (3) research in fault localization can significantly improve the quality of program repair techniques, and (4) semi-automated approaches in which developers suggest fix locations may produce high-quality patches.", notes = "Also known as \cite{8854217}", } @InProceedings{AfzalTF08, author = "Wasif Afzal and Richard Torkar and Robert Feldt", title = "A Systematic Mapping Study on Non-Functional Search-based Software Testing", booktitle = "Proceedings of the 20th International Conference on Software Engineering and Knowledge Engineering (SEKE '08)", year = "2008", pages = "488--493", address = "San Francisco, CA, USA", month = jul # " 1-3", publisher = "Knowledge Systems Institute Graduate School", keywords = "genetic algorithms, genetic programming", bibsource = "http://crestweb.cs.ucl.ac.uk/resources/sbse_repository/repository.html", ISBN = "1-891706-22-5", URL = "http://www.torkar.se/resources/A-systematic-mapping-study-on-non-functional-search-based-software-testing.pdf", size = "6 pages", abstract = "Automated software test generation has been applied across the spectrum of test case design methods; this includes white-box (structural), black-box (functional), grey-box (combination of structural and functional) and non-functional testing. In this paper, we undertake a systematic mapping study to present a broad review of primary studies on the application of search-based optimization techniques to non-functional testing. The motivation is to identify the evidence available on the topic and to identify gaps in the application of search-based optimization techniques to different types of non-functional testing. The study is based on a comprehensive set of 35 papers obtained after using a multi-stage selection criteria and are published in workshops, conferences and journals in the time span 1996--2007. We conclude that the search-based software testing community needs to do more and broader studies on non-functional search-based software testing (NFSBST) and the results from our systematic map can help direct such efforts.", notes = "http://www.ksi.edu/seke/seke08.html http://www.ksi.edu/seke/sk08pgm.html http://www.ksi.edu/seke/tocs/seke2008toc.pdf ", } @InProceedings{Afzal08e, author = "Wasif Afzal and Richard Torkar", title = "Suitability of Genetic Programming for Software Reliability Growth Modeling", booktitle = "The 2008 International Symposium on Computer Science and its Applications (CSA'08)", year = "2008", pages = "114--117", address = "Hobart, ACT", month = "13-15 " # oct, publisher = "IEEE Computer Society", keywords = "genetic algorithms, genetic programming, software reliability data points, software reliability growth modeling, SBSE", DOI = "doi:10.1109/CSA.2008.13", abstract = "Genetic programming (GP) has been found to be effective in finding a model that fits the given data points without making any assumptions about the model structure. This makes GP a reasonable choice for software reliability growth modeling. This paper discusses the suitability of using GP for software reliability growth modeling and highlights the mechanisms that enable GP to progressively search for fitter solutions.", notes = "Also known as \cite{4654071} ", } @InProceedings{Afzal08d, author = "Wasif Afzal and Richard Torkar", title = "A comparative evaluation of using genetic programming for predicting fault count data", booktitle = "Proceedings of the Third International Conference on Software Engineering Advances (ICSEA'08)", year = "2008", pages = "407--414", address = "Sliema, Malta", month = "26-31", keywords = "genetic algorithms, genetic programming, prediction, software reliability growth modeling, SBSE", isbn13 = "978-1-4244-3218-9", DOI = "doi:10.1109/ICSEA.2008.9", abstract = "There have been a number of software reliability growth models (SRGMs) proposed in literature. Due to several reasons, such as violation of models' assumptions and complexity of models, the practitioners face difficulties in knowing which models to apply in practice. This paper presents a comparative evaluation of traditional models and use of genetic programming (GP) for modeling software reliability growth based on weekly fault count data of three different industrial projects. The motivation of using a GP approach is its ability to evolve a model based entirely on prior data without the need of making underlying assumptions. The results show the strengths of using GP for predicting fault count data.", notes = "Also known as \cite{4668139} ", } @InProceedings{Afzal08b, author = "Wasif Afzal and Richard Torkar and Robert Feldt", title = "Prediction of fault count data using genetic programming", booktitle = "Proceedings of the 12th IEEE International Multitopic Conference (INMIC'08)", year = "2008", pages = "349--356", address = "Karachi, Pakistan", month = "23-24 " # dec, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, SBSE, fault count data, prediction", isbn13 = "978-1-4244-2823-6", URL = "http://drfeldt.googlepages.com/afzal_submitted0805icsea_prediction_.pdf", DOI = "doi:10.1109/INMIC.2008.4777762", abstract = "Software reliability growth modeling helps in deciding project release time and managing project resources. A large number of such models have been presented in the past. Due to the existence of many models, the models' inherent complexity, and their accompanying assumptions; the selection of suitable models becomes a challenging task. This paper presents empirical results of using genetic programming (GP) for modeling software reliability growth based on weekly fault count data of three different industrial projects. The goodness of fit (adaptability) and predictive accuracy of the evolved model is measured using five different measures in an attempt to present a fair evaluation. The results show that the GP evolved model has statistically significant goodness of fit and predictive accuracy.", notes = "Also known as \cite{4777762} ", } @InProceedings{Afzal:2009:SSBSE, author = "Wasif Afzal and Richard Torkar and Robert Feldt", title = "Search-Based Prediction of Fault Count Data", booktitle = "Proceedings 1st International Symposium on Search Based Software Engineering SSBSE 2009", year = "2009", editor = "Massimiliano {Di Penta} and Simon Poulding", pages = "35--38", address = "Windsor, UK", month = "13-15 " # may, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, SBSE, search-based prediction, software fault count data, software reliability growth model, symbolic regression, regression analysis, software fault tolerance", isbn13 = "978-0-7695-3675-0", DOI = "doi:10.1109/SSBSE.2009.17", abstract = "Symbolic regression, an application domain of genetic programming (GP), aims to find a function whose output has some desired property, like matching target values of a particular data set. While typical regression involves finding the coefficients of a pre-defined function, symbolic regression finds a general function, with coefficients, fitting the given set of data points. The concepts of symbolic regression using genetic programming can be used to evolve a model for fault count predictions. Such a model has the advantages that the evolution is not dependent on a particular structure of the model and is also independent of any assumptions, which are common in traditional time-domain parametric software reliability growth models. This research aims at applying experiments targeting fault predictions using genetic programming and comparing the results with traditional approaches to compare efficiency gains.", notes = "order number P3675 http://www.ssbse.info/ Also known as \cite{5033177}", } @Article{Afzal2009, author = "Wasif Afzal and Richard Torkar and Robert Feldt", title = "A systematic review of search-based testing for non-functional system properties", journal = "Information and Software Technology", year = "2009", volume = "51", number = "6", pages = "957--976", month = jun, keywords = "genetic algorithms, genetic programming, Systematic review, Non-functional system properties, Search-based software testing", ISSN = "0950-5849", URL = "http://drfeldt.googlepages.com/afzal_submitted0805ist_sysrev_nfr_sb.pdf", URL = "http://www.sciencedirect.com/science/article/B6V0B-4VHXDTD-1/2/9da989f9d874eb88d1f82d9a0878114b", DOI = "doi:10.1016/j.infsof.2008.12.005", size = "19 pages", abstract = "Search-based software testing is the application of metaheuristic search techniques to generate software tests. The test adequacy criterion is transformed into a fitness function and a set of solutions in the search space are evaluated with respect to the fitness function using a metaheuristic search technique. The application of metaheuristic search techniques for testing is promising due to the fact that exhaustive testing is infeasible considering the size and complexity of software under test. Search-based software testing has been applied across the spectrum of test case design methods; this includes white-box (structural), black-box (functional) and grey-box (combination of structural and functional) testing. In addition, metaheuristic search techniques have also been applied to test non-functional properties. The overall objective of undertaking this systematic review is to examine existing work into non-functional search-based software testing (NFSBST). We are interested in types of non-functional testing targeted using metaheuristic search techniques, different fitness functions used in different types of search-based non-functional testing and challenges in the application of these techniques. The systematic review is based on a comprehensive set of 35 articles obtained after a multi-stage selection process and have been published in the time span 1996-2007. The results of the review show that metaheuristic search techniques have been applied for non-functional testing of execution time, quality of service, security, usability and safety. A variety of metaheuristic search techniques are found to be applicable for non-functional testing including simulated annealing, tabu search, genetic algorithms, ant colony methods, grammatical evolution, genetic programming (and its variants including linear genetic programming) and swarm intelligence methods. The review reports on different fitness functions used to guide the search for each of the categories of execution time, safety, usability, quality of service and security; along with a discussion of possible challenges in the application of metaheuristic search techniques.", } @MastersThesis{Afzal:Licentiate, author = "Wasif Afzal", title = "Search-Based Approaches to Software Fault Prediction and Software Testing", school = "School of Engineering, Dept. of Systems and Software Engineering, Blekinge Institute of Technology", year = "2009", type = "Licentiate Dissertation", address = "Sweden", keywords = "genetic algorithms, genetic programming, SBSE, Software Engineering, Computer Science, Artificial Intelligence", URL = "http://www.bth.se/fou/forskinfo.nsf/all/f0738b5fc4ca0bbac12575980043def3/$file/Afzal_lic.pdf", broken = "http://www.bth.se/fou/forskinfo.nsf/all/f0738b5fc4ca0bbac12575980043def3?OpenDocument", size = "212 pages", isbn13 = "978-91-7295-163-1", language = "eng", oai = "oai:bth.se:forskinfoF0738B5FC4CA0BBAC12575980043DEF3", abstract = "Software verification and validation activities are essential for software quality but also constitute a large part of software development costs. Therefore efficient and cost-effective software verification and validation activities are both a priority and a necessity considering the pressure to decrease time-to-market and intense competition faced by many, if not all, companies today. It is then perhaps not unexpected that decisions related to software quality, when to stop testing, testing schedule and testing resource allocation needs to be as accurate as possible. This thesis investigates the application of search-based techniques within two activities of software verification and validation: Software fault prediction and software testing for non-functional system properties. Software fault prediction modeling can provide support for making important decisions as outlined above. In this thesis we empirically evaluate symbolic regression using genetic programming (a search-based technique) as a potential method for software fault predictions. Using data sets from both industrial and open-source software, the strengths and weaknesses of applying symbolic regression in genetic programming are evaluated against competitive techniques. In addition to software fault prediction this thesis also consolidates available research into predictive modeling of other attributes by applying symbolic regression in genetic programming, thus presenting a broader perspective. As an extension to the application of search-based techniques within software verification and validation this thesis further investigates the extent of application of search-based techniques for testing non-functional system properties. Based on the research findings in this thesis it can be concluded that applying symbolic regression in genetic programming may be a viable technique for software fault prediction. We additionally seek literature evidence where other search-based techniques are applied for testing of non-functional system properties, hence contributing towards the growing application of search-based techniques in diverse activities within software verification and validation.", } @InCollection{Afzal:2010:ECoaSE, author = "Wasif Afzal and Richard Torkar and Robert Feldt and Tony Gorschek", title = "Genetic Programming for Cross-Release Fault Count Predictions in Large and Complex Software Projects", booktitle = "Evolutionary Computation and Optimization Algorithms in Software Engineering: Applications and Techniques", publisher = "IGI Global", year = "2010", editor = "Monica Chis", chapter = "6", pages = "94--126", month = jun, keywords = "genetic algorithms, genetic programming, SBSE", isbn13 = "9781615208098", DOI = "doi:10.4018/978-1-61520-809-8.ch006", abstract = "Software fault prediction can play an important role in ensuring software quality through efficient resource allocation. This could, in turn, reduce the potentially high consequential costs due to faults. Predicting faults might be even more important with the emergence of short-timed and multiple software releases aimed at quick delivery of functionality. Previous research in software fault prediction has indicated that there is a need i) to improve the validity of results by having comparisons among number of data sets from a variety of software, ii) to use appropriate model evaluation measures and iii) to use statistical testing procedures. Moreover, cross-release prediction of faults has not yet achieved sufficient attention in the literature. In an attempt to address these concerns, this paper compares the quantitative and qualitative attributes of 7 traditional and machine-learning techniques for modelling the cross-release prediction of fault count data. The comparison is done using extensive data sets gathered from a total of 7 multi-release open-source and industrial software projects. These software projects together have several years of development and are from diverse application areas, ranging from a web browser to a robotic controller software. Our quantitative analysis suggests that genetic programming (GP) tends to have better consistency in terms of goodness of fit and accuracy across majority of data sets. It also has comparatively less model bias. Qualitatively, ease of configuration and complexity are less strong points for GP even though it shows generality and gives transparent models. Artificial neural networks did not perform as well as expected while linear regression gave average predictions in terms of goodness of fit and accuracy. Support vector machine regression and traditional software reliability growth models performed below average on most of the quantitative evaluation criteria while remained on average for most of the qualitative measures.", } @InProceedings{Afzal:2010:SSBSE, author = "Wasif Afzal and Richard Torkar and Robert Feldt and Greger Wikstrand", title = "Search-based Prediction of Fault-slip-through in Large Software Projects", booktitle = "Second International Symposium on Search Based Software Engineering (SSBSE 2010)", year = "2010", month = "7-9 " # sep, pages = "79--88", address = "Benevento, Italy", keywords = "genetic algorithms, genetic programming, gene expression programming, sbse, AIRS, GEP, GP, MR, PSO-ANN, artificial immune recognition system, artificial neural network, fault-slip-through, multiple regression, particle swarm optimisation, search-based prediction, software project, software testing process, artificial immune systems, fault tolerant computing, neural nets, particle swarm optimisation, program testing, regression analysis", DOI = "doi:10.1109/SSBSE.2010.19", isbn13 = "978-0-7695-4195-2", abstract = "A large percentage of the cost of rework can be avoided by finding more faults earlier in a software testing process. Therefore, determination of which software testing phases to focus improvements work on, has considerable industrial interest. This paper evaluates the use of five different techniques, namely particle swarm optimization based artificial neural networks (PSO-ANN), artificial immune recognition systems (AIRS), gene expression programming (GEP), genetic programming (GP) and multiple regression (MR), for predicting the number of faults slipping through unit, function, integration and system testing phases. The objective is to quantify improvement potential in different testing phases by striving towards finding the right faults in the right phase. We have conducted an empirical study of two large projects from a telecommunication company developing mobile platforms and wireless semiconductors. The results are compared using simple residuals, goodness of fit and absolute relative error measures. They indicate that the four search-based techniques (PSO-ANN, AIRS, GEP, GP) perform better than multiple regression for predicting the fault-slip-through for each of the four testing phases. At the unit and function testing phases, AIRS and PSO-ANN performed better while GP performed better at integration and system testing phases. The study concludes that a variety of search-based techniques are applicable for predicting the improvement potential in different testing phases with GP showing more consistent performance across two of the four test phases.", notes = "IEEE Computer Society Order Number P4195 BMS Part Number: CFP1099G-PRT Library of Congress Number 2010933544 http://ssbse.info/2010/program.php Also known as \cite{5635180}", } @InProceedings{Afzal:2010:APSEC, author = "Wasif Afzal", title = "Using Faults-Slip-Through Metric as a Predictor of Fault-Proneness", booktitle = "17th Asia Pacific Software Engineering Conference (APSEC 2010)", year = "2010", month = nov # " 30-" # dec # " 3", pages = "414--422", abstract = "Background: The majority of software faults are present in small number of modules, therefore accurate prediction of fault-prone modules helps improve software quality by focusing testing efforts on a subset of modules. Aims: This paper evaluates the use of the faults-slip-through (FST) metric as a potential predictor of fault-prone modules. Rather than predicting the fault-prone modules for the complete test phase, the prediction is done at the specific test levels of integration and system test. Method: We applied eight classification techniques, to the task of identifying fault prone modules, representing a variety of approaches, including a standard statistical technique for classification (logistic regression), tree-structured classifiers (C4.5 and random forests), a Bayesian technique (Naive Bayes), machine-learning techniques (support vector machines and back-propagation artificial neural networks) and search-based techniques (genetic programming and artificial immune recognition systems) on FST data collected from two large industrial projects from the telecommunication domain. Results: Using area under the receiver operating characteristic (ROC) curve and the location of (PF, PD) pairs in the ROC space, the faults slip-through metric showed impressive results with the majority of the techniques for predicting fault-prone modules at both integration and system test levels. There were, however, no statistically significant differences between the performance of different techniques based on AUC, even though certain techniques were more consistent in the classification performance at the two test levels. Conclusions: We can conclude that the faults-slip-through metric is a potentially strong predictor of fault-proneness at integration and system test levels. The faults-slip-through measurements interact in ways that is conveniently accounted for by majority of the data mining techniques.", keywords = "genetic algorithms, genetic programming, sbse, Bayesian technique, artificial immune recognition systems, back-propagation artificial neural networks, data mining, fault-proneness predictor, faults-slip-through metric, logistic regression, machine-learning techniques, receiver operating characteristic curve, search-based techniques, software faults, software quality, standard statistical technique, support vector machines, system test levels, tree-structured classifiers, backpropagation, data mining, neural nets, program testing, software quality, statistical analysis, support vector machines", DOI = "doi:10.1109/APSEC.2010.54", ISSN = "1530-1362", notes = "Blekinge Inst. of Technol., Ronneby, Sweden. Also known as \cite{5693218}", } @Article{Afzal201111984, author = "Wasif Afzal and Richard Torkar", title = "On the application of genetic programming for software engineering predictive modeling: A systematic review", journal = "Expert Systems with Applications", volume = "38", number = "9", pages = "11984--11997", year = "2011", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2011.03.041", URL = "http://www.sciencedirect.com/science/article/B6V03-52C8FT6-5/2/668361024e4b2bcf9a4a73195271591c", keywords = "genetic algorithms, genetic programming, Systematic review, Symbolic regression, Modelling", abstract = "The objective of this paper is to investigate the evidence for symbolic regression using genetic programming (GP) being an effective method for prediction and estimation in software engineering, when compared with regression/machine learning models and other comparison groups (including comparisons with different improvements over the standard GP algorithm). We performed a systematic review of literature that compared genetic programming models with comparative techniques based on different independent project variables. A total of 23 primary studies were obtained after searching different information sources in the time span 1995-2008. The results of the review show that symbolic regression using genetic programming has been applied in three domains within software engineering predictive modeling: (i) Software quality classification (eight primary studies). (ii) Software cost/effort/size estimation (seven primary studies). (iii) Software fault prediction/software reliability growth modelling (eight primary studies). While there is evidence in support of using genetic programming for software quality classification, software fault prediction and software reliability growth modelling; the results are inconclusive for software cost/effort/size estimation.", } @PhdThesis{Afzal:thesis, author = "Wasif Afzal", title = "Search-Based Prediction of Software Quality: Evaluations And Comparisons", school = "School of Computing, Blekinge Institute of Technology", year = "2011", address = "Sweden", month = "5 " # may, keywords = "genetic algorithms, genetic programming, SBSE", URL = "http://www.bth.se/fou/forskinfo.nsf/0/dd0dcce8cc126a52c125784500410306/$file/Dis%20Wasif%20Afzal%20thesis.pdf", isbn13 = "978-91-7295-203-4", size = "313 pages", abstract = "Software verification and validation (V&V) activities are critical for achieving software quality; however, these activities also constitute a large part of the costs when developing software. Therefore efficient and effective software V&V activities are both a priority and a necessity considering the pressure to decrease time-to-market and the intense competition faced by many, if not all, companies today. It is then perhaps not unexpected that decisions that affects software quality, e.g., how to allocate testing resources, develop testing schedules and to decide when to stop testing, needs to be as stable and accurate as possible. The objective of this thesis is to investigate how search-based techniques can support decision-making and help control variation in software V&V activities, thereby indirectly improving software quality. Several themes in providing this support are investigated: predicting reliability of future software versions based on fault history; fault prediction to improve test phase efficiency; assignment of resources to fixing faults; and distinguishing fault-prone software modules from non-faulty ones. A common element in these investigations is the use of search-based techniques, often also called metaheuristic techniques, for supporting the V&V decision-making processes. Search-based techniques are promising since, as many problems in real world, software V&V can be formulated as optimisation problems where near optimal solutions are often good enough. Moreover, these techniques are general optimization solutions that can potentially be applied across a larger variety of decision-making situations than other existing alternatives. Apart from presenting the current state of the art, in the form of a systematic literature review, and doing comparative evaluations of a variety of metaheuristic techniques on large-scale projects (both industrial and open-source), this thesis also presents methodological investigations using search-based techniques that are relevant to the task of software quality measurement and prediction. The results of applying search-based techniques in large-scale projects, while investigating a variety of research themes, show that they consistently give competitive results in comparison with existing techniques. Based on the research findings, we conclude that search-based techniques are viable techniques to use in supporting the decision-making processes within software V&V activities. The accuracy and consistency of these techniques make them important tools when developing future decision support for effective management of software V&V activities.", notes = "Advisors, Dr. Richard Torkar and Dr. Robert Feldt. http://www.bth.se/eng/calendar.nsf/allaDok/9984ce8a1e18e8ecc125782a004d4167!OpenDocument Doctoral Dissertation Series No. 2011:06", } @Article{Afzal:2013:SQJ, author = "Wasif Afzal and Richard Torkar and Robert Feldt and Tony Gorschek", title = "Prediction of faults-slip-through in large software projects: an empirical evaluation", journal = "Software Quality Journal", year = "2014", volume = "22", number = "1", pages = "51--86", month = mar, publisher = "Springer US", keywords = "genetic algorithms, genetic programming, SBSE, Prediction, Empirical, Faults-slip-through, Search-based", ISSN = "0963-9314", DOI = "doi:10.1007/s11219-013-9205-3", language = "English", oai = "oai:bth.se:forskinfo3D40224F7CBF862DC1257B7800251E66", URL = "http://www.bth.se/fou/forskinfo.nsf/all/3d40224f7cbf862dc1257b7800251e66?OpenDocument", size = "36 pages", abstract = "A large percentage of the cost of rework can be avoided by finding more faults earlier in a software test process. Therefore, determination of which software test phases to focus improvement work on has considerable industrial interest. We evaluate a number of prediction techniques for predicting the number of faults slipping through to unit, function, integration, and system test phases of a large industrial project. The objective is to quantify improvement potential in different test phases by striving toward finding the faults in the right phase. The results show that a range of techniques are found to be useful in predicting the number of faults slipping through to the four test phases; however, the group of search-based techniques (genetic programming, gene expression programming, artificial immune recognition system, and particle swarm optimisation (PSO) based artificial neural network) consistently give better predictions, having a representation at all of the test phases. Human predictions are consistently better at two of the four test phases. We conclude that the human predictions regarding the number of faults slipping through to various test phases can be well supported by the use of search-based techniques. A combination of human and an automated search mechanism (such as any of the search-based techniques) has the potential to provide improved prediction results.", } @InCollection{Afzal2016, author = "Wasif Afzal and Richard Torkar", title = "Towards Benchmarking Feature Subset Selection Methods for Software Fault Prediction", booktitle = "Computational Intelligence and Quantitative Software Engineering", publisher = "Springer", year = "2016", editor = "Witold Pedrycz and Giancarlo Succi and Alberto Sillitti", volume = "617", series = "Studies in Computational Intelligence", chapter = "3", pages = "33--58", keywords = "genetic algorithms, genetic programming, SBSE, Feature subset selection, Fault prediction, Empirical", isbn13 = "978-3-319-25964-2", DOI = "doi:10.1007/978-3-319-25964-2_3", abstract = "Despite the general acceptance that software engineering datasets often contain noisy, irrelevant or redundant variables, very few benchmark studies of feature subset selection (FSS) methods on real-life data from software projects have been conducted. This paper provides an empirical comparison of state-of-the-art FSS methods: information gain attribute ranking (IG); Relief (RLF); principal component analysis (PCA); correlation-based feature selection (CFS); consistency-based subset evaluation (CNS); wrapper subset evaluation (WRP); and an evolutionary computation method, genetic programming (GP), on five fault prediction datasets from the PROMISE data repository. For all the datasets, the area under the receiver operating characteristic curve, the AUC value averaged over 10-fold cross-validation runs, was calculated for each FSS method-dataset combination before and after FSS. Two diverse learning algorithms, C4.5 and naive Bayes (NB) are used to test the attribute sets given by each FSS method. The results show that although there are no statistically significant differences between the AUC values for the different FSS methods for both C4.5 and NB, a smaller set of FSS methods (IG, RLF, GP) consistently select fewer attributes without degrading classification accuracy. We conclude that in general, FSS is beneficial as it helps improve classification accuracy of NB and C4.5. There is no single best FSS method for all datasets but IG, RLF and GP consistently select fewer attributes without degrading classification accuracy within statistically significant boundaries.", } @InProceedings{afzali:2018:AJCAI, author = "Shima Afzali and Harith Al-Sahaf and Bing Xue and Christopher Hollitt and Mengjie Zhang", title = "A Genetic Programming Approach for Constructing Foreground and Background Saliency Features for Salient Object Detection", booktitle = "Australasian Joint Conference on Artificial Intelligence", year = "2018", editor = "Tanja Mitrovic and Bing Xue and Xiaodong Li", volume = "11320", series = "LNCS", address = "Wellington, New Zealand", month = dec # " 11-14", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-030-03990-5", URL = "http://link.springer.com/chapter/10.1007/978-3-030-03991-2_21", DOI = "doi:10.1007/978-3-030-03991-2_21", } @InProceedings{Afzali:2019:evoapplications, author = "Shima Afzali and Harith Al-Sahaf and Bing Xue and Christopher Hollitt and Mengjie Zhang", title = "Genetic Programming for Feature Selection and Feature Combination in Salient Object Detection", booktitle = "22nd International Conference, EvoApplications 2019", year = "2019", month = "24-26 " # apr, editor = "Paul Kaufmann and Pedro A. Castillo", series = "LNCS", volume = "11454", publisher = "Springer Verlag", address = "Leipzig, Germany", pages = "308--324", organisation = "EvoStar, Species", keywords = "genetic algorithms, genetic programming, Salient Object Detection, Feature combination, Feature selection", isbn13 = "978-3-030-16691-5", DOI = "doi:10.1007/978-3-030-16692-2_21", abstract = "Salient Object Detection (SOD) aims to model human visual attention system to cope with the complex natural scene which contains various objects at different scales. Over the past two decades, a wide range of saliency features have been introduced in the SOD field, however feature selection has not been widely investigated for selecting informative, non-redundant, and complementary features from the existing features. In SOD, multi-level feature extraction and feature combination are two fundamental stages to compute the final saliency map. However, designing a good feature combination framework is a challenging task and requires domain-expert intervention. In this paper, we propose a genetic programming (GP) based method that is able to automatically select the complementary saliency features and generate mathematical function to combine those features. The performance of the proposed method is evaluated using four benchmark datasets and compared to nine state-of-the-art methods. The qualitative and quantitative results show that the proposed method significantly outperformed, or achieved comparable performance to, the competitor methods.", notes = "http://www.evostar.org/2019/cfp_evoapps.php EuroGP'2019 held in conjunction with EvoCOP2019, EvoMusArt2019 and EvoApplications2019", } @PhdThesis{Afzali:thesis, author = "Shima {Afzali Vahed Moghaddam}", title = "Evolutionary Computation for Feature Manipulation in Salient Object Detection", school = "Computer Science, Victoria University of Wellington", year = "2020", address = "New Zealand", keywords = "genetic algorithms, genetic programming", URL = "http://hdl.handle.net/10063/8897", URL = "http://researcharchive.vuw.ac.nz/xmlui/handle/10063/8897?show=full", URL = "http://researcharchive.vuw.ac.nz/xmlui/bitstream/handle/10063/8897/thesis_access.pdf", size = "267 pages", abstract = "The human visual system can efficiently cope with complex natural scenes containing various objects at different scales using the visual attention mechanism. Salient object detection (SOD) aims to simulate the capability of the human visual system in prioritizing objects for high-level processing. SOD is a process of identifying and localizing the most attention grabbing object(s) of a scene and separating the whole extent of the object(s) from the scene. In SOD, significant research has been dedicated to design and introduce new features to the domain. The existing saliency feature space suffers from some difficulties such as having high dimensionality, features are not equally important, some features are irrelevant, and the original features are not informative enough. These difficulties can lead to various performance limitations. Feature manipulation is the process which improves the input feature space to enhance the learning quality and performance. Evolutionary computation (EC) techniques have been employed in a wide range of tasks due to their powerful search abilities. Genetic programming (GP) and particle swarm optimization (PSO) are well-known EC techniques which have been used for feature manipulation. The overall goal of this thesis is to develop feature manipulation methods including feature weighting, feature selection, and feature construction using EC techniques to improve the input feature set for SOD. This thesis proposes a feature weighting method using PSO to explore the relative contribution of each saliency feature in the feature combination process. Saliency features are referred to the features which are extracted from different levels (e.g., pixel, segmentation) of an image to compute the saliency values over the entire image. The experimental results show that different datasets favour different weights for the employed features. The results also reveal that by considering the importance of each feature in the combination process, the proposed method has achieved better performance than that of the competitive methods. This thesis proposes a new bottom-up SOD method to detect salient objects by constructing two new informative saliency features and designing a new feature combination framework. The proposed method aims at developing features which target to identify different regions of the image. The proposed method makes a good balance between computational time and performance. This thesis proposes a GP-based method to automatically construct foreground and background saliency features. The automatically constructed features do not require domain-knowledge and they are more informative compared to the manually constructed features. The results show that GP is robust towards the changes in the input feature set (e.g., adding more features to the input feature set) and improves the performance by introducing more informative features to the SOD domain. This thesis proposes a GP-based SOD method which automatically produces saliency maps (a 2-D map containing saliency values) for different types of images. This GP-based SOD method applies feature selection and feature combination during the learning process for SOD. GP with built-in feature selection process which selects informative features from the original set and combines the selected features to produce the final saliency map. The results show that GP can potentially explore a large search space and find a good way to combine different input features. This thesis introduces GP for the first time to construct high-level saliency features from the low-level features for SOD, which aims to improve the performance of SOD, particularly on challenging and complex SOD tasks. The proposed method constructs fewer features that achieve better saliency performance than the original full feature set.", notes = "Supervisors: Bing Xue, Mengjie Zhang, Christopher Hollitt, Harith Al-Sahaf", } @Article{Afzali:2021:ESA, author = "Shima {Afzali Vahed Moghaddam} and Harith Al-Sahaf and Bing Xue and Christopher Hollitt and Mengjie Zhang", title = "An automatic feature construction method for salient object detection: A genetic programming approach", journal = "Expert Systems with Applications", volume = "186", pages = "115726", year = "2021", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2021.115726", URL = "https://www.sciencedirect.com/science/article/pii/S0957417421011076", keywords = "genetic algorithms, genetic programming, Salient object detection, Feature construction", abstract = "Over the last two decades, salient object detection (SOD) has received increasingly more attention due to its ability to handle complex natural scenes and its various real-world applications. The performance of an SOD method mainly relies on saliency features that are extracted with different levels of information. Low-level saliency features are often effective in simple scenarios, but they are not always robust in challenging scenarios. With the recent prevalence of high-level saliency features such as deep convolutional neural networks (CNNs) features, a remarkable progress has been achieved in the SOD field. However, CNN-based constructed high-level features unavoidably drop the location information and low-level fine details (e.g., edges and corners) of salient object(s), leading to unclear/blurry boundary predictions. In addition, deep CNN methods have difficulties to generalize and accurately detect salient objects when they are trained with limited number of images (e.g. small datasets). This paper proposes a new automatic feature construction method using Genetic Programming (GP) to construct informative high-level saliency features for SOD. The proposed method takes low-level and hand-crafted saliency features as input to construct high-level features. The constructed GP-based high-level features not only detect the general objects, but they are also good at capturing details and edges/boundaries. The GP-based constructed features have better interpretability compared to CNN-based features. The proposed GP-based method can potentially cope with a small number of samples for training to obtain a good generalization as long as the given training data has enough information to represent the distribution of the data. The experiments on six datasets reveal that the new method achieves consistently high performance compared to twelve state-of-the-art SOD methods", } @InProceedings{agapie:1999:RSCC, author = "Alexandru Agapie", title = "Random Systems with Complete Connections", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "770", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems, poster papers", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-862.ps", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InProceedings{eurogp06:AgapitosLucas, author = "Alexandros Agapitos and Simon M. Lucas", title = "Learning Recursive Functions with Object Oriented Genetic Programming", editor = "Pierre Collet and Marco Tomassini and Marc Ebner and Steven Gustafson and Anik\'o Ek\'art", booktitle = "Proceedings of the 9th European Conference on Genetic Programming", publisher = "Springer", series = "Lecture Notes in Computer Science", volume = "3905", year = "2006", address = "Budapest, Hungary", month = "10 - 12 " # apr, organisation = "EvoNet", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-33143-3", pages = "166--177", DOI = "doi:10.1007/11729976_15", bibsource = "DBLP, http://dblp.uni-trier.de", abstract = "This paper describes the evolution of recursive functions within an Object-Oriented Genetic Programming (OOGP) system. We evolved general solutions to factorial, Fibonacci, exponentiation, even-n-Parity, and nth-3. We report the computational effort required to evolve these methods and provide a comparison between crossover and mutation variation operators, and also undirected random search. We found that the evolutionary algorithms performed much better than undirected random search, and that mutation outperformed crossover on most problems.", notes = "Part of \cite{collet:2006:GP} EuroGP'2006 held in conjunction with EvoCOP2006 and EvoWorkshops2006 Java reflection.", } @InProceedings{Agapitos:2006:CEC, author = "Alexandros Agapitos and Simon M. Lucas", title = "Evolving Efficient Recursive Sorting Algorithms", booktitle = "Proceedings of the 2006 IEEE Congress on Evolutionary Computation", year = "2006", editor = "Gary G. Yen and Lipo Wang and Piero Bonissone and Simon M. Lucas", pages = "9227--9234", address = "Vancouver", month = "16-21 " # jul, publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, computational complexity, evolutionary computation, object-oriented languages, object-oriented programming, OOGP, evolutionary process, fitness function, language primitives, object oriented genetic programming, recursive sorting algorithms, time complexity", ISBN = "0-7803-9487-9", URL = "http://privatewww.essex.ac.uk/~aagapi/papers/AgapitosLucasEvolvingSort.pdf", DOI = "doi:10.1109/CEC.2006.1688643", size = "8 pages", abstract = "Object Oriented Genetic Programming (OOGP) is applied to the task of evolving general recursive sorting algorithms. We studied the effects of language primitives and fitness functions on the success of the evolutionary process. For language primitives, these were the methods of a simple list processing package. Five different fitness functions based on sequence disorder were evaluated. The time complexity of the successfully evolved algorithms was measured experimentally in terms of the number of method invocations made, and for the best evolved individuals this was best approximated as O(n log(n)). This is the first time that sorting algorithms of this complexity have been evolved.", notes = "WCCI 2006 - A joint meeting of the IEEE, the EPS, and the IEE. Best in session. IEEE Xplore gives pages as 2677--2684", } @InProceedings{eurogp07:agapitos1, author = "Alexandros Agapitos and Simon M. Lucas", title = "Evolving a Statistics Class Using Object Oriented Evolutionary Programming", editor = "Marc Ebner and Michael O'Neill and Anik\'o Ek\'art and Leonardo Vanneschi and Anna Isabel Esparcia-Alc\'azar", booktitle = "Proceedings of the 10th European Conference on Genetic Programming", publisher = "Springer", series = "Lecture Notes in Computer Science", volume = "4445", year = "2007", address = "Valencia, Spain", month = "11-13 " # apr, pages = "291--300", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-540-71602-0", ISBN = "3-540-71602-5", DOI = "doi:10.1007/978-3-540-71605-1_27", abstract = "Object Oriented Evolutionary Programming is used to evolve programs that calculate some statistical measures on a set of numbers. We compared this technique with a more standard functional representation. We also studied the effects of scalar and Pareto-based multi-objective fitness functions to the induction of multi-task programs. We found that the induction of a program residing in an OO representation space is more efficient, yielding less fitness evaluations, and that scalar fitness performed better than Pareto-based fitness in this problem domain.", notes = "Part of \cite{ebner:2007:GP} EuroGP'2007 held in conjunction with EvoCOP2007, EvoBIO2007 and EvoWorkshops2007", } @InProceedings{eurogp07:agapitos2, author = "Alexandros Agapitos and Simon M. Lucas", title = "Evolving Modular Recursive Sorting Algorithms", editor = "Marc Ebner and Michael O'Neill and Anik\'o Ek\'art and Leonardo Vanneschi and Anna Isabel Esparcia-Alc\'azar", booktitle = "Proceedings of the 10th European Conference on Genetic Programming", publisher = "Springer", series = "Lecture Notes in Computer Science", volume = "4445", year = "2007", address = "Valencia, Spain", month = "11-13 " # apr, pages = "301--310", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-540-71602-0", ISBN = "3-540-71602-5", DOI = "doi:10.1007/978-3-540-71605-1_28", abstract = "A fundamental issue in evolutionary learning is the definition of the solution representation language. We present the application of Object Oriented Genetic Programming to the task of coevolving general recursive sorting algorithms along with their primitive representation alphabet. We report the computational effort required to evolve target solutions and provide a comparison between crossover and mutation variation operators, and also undirected random search. We found that the induction of evolved method signatures (typed parameters and return type) can be realized through an evolutionary fitness-driven process. We also found that the evolutionary algorithm outperformed undirected random search, and that mutation performed better than crossover in this problem domain. The main result is that modular sorting algorithms can be evolved.", notes = "Part of \cite{ebner:2007:GP} EuroGP'2007 held in conjunction with EvoCOP2007, EvoBIO2007 and EvoWorkshops2007", } @InProceedings{1277271, author = "Alexandros Agapitos and Julian Togelius and Simon Mark Lucas", title = "Evolving controllers for simulated car racing using object oriented genetic programming", booktitle = "GECCO '07: Proceedings of the 9th annual conference on Genetic and evolutionary computation", year = "2007", editor = "Dirk Thierens and Hans-Georg Beyer and Josh Bongard and Jurgen Branke and John Andrew Clark and Dave Cliff and Clare Bates Congdon and Kalyanmoy Deb and Benjamin Doerr and Tim Kovacs and Sanjeev Kumar and Julian F. Miller and Jason Moore and Frank Neumann and Martin Pelikan and Riccardo Poli and Kumara Sastry and Kenneth Owen Stanley and Thomas Stutzle and Richard A Watson and Ingo Wegener", volume = "2", isbn13 = "978-1-59593-697-4", pages = "1543--1550", address = "London", URL = "http://gpbib.cs.ucl.ac.uk/gecco2007/docs/p1543.pdf", DOI = "doi:10.1145/1276958.1277271", publisher = "ACM Press", publisher_address = "New York, NY, USA", month = "7-11 " # jul, organisation = "ACM SIGEVO (formerly ISGEC)", keywords = "genetic algorithms, genetic programming, evolutionary computer games, evolutionary robotics, homologous uniform crossover, neural networks, object oriented, subtree macro-mutation", abstract = "The Probabilistic Adaptive Mapping Developmental Genetic Programming (PAM DGP) algorithm that cooperatively Co-evolves a population of adaptive mappings and associated genotypes is used to learn recursive solutions given a function set consisting of general (not implicitly recursive) machine-language instructions. PAM DGP using redundant encodings to model the evolution of the biological genetic code is found to more efficiently learn 2nd and 3rd order recursive Fibonacci functions than related developmental systems and traditional linear GP. PAM DGP using redundant encoding is also demonstrated to produce the semantically highest quality solutions for all three recursive functions considered (Factorial, 2nd and 3rd order Fibonacci). PAM DGP is then shown to have produced such solutions by evolving redundant mappings to select and emphasise appropriate subsets of the function set useful for producing the naturally recursive solutions.", notes = "GECCO-2007 A joint meeting of the sixteenth international conference on genetic algorithms (ICGA-2007) and the twelfth annual genetic programming conference (GP-2007). ACM Order Number 910071", } @InProceedings{Agapitos:2007:cec, title = "Multiobjective Techniques for the Use of State in Genetic Programming Applied to Simulated Car Racing", author = "Alexandros Agapitos and Julian Togelius and Simon M. Lucas", booktitle = "2007 IEEE Congress on Evolutionary Computation", year = "2007", editor = "Dipti Srinivasan and Lipo Wang", pages = "1562--1569", address = "Singapore", month = "25-28 " # sep, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", ISBN = "1-4244-1340-0", file = "1977.pdf", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CEC.2007.4424659", abstract = "Multi-objective optimisation is applied to encourage the effective use of state variables in car controlling programs evolved using Genetic Programming. Three different metrics for measuring the use of state within a program are introduced. Comparisons are performed among multi- and single-objective fitness functions with respect to learning speed and final fitness of evolved individuals, and attempts are made at understanding whether there is a trade-off between good performance and stateful controllers in this problem domain.", notes = "CEC 2007 - A joint meeting of the IEEE, the EPS, and the IET. IEEE Catalog Number: 07TH8963C", } @InProceedings{Agapitos:2008:gecco, author = "Alexandros Agapitos and Matthew Dyson and Simon M. Lucas and Francisco Sepulveda", title = "Learning to recognise mental activities: genetic programming of stateful classifiers for brain-computer interfacing", booktitle = "GECCO '08: Proceedings of the 10th annual conference on Genetic and evolutionary computation", year = "2008", editor = "Maarten Keijzer and Giuliano Antoniol and Clare Bates Congdon and Kalyanmoy Deb and Benjamin Doerr and Nikolaus Hansen and John H. Holmes and Gregory S. Hornby and Daniel Howard and James Kennedy and Sanjeev Kumar and Fernando G. Lobo and Julian Francis Miller and Jason Moore and Frank Neumann and Martin Pelikan and Jordan Pollack and Kumara Sastry and Kenneth Stanley and Adrian Stoica and El-Ghazali Talbi and Ingo Wegener", isbn13 = "978-1-60558-130-9", pages = "1155--1162", address = "Atlanta, GA, USA", URL = "http://gpbib.cs.ucl.ac.uk/gecco2008/docs/p1155.pdf", DOI = "doi:10.1145/1389095.1389326", publisher = "ACM", publisher_address = "New York, NY, USA", month = "12-16 " # jul, keywords = "genetic algorithms, genetic programming, Brain computer interface, classification on Raw signal, stateful representation, statistical signal primitives", size = "8 pages", abstract = "Two families (stateful and stateless) of genetically programmed classifiers were tested on a five class brain-computer interface (BCI) data set of raw EEG signals. The ability of evolved classifiers to discriminate mental tasks from each other were analysed in terms of accuracy, precision and recall. A model describing the dynamics of state usage in stateful programs is introduced. An investigation of relationships between the model attributes and associated classification results was made. The results show that both stateful and stateless programs can be successfully evolved for this task, though stateful programs start from lower fitness and take longer to evolve", notes = "GECCO-2008 A joint meeting of the seventeenth international conference on genetic algorithms (ICGA-2008) and the thirteenth annual genetic programming conference (GP-2008). ACM Order Number 910081. Also known as \cite{1389326}", } @InProceedings{Agapitos2:2008:gecco, author = "Alexandros Agapitos and Matthew Dyson and Jenya Kovalchuk and Simon Mark Lucas", title = "On the genetic programming of time-series predictors for supply chain management", booktitle = "GECCO '08: Proceedings of the 10th annual conference on Genetic and evolutionary computation", year = "2008", editor = "Maarten Keijzer and Giuliano Antoniol and Clare Bates Congdon and Kalyanmoy Deb and Benjamin Doerr and Nikolaus Hansen and John H. Holmes and Gregory S. Hornby and Daniel Howard and James Kennedy and Sanjeev Kumar and Fernando G. Lobo and Julian Francis Miller and Jason Moore and Frank Neumann and Martin Pelikan and Jordan Pollack and Kumara Sastry and Kenneth Stanley and Adrian Stoica and El-Ghazali Talbi and Ingo Wegener", isbn13 = "978-1-60558-130-9", pages = "1163--1170", address = "Atlanta, GA, USA", URL = "http://gpbib.cs.ucl.ac.uk/gecco2008/docs/p1163.pdf", URL = "http://privatewww.essex.ac.uk/~yvkova/Papers/GP_GECCO08.pdf", DOI = "doi:10.1145/1389095.1389327", publisher = "ACM", publisher_address = "New York, NY, USA", month = "12-16 " # jul, keywords = "genetic algorithms, genetic programming, Iterated single-step prediction, prediction/forecasting, single-step prediction, statistical time-series Features", notes = "GECCO-2008 A joint meeting of the seventeenth international conference on genetic algorithms (ICGA-2008) and the thirteenth annual genetic programming conference (GP-2008). ACM Order Number 910081. Also known as \cite{1389327}", } @InProceedings{Agapitos:2008:CIG, author = "Alexandros Agapitos and Julian Togelius and Simon M. Lucas and Jurgen Schmidhuber and Andreas Konstantinidis", title = "Generating Diverse Opponents with Multiobjective Evolution", booktitle = "Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games", year = "2008", pages = "135--142", address = "Perth, Australia", month = dec # " 15-18", publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Reinforcement Learning, Multiobjective Evolution, AI in Computer Games, EMOA, Car Racing, MOGA, AI game agent, computational intelligence, diverse opponent generation, game play learning, multiobjective evolutionary algorithm, nonplayer character, computer games, evolutionary computation, learning (artificial intelligence), multi-agent systems", URL = "http://julian.togelius.com/Agapitos2008Generating.pdf", DOI = "doi:10.1109/CIG.2008.5035632", abstract = "For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way to use multiobjective evolutionary algorithms to automatically create populations of NPCs, such as opponents and collaborators, that are interestingly diverse in behaviour space. Experiments are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of GP-based controllers yield Pareto fronts of interesting controllers.", notes = "Also known as \cite{5035632}", } @InProceedings{agapitos_etal:ppsn2010, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Evolutionary Learning of Technical Trading Rules without Data-mining Bias", booktitle = "PPSN 2010 11th International Conference on Parallel Problem Solving From Nature", pages = "294--303", year = "2010", volume = "6238", editor = "Robert Schaefer and Carlos Cotta and Joanna Kolodziej and Guenter Rudolph", publisher = "Springer", series = "Lecture Notes in Computer Science", isbn13 = "978-3-642-15843-8", address = "Krakow, Poland", month = "11-15 " # sep, keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1007/978-3-642-15844-5_30", abstract = "In this paper we investigate the profitability of evolved technical trading rules when controlling for data-mining bias. For the first time in the evolutionary computation literature, a comprehensive test for a rule's statistical significance using Hansen's Superior Predictive Ability is explicitly taken into account in the fitness function, and multi-objective evolutionary optimisation is employed to drive the search towards individual rules with better generalisation abilities. Empirical results on a spot foreign-exchange market index suggest that increased out-of-sample performance can be obtained after accounting for data-mining bias effects in a multi-objective fitness function, as compared to a single-criterion fitness measure that considers solely the average return.", } @InProceedings{Agapitos:2010:AIAI, author = "Alexandros Agapitos and Andreas Konstantinidis and Haris Haralambous and Harris Papadopoulos", title = "Evolutionary Prediction of Total Electron Content over Cyprus", booktitle = "6th IFIP Advances in Information and Communication Technology AIAI 2010", year = "2010", editor = "Harris Papadopoulos and Andreas Andreou and Max Bramer", volume = "339", series = "IFIP Advances in Information and Communication Technology", pages = "387--394", address = "Larnaca, Cyprus", month = oct # " 6-7", publisher = "Springer", keywords = "genetic algorithms, genetic programming, Evolutionary Algorithms, Global Positioning System, Total Electron Content", DOI = "doi:10.1007/978-3-642-16239-8_50", abstract = "Total Electron Content (TEC) is an ionospheric characteristic used to derive the signal delay imposed by the ionosphere on trans-ionospheric links and subsequently overwhelm its negative impact in accurate position determination. In this paper, an Evolutionary Algorithm (EA), and particularly a Genetic Programming (GP) based model is designed. The proposed model is based on the main factors that influence the variability of the predicted parameter on a diurnal, seasonal and long-term time-scale. Experimental results show that the GP-model, which is based on TEC measurements obtained over a period of 11 years, has produced a good approximation of the modeled parameter and can be implemented as a local model to account for the ionospheric imposed error in positioning. The GP-based approach performs better than the existing Neural Network-based approach in several cases.", affiliation = "School of Computer Science and Informatics, University College Dublin, Dublin, Ireland", notes = "http://www.cs.ucy.ac.cy/aiai2010/", } @InProceedings{agapitosetal:2010:cfe, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Promoting the generalisation of genetically induced trading rules", booktitle = "Proceedings of the 4th International Conference on Computational and Financial Econometrics CFE'10", year = "2010", editor = "G. Kapetanios and O. Linton and M. McAleer and E. Ruiz", pages = "E678", address = "Senate House, University of London, UK", month = "10-12 " # dec, organisation = "CSDA, LSE, Queen Mary and Westerfield College", publisher = "ERCIM", keywords = "genetic algorithms, genetic programming", URL = "http://www.cfe-csda.org/cfe10/LondonBoA.pdf", size = "Abstracts only", abstract = "The goal of Machine Learning is not to induce an exact representation of the training patterns themselves, but rather to build a model of the underlying pattern-generation process. One of the most important aspects of this computational process is how to obtain general models that are representative of the true concept, and as a result, perform efficiently when presented with novel patterns from that concept. A particular form of evolutionary machine learning, Genetic Programming, tackles learning problems by means of an evolutionary process of program discovery. In this paper we investigate the profitability of evolved technical trading rules when accounting for the problem of over-fitting. Out-of-sample rule performance deterioration is a well-known problem, and has been mainly attributed to the tendency of the evolved models to find meaningless regularities in the training dataset due to the high dimensionality of features and the rich hypothesis space. We present a review of the major established methods for promoting generalisation in conventional machine learning paradigms. Then, we report empirical results of adapting such techniques to the Genetic Programming methodology, and applying it to discover trading rules for various financial datasets.", notes = "http://www.cfe-csda.org/cfe10/", } @InProceedings{agapitos:2011:EuroGP, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon and Theodoros Theodoridis", title = "Maximum Margin Decision Surfaces for Increased Generalisation in Evolutionary Decision Tree Learning", booktitle = "Proceedings of the 14th European Conference on Genetic Programming, EuroGP 2011", year = "2011", month = "27-29 " # apr, editor = "Sara Silva and James A. Foster and Miguel Nicolau and Mario Giacobini and Penousal Machado", series = "LNCS", volume = "6621", publisher = "Springer Verlag", address = "Turin, Italy", pages = "61--72", organisation = "EvoStar", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-20406-7", DOI = "doi:10.1007/978-3-642-20407-4_6", abstract = "Decision tree learning is one of the most widely used and practical methods for inductive inference. We present a novel method that increases the generalisation of genetically-induced classification trees, which employ linear discriminants as the partitioning function at each internal node. Genetic Programming is employed to search the space of oblique decision trees. At the end of the evolutionary run, a (1+1) Evolution Strategy is used to geometrically optimise the boundaries in the decision space, which are represented by the linear discriminant functions. The evolutionary optimisation concerns maximising the decision-surface margin that is defined to be the smallest distance between the decision-surface and any of the samples. Initial empirical results of the application of our method to a series of datasets from the UCI repository suggest that model generalisation benefits from the margin maximisation, and that the new method is a very competent approach to pattern classification as compared to other learning algorithms.", notes = "Part of \cite{Silva:2011:GP} EuroGP'2011 held in conjunction with EvoCOP2011 EvoBIO2011 and EvoApplications2011", } @InProceedings{Agapitos:2011:GECCOcomp, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Stateful program representations for evolving technical trading rules", booktitle = "GECCO '11: Proceedings of the 13th annual conference companion on Genetic and evolutionary computation", year = "2011", editor = "Natalio Krasnogor and Pier Luca Lanzi and Andries Engelbrecht and David Pelta and Carlos Gershenson and Giovanni Squillero and Alex Freitas and Marylyn Ritchie and Mike Preuss and Christian Gagne and Yew Soon Ong and Guenther Raidl and Marcus Gallager and Jose Lozano and Carlos Coello-Coello and Dario Landa Silva and Nikolaus Hansen and Silja Meyer-Nieberg and Jim Smith and Gus Eiben and Ester Bernado-Mansilla and Will Browne and Lee Spector and Tina Yu and Jeff Clune and Greg Hornby and Man-Leung Wong and Pierre Collet and Steve Gustafson and Jean-Paul Watson and Moshe Sipper and Simon Poulding and Gabriela Ochoa and Marc Schoenauer and Carsten Witt and Anne Auger", isbn13 = "978-1-4503-0690-4", keywords = "genetic algorithms, genetic programming: Poster", pages = "199--200", month = "12-16 " # jul, organisation = "SIGEVO", address = "Dublin, Ireland", DOI = "doi:10.1145/2001858.2001969", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "A family of stateful program representations in grammar-based Genetic Programming are being compared against their stateless counterpart in the problem of binary classification of sequences of daily prices of a financial asset. Empirical results suggest that stateful classifiers learn as fast as stateless ones but generalise better to unseen data, rendering this form of program representation strongly appealing to the automatic programming of technical trading rules.", notes = "Also known as \cite{2001969} Distributed on CD-ROM at GECCO-2011. ACM Order Number 910112.", } @InProceedings{Agapitos:2011:CIG, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon and Theodoros Theodoridis", title = "Learning Environment Models in Car Racing Using Stateful Genetic Programming", booktitle = "Proceedings of the 2011 IEEE Conference on Computational Intelligence and Games", year = "2011", address = "Seoul, South Korea", pages = "219--226", month = "31 " # aug # " - 3 " # sep, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Reinforcement Learning, Multiobjective Evolution, AI in Computer Games, Car Racing, AI game agent, computational intelligence, diverse opponent generation, game play learning, nonplayer character, computer games, evolutionary computation, learning (artificial intelligence), multi-agent systems, 2D data structures, artificial agents, car racing games, learning environment models, model building behaviour, modular programs, non player characters, cognition, computer games, data structures, learning (artificial intelligence), multi-agent systems", isbn13 = "978-1-4577-0010-1", URL = "http://cilab.sejong.ac.kr/cig2011/proceedings/CIG2011/papers/paper54.pdf", DOI = "doi:10.1109/CIG.2011.6032010", size = "8 pages", abstract = "For computational intelligence to be useful in creating game agent AI we need to focus on methods that allow the creation and maintenance of models for the environment, which the artificial agents inhabit. Maintaining a model allows an agent to plan its actions more effectively by combining immediate sensory information along with a memories that have been acquired while operating in that environment. To this end, we propose a way to build environment models for non-player characters in car racing games using stateful Genetic Programming. A method is presented, where general-purpose 2-dimensional data-structures are used to build a model of the racing track. Results demonstrate that model-building behaviour can be cooperatively coevolved with car-controlling behaviour in modular programs that make use of these models in order to navigate successfully around a racing track.", notes = "Indexed memory. Also known as \cite{6032010}", } @InCollection{Agapitos:NCFE:2011, author = "Alexandros Agapitos and Abhinav Goyal and Cal Muckley", title = "An Evolutionary Algorithmic Investigation of {US} Corporate Payout Policy", booktitle = "Natural Computing in Computational Finance (Volume 4)", publisher = "Springer", year = "2012", editor = "Anthony Brabazon and Michael O'Neill and Dietmar Maringer", volume = "380", series = "Studies in Computational Intelligence", chapter = "7", pages = "123--139", keywords = "genetic algorithms, genetic programming, US Corporate Payout Policy, Symbolic Regression", isbn13 = "978-3-642-23335-7", URL = "http://hdl.handle.net/10197/3552", URL = "https://researchrepository.ucd.ie/bitstream/10197/3552/1/gp_bookchapter.pdf", URL = "http://www.springer.com/engineering/computational+intelligence+and+complexity/book/978-3-642-23335-7", DOI = "doi:10.1007/978-3-642-23336-4_7", abstract = "This Chapter examines cash dividends and share repurchases in the United States during the period 1990 to 2008. In the extant literature a variety of classical statistical methodologies have been adopted, foremost among these is the method of panel regression modelling. Instead, in this Chapter, we have informed our model specifications and our coefficient estimates using a genetic program. Our model captures effects from a wide range of pertinent proxy variables related to the agency cost-based life cycle theory, the signalling theory and the catering theory of corporate payout policy determination. In line with the extant literature, our findings indicate the predominant importance of the agency-cost based life cycle theory. The adopted evolutionary algorithm approach also provides important new insights concerning the influence of firm size, the concentration of firm ownership and cash flow uncertainty with respect to corporate payout policy determination in the United States.", } @InProceedings{agapitos:evoapps12, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Evolving Seasonal Forecasting Models with Genetic Programming in the Context of Pricing Weather-Derivatives", booktitle = "Applications of Evolutionary Computing, EvoApplications 2012: EvoCOMNET, EvoCOMPLEX, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoNUM, EvoPAR, EvoRISK, EvoSTIM, EvoSTOC", year = "2011", month = "11-13 " # apr, editor = "Cecilia {Di Chio} and Alexandros Agapitos and Stefano Cagnoni and Carlos Cotta and F. {Fernandez de Vega} and Gianni A. {Di Caro} and Rolf Drechsler and Aniko Ekart and Anna I Esparcia-Alcazar and Muddassar Farooq and William B. Langdon and Juan J. Merelo and Mike Preuss and Hendrik Richter and Sara Silva and Anabela Simoes and Giovanni Squillero and Ernesto Tarantino and Andrea G. B. Tettamanzi and Julian Togelius and Neil Urquhart and A. Sima Uyar and Georgios N. Yannakakis", series = "LNCS", volume = "7248", publisher = "Springer Verlag", address = "Malaga, Spain", publisher_address = "Berlin", pages = "135--144", organisation = "EvoStar", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-29177-7", DOI = "doi:10.1007/978-3-642-29178-4_14", size = "10 pages", abstract = "In this study we evolve seasonal forecasting temperature models, using Genetic Programming (GP), in order to provide an accurate, localised, long-term forecast of a temperature profile as part of the broader process of determining appropriate pricing model for weather-derivatives, financial instruments that allow organisations to protect themselves against the commercial risks posed by weather fluctuations. Two different approaches for time-series modelling are adopted. The first is based on a simple system identification approach whereby the temporal index of the time-series is used as the sole regressor of the evolved model. The second is based on iterated single-step prediction that resembles autoregressive and moving average models in statistical time-series modelling. Empirical results suggest that GP is able to successfully induce seasonal forecasting models, and that autoregressive models compose a more stable unit of evolution in terms of generalisation performance for the three datasets investigated.", notes = "EvoFIN Part of \cite{DiChio:2012:EvoApps} EvoApplications2012 held in conjunction with EuroGP2012, EvoCOP2012, EvoBio'2012 and EvoMusArt2012", affiliation = "Financial Mathematics and Computation Research Cluster Natural Computing Research and Applications Group Complex and Adaptive Systems Laboratory, University College Dublin, Ireland", } @InCollection{Agapitos:FDMCI:2012, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Genetic Programming for the Induction of Seasonal Forecasts: A Study on Weather Derivatives", booktitle = "Financial Decision Making Using Computational Intelligence", publisher = "Springer", year = "2012", editor = "Doumpos Michael and Zopounidis Constantin and Pardalos Panos", volume = "70", series = "Springer Optimization and Its Applications", chapter = "6", pages = "153--182", note = "Due: July 31, 2012", keywords = "genetic algorithms, genetic programming, Weather derivatives pricing, Seasonal temperature forecasting, Autoregressive models, Supervised ensemble learning, Generalisation", isbn13 = "978-1-4614-3772-7", URL = "http://www.springer.com/mathematics/applications/book/978-1-4614-3772-7", } @InProceedings{conf/ppsn/Agapitos12, author = "Alexandros Agapitos and Anthony Brabazon and Michael O'Neill", title = "Controlling Overfitting in Symbolic Regression Based on a Bias/Variance Error Decomposition", booktitle = "Parallel Problem Solving from Nature, PPSN XII (part 1)", year = "2012", editor = "Carlos A. {Coello Coello} and Vincenzo Cutello and Kalyanmoy Deb and Stephanie Forrest and Giuseppe Nicosia and Mario Pavone", volume = "7491", series = "Lecture Notes in Computer Science", pages = "438--447", address = "Taormina, Italy", month = sep # " 1-5", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-32936-4", DOI = "doi:10.1007/978-3-642-32937-1_44", size = "10 pages", abstract = "We consider the fundamental property of generalisation of data-driven models evolved by means of Genetic Programming (GP). The statistical treatment of decomposing the regression error into bias and variance terms provides insight into the generalisation capability of this modelling method. The error decomposition is used as a source of inspiration to design a fitness function that relaxes the sensitivity of an evolved model to a particular training dataset. Results on eight symbolic regression problems show that new method is capable on inducing better-generalising models than standard GP for most of the problems.", affiliation = "Natural Computing Research and Applications Group, University College Dublin, Ireland", } @InProceedings{agapitos:2013:EuroGP, author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", title = "Adaptive Distance Metrics for Nearest Neighbour Classification based on Genetic Programming", booktitle = "Proceedings of the 16th European Conference on Genetic Programming, EuroGP 2013", year = "2013", month = "3-5 " # apr, editor = "Krzysztof Krawiec and Alberto Moraglio and Ting Hu and A. Sima Uyar and Bin Hu", series = "LNCS", volume = "7831", publisher = "Springer Verlag", address = "Vienna, Austria", pages = "1--12", organisation = "EvoStar", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-37206-3", DOI = "doi:10.1007/978-3-642-37207-0_1", abstract = "Nearest Neighbour (NN) classification is a widely-used, effective method for both binary and multi-class problems. It relies on the assumption that class conditional probabilities are locally constant. However, this assumption becomes invalid in high dimensions, and severe bias can be introduced, which degrades the performance of the method. The employment of a locally adaptive distance metric becomes crucial in order to keep class conditional probabilities approximately uniform, whereby better classification performance can be attained. This paper presents a locally adaptive distance metric for NN classification based on a supervised learning algorithm (Genetic Programming) that learns a vector of feature weights for the features composing an instance query. Using a weighted Euclidean distance metric, this has the effect of adaptive neighbourhood shapes to query locations, stretching the neighbourhood along the directions for which the class conditional probabilities don't change much. Initial empirical results on a set of real-world classification datasets showed that the proposed method enhances the generalisation performance of standard NN algorithm, and that it is a competent method for pattern classification as compared to other learning algorithms.", notes = "Part of \cite{Krawiec:2013:GP} EuroGP'2013 held in conjunction with EvoCOP2013, EvoBIO2013, EvoMusArt2013 and EvoApplications2013", } @InProceedings{agapitos:2014:EuroGP, author = "Alexandros Agapitos and James McDermott and Michael O'Neill and Ahmed Kattan and Anthony Brabazon", title = "Higher Order Functions for Kernel Regression", booktitle = "17th European Conference on Genetic Programming", year = "2014", editor = "Miguel Nicolau and Krzysztof Krawiec and Malcolm I. Heywood and Mauro Castelli and Pablo Garcia-Sanchez and Juan J. Merelo and Victor M. {Rivas Santos} and Kevin Sim", series = "LNCS", volume = "8599", publisher = "Springer", pages = "1--12", address = "Granada, Spain", month = "23-25 " # apr, organisation = "EvoStar", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-662-44302-6", DOI = "doi:10.1007/978-3-662-44303-3_1", abstract = "Kernel regression is a well-established nonparametric method, in which the target value of a query point is estimated using a weighted average of the surrounding training examples. The weights are typically obtained by applying a distance-based kernel function, which presupposes the existence of a distance measure. This paper investigates the use of Genetic Programming for the evolution of task-specific distance measures as an alternative to Euclidean distance. Results on seven real-world datasets show that the generalisation performance of the proposed system is superior to that of Euclidean-based kernel regression and standard GP.", notes = "Part of \cite{Nicolau:2014:GP} EuroGP'2014 held in conjunction with EvoCOP2014, EvoBIO2014, EvoMusArt2014 and EvoApplications2014", } @InProceedings{Agapitos:2014:CEC, title = "Ensemble {Bayesian} Model Averaging in Genetic Programming", author = "Alexandros Agapitos and Michael O'Neill and Anthony Brabazon", pages = "2451--2458", booktitle = "Proceedings of the 2014 IEEE Congress on Evolutionary Computation", year = "2014", month = "6-11 " # jul, editor = "Carlos A. {Coello Coello}", address = "Beijing, China", ISBN = "0-7803-8515-2", keywords = "genetic algorithms, Genetic programming, Data mining, Classification, clustering and data analysis", DOI = "doi:10.1109/CEC.2014.6900567", abstract = "This paper considers the general problem of function estimation via Genetic Programming (GP). Data analysts typically select a model from a population of models, and then proceed as if the selected model had generated the data. This approach ignores the uncertainty in model selection, leading to over-confident inferences and lack of generalisation. We adopt a coherent method for accounting for this uncertainty through a weighted averaging of all models competing in a population of GP. It is a principled statistical method for post-processing a population of programs into an ensemble, which is based on Bayesian Model Averaging (BMA). Under two different formulations of BMA, the predictive probability density function (PDF) of a response variable is a weighted average of PDFs centred around the individual predictions of component models that take the form of either standalone programs or ensembles of programs. The weights are equal to the posterior probabilities of the models generating the predictions, and reflect the models' skill on the training dataset. The method was applied to a number of synthetic symbolic regression problems, and results demonstrate that it generalises better than standard methods for model selection, as well as methods for ensemble construction in GP.", notes = "WCCI2014", } @InProceedings{agapitos:cec2015, author = "Alexandros Agapitos and Michael O'Neill and Miguel Nicolau and David Fagan and Ahmed Kattan and Kathleen Curran", title = "Deep Evolution of Feature Representations for Handwritten Digit Recognition", booktitle = "Proceedings of 2015 IEEE Congress on Evolutionary Computation (CEC 2015)", editor = "Yadahiko Murata", pages = "2452--2459", year = "2015", address = "Sendai, Japan", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CEC.2015.7257189", abstract = "A training protocol for learning deep neural networks, called greedy layer-wise training, is applied to the evolution of a hierarchical, feed-forward Genetic Programming based system for feature construction and object recognition. Results on a popular handwritten digit recognition benchmark clearly demonstrate that two layers of feature transformations improves generalisation compared to a single layer. In addition, we show that the proposed system outperforms several standard Genetic Programming systems, which are based on hand-designed features, and use different program representations and fitness functions.", notes = "CEC2015", } @InProceedings{EvoBafin16Agapitosetal, author = "Alexandros Agapitos and Anthony Brabazon and Michael O'Neill", title = "Genetic Programming with Memory For Financial Trading", booktitle = "19th European Conference on the Applications of Evolutionary Computation", year = "2016", editor = "Giovanni Squillero and Paolo Burelli", series = "Lecture Notes in Computer Science", volume = "9597", pages = "19--34", address = "Porto, Portugal", month = mar # " 30 - " # apr # " 1", organisation = "EvoStar", publisher = "Springer", keywords = "genetic algorithms, genetic programming", URL = "http://dx.doi.org/10.1007/978-3-319-31204-0_2", DOI = "doi:10.1007/978-3-319-31204-0_2", abstract = "A memory-enabled program representation in strongly-typed Genetic Programming (GP) is compared against the standard representation in a number of financial time-series modelling tasks. The paper first presents a survey of GP systems that use memory. Thereafter, a number of simulations show that memory-enabled programs generalise better than their standard counterparts in most datasets of this problem domain.", notes = "EvoApplications2016 held in conjunction with EuroGP'2016, EvoCOP2016 and EvoMusArt2016", } @Article{Agapitos:2016:GPEM, author = "Alexandros Agapitos and Michael O'Neill and Ahmed Kattan and Simon M. Lucas", title = "Recursion in tree-based genetic programming", journal = "Genetic Programming and Evolvable Machines", year = "2017", volume = "18", number = "2", pages = "149--183", month = jun, keywords = "genetic algorithms, genetic programming, Evolutionary program synthesis Recursive programs, Variation operators, Fitness landscape analysis", ISSN = "1389-2576", DOI = "doi:10.1007/s10710-016-9277-5", size = "35 pages", abstract = "Recursion is a powerful concept that enables a solution to a problem to be expressed as a relatively simple decomposition of the original problem into sub-problems of the same type. We survey previous research about the evolution of recursive programs in tree-based Genetic Programming. We then present an analysis of the fitness landscape of recursive programs, and report results on evolving solutions to a range of problems. We conclude with guidelines concerning the choice of fitness function and variation operators, as well as the handling of the halting problem. The main findings are as follows. The distribution of fitness changes initially as we look at programs of increasing size but once some threshold has been exceeded, it shows very little variation with size. Furthermore, the proportion of halting programs decreases as size increases. Recursive programs exhibit the property of weak causality; small changes in program structure may cause big changes in semantics. Nevertheless, the evolution of recursive programs is not a needle-in-a-haystack problem; the neighbourhoods of optimal programs are populated by halting individuals of intermediate fitness. Finally, mutation-based variation operators performed the best in finding recursive solutions. Evolution was also shown to outperform random search.", notes = "Factorial, Fibonacci, Exponentiation, Even-n-parity, Nth ftp://ftp.cs.ucl.ac.uk/genetic/gp-code/rand_tree.cc Random walks and error-distance correlation. Canberra distance. (hard) limit of 10000 recursive calls. '..the distribution of error is roughly independent of size' BUT '..Even-n-parity and Nth in Fig. 4d,e do not show a convergence..' 'Overall, our findings are in accordance with simulation results published in \cite{langdon:2006:eurogp}'. 'Fig. 4 Proportion of halting programs (out of 2,000,000 programs) as a function of program size' '..once programs containing recursive nodes wither away from the population, it is impossible to be introduced again.'", } @Article{Agapitos:2018:CMS, author = "Alexandros Agapitos and Anthony Brabazon and Michael O'Neill", title = "Regularised Gradient Boosting for Financial Time-series Modelling", journal = "Computational Management Science", year = "2017", volume = "14", number = "3", pages = "367--391", month = jul, keywords = "genetic algorithms, genetic programming, Boosting algorithms, Gradient boosting, Stagewise additive modelling, Regularisation, Financial time-series modelling, Financial forecasting, Feedforward neural networks, ANN, Noisy data, Ensemble learning", URL = "https://ideas.repec.org/a/spr/comgts/v14y2017i3d10.1007_s10287-017-0280-y.html", DOI = "doi:10.1007/s10287-017-0280-y", abstract = "Gradient Boosting (GB) learns an additive expansion of simple basis-models. This is accomplished by iteratively fitting an elementary model to the negative gradient of a loss function with respect to the expansion's values at each training data-point evaluated at each iteration. For the case of squared-error loss function, the negative gradient takes the form of an ordinary residual for a given training data-point. Studies have demonstrated that running GB for hundreds of iterations can lead to overfitting, while a number of authors showed that by adding noise to the training data, generalisation is impaired even with relatively few basis-models. Regularisation is realised through the shrinkage of every newly-added basis-model to the expansion. This paper demonstrates that GB with shrinkage-based regularisation is still prone to overfitting in noisy datasets. We use a transformation based on a sigmoidal function for reducing the influence of extreme values in the residuals of a GB iteration without removing them from the training set. This extension is built on top of shrinkage-based regularisation. Simulations using synthetic, noisy data show that the proposed method slows-down overfitting and reduces the generalisation error of regularised GB. The proposed method is then applied to the inherently noisy domain of financial time-series modelling. Results suggest that for the majority of datasets the method generalises better when compared against standard regularised GB, as well as against a range of other time-series modelling methods.", notes = "School of Computer Science, University College Dublin, Dublin, Ireland", } @Article{Agapitos:ieeeTEC, author = "Alexandros Agapitos and Roisin Loughran and Miguel Nicolau and Simon Lucas and Michael O'Neill and Anthony Brabazon", title = "A Survey of Statistical Machine Learning Elements in Genetic Programming", journal = "IEEE Transactions on Evolutionary Computation", year = "2019", volume = "23", number = "6", pages = "1029--1048", month = dec, keywords = "genetic algorithms, genetic programming, Statistical Machine Learning, SML, Generalisation, Overfitting, Classification, Symbolic Regression, Model selection, Regularisation, Model Averaging, Bias-Variance trade-off", ISSN = "1089-778X", URL = "http://ncra.ucd.ie/papers/08648159.pdf", DOI = "doi:10.1109/TEVC.2019.2900916", size = "20 pages", abstract = "Modern Genetic Programming operates within the Statistical Machine Learning framework. In this framework evolution needs to balance between approximation of an unknown target function on the training data and generalisation, which is the ability to predict well on new data. The article provides a survey and critical discussion of Statistical Machine Learning methods that enable Genetic Programming to generalise.", notes = "also known as \cite{8648159} School of Computer Science, University College Dublin, Ireland", } @InProceedings{agapow:1996:cbecv, author = "Paul-Michael Agapow", title = "Computational Brittleness and the Evolution of Computer Viruses", editor = "Hans-Michael Voigt and Werner Ebeling and Ingo Rechenberg and Hans-Paul Schwefel", booktitle = "Parallel Problem Solving From Nature IV. Proceedings of the International Conference on Evolutionary Computation", year = "1996", publisher = "Springer-Verlag", volume = "1141", series = "LNCS", pages = "2--11", address = "Berlin, Germany", publisher_address = "Heidelberg, Germany", month = "22-26 " # sep, keywords = "genetic algorithms, genetic programming", ISBN = "3-540-61723-X", DOI = "doi:10.1007/3-540-61723-X_964", size = "10 pages", abstract = "In recent years computer viruses have grown to be of great concern. They have also been proposed as prototypical artificial life, but the possibility of their evolution has been dismissed due to modern computer programs being computationally brittle (i.e. a random change to a functional program will almost certainly render it non-functional) and the series of steps required for the evolution of a new virus being improbable. These allegations are examined by studying homology between functional program sequences. It is concluded that programs are far less brittle than expected. While the evolution of viruses de novo is still unlikely, evolution of pre-existing viruses and programs is feasible. This has significant implications for computer security and evolutionary computation.", notes = "http://lautaro.fb10.tu-berlin.de/ppsniv.html PPSN4 (UNIX Sun RISC) {"}programs are far less brittle than expected{"}.", affiliation = "La Trobe University Computer Science V. 3083 Melbourne Australia V. 3083 Melbourne Australia", } @InCollection{agarwal:2000:GPWPPAPE, author = "Ashish Agarwal", title = "Genetic Programming for Wafer Property Prediction After Plasma Enhanced", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 2000", year = "2000", editor = "John R. Koza", pages = "16--24", address = "Stanford, California, 94305-3079 USA", month = jun, publisher = "Stanford Bookstore", keywords = "genetic algorithms, genetic programming", notes = "part of \cite{koza:2000:gagp}", } @InProceedings{agarwal:2023:SDECGE, author = "Ekansh Agarwal and Ajeet Kumar Verma and Anindya Pain and Shantanu Sarkar", title = "Probabilistic Analysis of a Geosynthetic Reinforced Soil Retaining Wall Under Seismic Conditions Using Genetic Programming", booktitle = "Soil Dynamics, Earthquake and Computational Geotechnical Engineering", year = "2023", publisher = "Springer", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/chapter/10.1007/978-981-19-6998-0_20", DOI = "doi:10.1007/978-981-19-6998-0_20", } @Article{Aggarwal:2011:ijcse, author = "Khushboo Aggarwal and Sunil Kumar Singh and Sakar Khattar", title = "A high Performance Algorithm for Solving large scale Travelling Salesman Problem using Distributed Memory Architectures", journal = "Indian Journal of Computer Science and Engineering", year = "2011", volume = "2", number = "4", pages = "516--521", month = aug # "-" # sep, keywords = "genetic algorithms, genetic programming, TSP, traveling salesman problem, fitness functions", ISSN = "2231-3850", annote = "The Pennsylvania State University CiteSeerX Archives", bibsource = "OAI-PMH server at citeseerx.ist.psu.edu", language = "en", oai = "oai:CiteSeerX.psu:10.1.1.300.6369", rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.6369", URL = "http://www.ijcse.com/docs/INDJCSE11-02-04-175.pdf", size = "6 pages", abstract = "In this paper, we present an intelligent solution system for travelling salesman problem. The solution has three stages. The first stage uses Clustering Analysis in Data Mining to classify all customers by a number of attributes, such as distance, demand level, the density of customer, and city layout. The second stage introduces how to generate feasible routing schemes for each vehicle type. Specifically, a depth-first search algorithm with control rules is presented to generate feasible routing schemes. In the last stage, a genetic programming model is applied to find the best possible solution. Finally, we present a paradigm for using this algorithm for distributed memory architectures to gain the benefits of parallel processing.", } @Misc{Aggarwal:intern, author = "Varun Aggarwal", title = "Prediction of Protein Secondary Structure using Genetic Programming", howpublished = "Summer Internship Project Report During June-July 2003", year = "2003", keywords = "genetic algorithms, genetic programming", URL = "http://web.mit.edu/varun_ag/www/psspreport.pdf", size = "23 pages", abstract = "Project 1:Using SOM and Genetic Programming to predict Protein Secondary structure Project 2: Improving PSIPRED Predictions using Genetic Programming", notes = "Under: Dr. Bob MacCallum, Stockholm Bioinformatics Center, Stockholm University, Sweden", } @InProceedings{maccallum:2004:eurogp, author = "Varun Aggarwal and Robert MacCallum", title = "Evolved Matrix Operations for Post-Processing Protein Secondary Structure Predictions", booktitle = "Genetic Programming 7th European Conference, EuroGP 2004, Proceedings", year = "2004", editor = "Maarten Keijzer and Una-May O'Reilly and Simon M. Lucas and Ernesto Costa and Terence Soule", volume = "3003", series = "LNCS", pages = "220--229", address = "Coimbra, Portugal", publisher_address = "Berlin", month = "5-7 " # apr, organisation = "EvoNet", publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming: Poster", ISBN = "3-540-21346-5", URL = "http://web.mit.edu/varun_ag/www/aggarwal-eurogp2004.pdf", DOI = "doi:10.1007/978-3-540-24650-3_20", abstract = "Predicting the three-dimensional structure of proteins is a hard problem, so many have opted instead to predict the secondary structural state (usually helix, strand or coil) of each amino acid residue. This should be an easier task, but it now seems that a ceiling of around 76 percent per-residue three-state accuracy has been reached. Further improvements will require the correct processing of so-called {"}long-range information{"}. We present a novel application of genetic programming to evolve high level matrix operations to post-process secondary structure prediction probabilities produced by the popular, state-of-the-art neural network based PSIPRED by David Jones. We show that global and long-range information may be used to increase three-state accuracy by at least 0.26 percentage points - a small but statistically significant difference. This is on top of the 0.14 percentage point increase already made by PSIPRED's built-in filters.", notes = "Part of \cite{keijzer:2004:GP} EuroGP'2004 held in conjunction with EvoCOP2004 and EvoWorkshops2004", } @InCollection{Aggarwal:2006:GPTP, author = "Varun Aggarwal and Una-May O'Reilly", title = "Design of Posynomial Models for Mosfets: Symbolic Regression Using Genetic Algorithms", booktitle = "Genetic Programming Theory and Practice {IV}", year = "2006", editor = "Rick L. Riolo and Terence Soule and Bill Worzel", volume = "5", series = "Genetic and Evolutionary Computation", pages = "219--236", address = "Ann Arbor", month = "11-13 " # may, publisher = "Springer", keywords = "genetic algorithms, genetic programming, circuit sizing, symbolic regression, posynomial models, geometric programming", ISBN = "0-387-33375-4", URL = "http://people.csail.mit.edu/unamay/publications-dir/gptp06.pdf", DOI = "doi:10.1007/978-0-387-49650-4_14", size = "19 pages", abstract = "Starting from a broad description of analogue circuit design in terms of topology design and sizing, we discuss the difficulties of sizing and describe approaches that are manual or automatic. These approaches make use of blackbox optimisation techniques such as evolutionary algorithms or convex optimization techniques such as geometric programming. Geometric programming requires posynomial expressions for a circuit's performance measurements. We show how a genetic algorithm can be exploited to evolve a polynomial expression (i.e. model) of transistor (i.e. mosfet) behaviour more accurately than statistical techniques in the literature.", notes = "part of \cite{Riolo:2006:GPTP} Published Jan 2007 after the workshop", } @Article{Aghbashlo:2016:Energy, author = "Mortaza Aghbashlo and Shahaboddin Shamshirband and Meisam Tabatabaei and Por Lip Yee and Yaser Nabavi Larimi", title = "The use of ELM-WT (extreme learning machine with wavelet transform algorithm) to predict exergetic performance of a {DI} diesel engine running on diesel/biodiesel blends containing polymer waste", journal = "Energy", volume = "94", pages = "443--456", year = "2016", ISSN = "0360-5442", DOI = "doi:10.1016/j.energy.2015.11.008", URL = "http://www.sciencedirect.com/science/article/pii/S0360544215015327", abstract = "In this study, a novel method based on Extreme Learning Machine with wavelet transform algorithm (ELM-WT) was designed and adapted to estimate the exergetic performance of a DI diesel engine. The exergetic information was obtained by calculating mass, energy, and exergy balance equations for the experimental trials conducted at various engine speeds and loads as well as different biodiesel and expanded polystyrene contents. Furthermore, estimation capability of the ELM-WT model was compared with that of the ELM, GP (genetic programming) and ANN (artificial neural network) models. The experimental results showed that an improvement in the exergetic performance modelling of the DI diesel engine could be achieved by the ELM-WT approach in comparison with the ELM, GP, and ANN methods. Furthermore, the results showed that the applied algorithm could learn thousands of times faster than the conventional popular learning algorithms. Obviously, the developed ELM-WT model could be used with a high degree of confidence for further work on formulating novel model predictive strategy for investigating exergetic performance of DI diesel engines running on various renewable and non-renewable fuels.", keywords = "genetic algorithms, genetic programming, Biodiesel, DI diesel engine, Exergetic performance parameters, Expanded polystyrene, Cost sensitivity analysis, Extreme learning machine-wavelet (ELM-WT)", } @Article{agnelli:2002:PRL, author = "Davide Agnelli and Alessandro Bollini and Luca Lombardi", title = "Image classification: an evolutionary approach", journal = "Pattern Recognition Letters", year = "2002", number = "1-3", volume = "23", pages = "303--309", month = jan, keywords = "genetic algorithms, genetic programming, Image classification, Supervised learning", ISSN = "0167-8655", broken = "http://www.sciencedirect.com/science/article/B6V15-443K10X-6/1/7af8206767ca79f9898fec720a84c656", DOI = "doi:10.1016/S0167-8655(01)00128-3", size = "7 pages", abstract = "Evolutionary algorithms are proving viable in solving complex optimization problems such as those typical of supervised learning approaches to image understanding. This paper presents an evolutionary approach to image classification and discusses some experimental results, suggesting that genetic programming could provide a convenient alternative to standard supervised learning methods.", } @InProceedings{Agrawal:2023:ICSE, author = "Arpan Agrawal and Emily First and Zhanna Kaufman and Tom Reichel and Shizhuo Zhang and Timothy Zhou and Alex Sanchez-Stern and Talia Ringer and Yuriy Brun", title = "Proofster: Automated Formal Verification", booktitle = "Proceedings of the Demonstrations Track at the 45th International Conference on Software Engineering (ICSE)", year = "2023", pages = "26--30", address = "Melbourne", month = "14-20 " # may, keywords = "genetic algorithms, genetic programming", isbn13 = "979-8-3503-2264-4", DOI = "doi:10.1109/ICSE-Companion58688.2023.00018", video_url = "https://youtu.be/xQAi66lRfwI/", code_url = "https://proofster.cs.umass.edu/", size = "5 pages", abstract = "Formal verification is an effective but extremely work-intensive method of improving software quality. Verifying the correctness of software systems often requires significantly more effort than implementing them in the first place, despite the existence of proof assistants, such as Coq, aiding the process. Recent work has aimed to fully automate the synthesis of formal verification proofs, but little tool support exists for practitioners. This paper presents Proofster, a web-based tool aimed at assisting developers with the formal verification process via proof synthesis. Proofster inputs a Coq theorem specifying a property of a software system and attempts to automatically synthesize a formal proof of the correctness of that property. When it is unable to produce a proof, Proofster outputs the proof-space search tree its synthesis explored, which can guide the developer to provide a hint to enable Proofster to synthesize the proof. Proofster runs online at https://proofster.cs.umass.edu/ and a video demonstrating Proofster is available at https://youtu.be/xQAi66lRfwI/.", notes = "Demo Track", } @InProceedings{aguilar:1998:rcmmcfssdft, author = "Jose L. Aguilar and Mariela Cerrada", title = "Reliability-Centered Maintenance Methodology-Based Fuzzy Classifier System Design for Fault Tolerance", booktitle = "Genetic Programming 1998: Proceedings of the Third Annual Conference", year = "1998", editor = "John R. Koza and Wolfgang Banzhaf and Kumar Chellapilla and Kalyanmoy Deb and Marco Dorigo and David B. Fogel and Max H. Garzon and David E. Goldberg and Hitoshi Iba and Rick Riolo", pages = "621", address = "University of Wisconsin, Madison, Wisconsin, USA", publisher_address = "San Francisco, CA, USA", month = "22-25 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms, classifiers", ISBN = "1-55860-548-7", notes = "GP-98", } @InProceedings{aguilar:1999:ABGAMOP, author = "Jose Aguilar and Pablo Miranda", title = "Approaches Based on Genetic Algorithms for Multiobjective Optimization Problems", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "3--10", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-873.pdf", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-873.ps", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InProceedings{aguilar:1999:TGADRSLS, author = "Jesus Aguilar and Jose Riquelme and Miguel Toro", title = "Three Geometric Approaches for representing Decision Rules in a Supervised Learning System", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "771", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems, poster papers", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-391.pdf", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GA-391.ps", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99). See also \cite{aguilar:1999:T}", } @InProceedings{aguilar:1999:T, author = "Jesus Aguilar and Jose Riquelme and Miguel Toro", title = "Three geometric approaches for representing decision rules in a supervised learning system", booktitle = "Late Breaking Papers at the 1999 Genetic and Evolutionary Computation Conference", year = "1999", editor = "Scott Brave and Annie S. Wu", pages = "8--15", address = "Orlando, Florida, USA", month = "13 " # jul, keywords = "Genetic Algorithms, data mining, supervised learning, hyper rectangles, rotated hyper rectangles, hyper ellipse", abstract = "hyperrectangles, rotated hyperrectangles and hyperellipses", notes = "GECCO-99LB", } @InProceedings{aguilar3:2001:gecco, title = "Fuzzy Classifier System and Genetic Programming on System Identification Problems", author = "Jose Aguilar and Mariela Cerrada", pages = "1245--1251", year = "2001", publisher = "Morgan Kaufmann", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2001)", editor = "Lee Spector and Erik D. Goodman and Annie Wu and W. B. Langdon and Hans-Michael Voigt and Mitsuo Gen and Sandip Sen and Marco Dorigo and Shahram Pezeshk and Max H. Garzon and Edmund Burke", address = "San Francisco, California, USA", publisher_address = "San Francisco, CA 94104, USA", month = "7-11 " # jul, keywords = "genetic algorithms, genetic programming, real world applications", ISBN = "1-55860-774-9", URL = "http://gpbib.cs.ucl.ac.uk/gecco2001/d24.pdf", notes = "GECCO-2001 A joint meeting of the tenth International Conference on Genetic Algorithms (ICGA-2001) and the sixth Annual Genetic Programming Conference (GP-2001) Part of \cite{spector:2001:GECCO}", } @InProceedings{WSEAS_640_Aguilar, author = "Jose Aguilar and Mariela Cerrada", title = "Genetic Programming-Based Approach for System Identification Applying Genetic Programming to obtain Separation", address = "Puerto De La Cruz, Tenerife, Spain", year = "2001", booktitle = "WSES International Conferences WSEAS NNA-FSFS-EC 2001", editor = "Nikos E. Mastorakis", pages = "6401--6406", month = feb # " 11-15", organisation = "The World Scientific and Engineering Academy and Society (WSEAS)", keywords = "genetic algorithms, genetic programming, Genetic Programming, Evolutionary Computation, Identification Systems", URL = "http://www.wseas.us/e-library/conferences/tenerife2001/papers/640.pdf", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.611.1267", size = "6 pages", abstract = "In this work, an approach based on Genetic Programming is proposed for the input-output systems identification problem. Laguerre's functions and the ARX method have been commonly used to solve the systems identification problem. Recently, approaches based on Artificial Neural Networks have been used to solve this problem. Genetic Programming is an Evolutionary Computation technique based on the evolution of mathematical symbols (constants, functions, variables, operators, etc.). To achieve the identification, a set of analysis trees is used to describe the different models (individuals) that our approach proposes during its execution. At the end of the evolutionary process, an input-output model of the system is proposed by our approach (it is the best individual).", notes = "paper ID number 640 http://www.wseas.us/e-library/conferences/tenerife2001/index.htm ", } @Misc{Aguilar:2004:sci, author = "J. Aguilar and J. Altamiranda", title = "A Data Mining Algorithm Based on the Genetic Programming", year = "2004", keywords = "genetic algorithms, genetic programming, Data Mining, Clustering", size = "10 pages", abstract = "Data Mining is composed by a set of methods to extract knowledgement from large database. One of these methods is Genetic Programming. In this work we use this method to build a Data Mining System that define a set of patterns in order to classify the data. We define a grammar, which is used by the Genetic Programming in order to define the rules that represent the patterns. In this way, we can group the data in class and simplify the information in the database according to the set of patterns.", notes = " J. Aguilar Universidad de los Andes, Facultad de Ingenieria, Departamento de Computacion, CEMISID, Merida, Venezuela, 5101 J. Altamiranda Universidad de los Andes, Facultad de Ingenieria, Postgrado de Computacion, CEMISID, Merida, Venezuela, 5101 ", } @InProceedings{Aguilar:DEU:cec2006, author = "Jose Aguilar and Gilberto Gonzalez", title = "Data Extrapolation Using Genetic Programming to Matrices Singular Values Estimation", booktitle = "Proceedings of the 2006 IEEE Congress on Evolutionary Computation", year = "2006", editor = "Gary G. Yen and Simon M. Lucas and Gary Fogel and Graham Kendall and Ralf Salomon and Byoung-Tak Zhang and Carlos A. Coello Coello and Thomas Philip Runarsson", pages = "3227--3230", address = "Vancouver, BC, Canada", month = "16-21 " # jul, publisher = "IEEE Press", ISBN = "0-7803-9487-9", URL = "http://ieeexplore.ieee.org/servlet/opac?punumber=11108", DOI = "doi:10.1109/CEC.2006.1688718", keywords = "genetic algorithms, genetic programming", abstract = "In mathematical models where the dimensions of the matrices are very large, the use of classical methods to compute the singular values is very time consuming and requires a lot of computational resources. In this way, it is necessary to find new faster methods to compute the singular values of a very large matrix. We present a method to estimate the singular values of a matrix based on Genetic Programming (GP). GP is an approach based on the evolutionary principles of the species. GP is used to make extrapolations of data out of sample data. The extrapolations of data are achieved by irregularity functions which approximate very well the trend of the sample data. GP produces from just simple's functions, operators and a fitness function, complex mathematical expressions that adjust smoothly to a group of points of the form (xi, yi). We obtain amazing mathematical formulas that follow the behaviour of the sample data. We compare our algorithm with two techniques: the linear regression and non linear regression approaches. Our results suggest that we can predict with some percentage of error the largest singular values of a matrix without computing the singular values of the whole matrix and using only some random selected columns of the matrix.", notes = "WCCI 2006 - A joint meeting of the IEEE, the EPS, and the IEE. IEEE Catalog Number: 06TH8846D", } @Article{AguilarRivera:2015:ESA, author = "Ruben Aguilar-Rivera and Manuel Valenzuela-Rendon and J. J. Rodriguez-Ortiz", title = "Genetic algorithms and {Darwinian} approaches in financial applications: A survey", journal = "Expert Systems with Applications", year = "2015", volume = "42", number = "21", pages = "7684--7697", month = "30 " # nov, keywords = "genetic algorithms, genetic programming, Evolutionary computation, Finance, Portfolio optimization, Survey", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2015.06.001", URL = "http://www.sciencedirect.com/science/article/pii/S0957417415003954", abstract = "This article presents a review of the application of evolutionary computation methods to solving financial problems. Genetic algorithms, genetic programming, multi-objective evolutionary algorithms, learning classifier systems, co-evolutionary approaches, and estimation of distribution algorithms are the techniques considered. The novelty of our approach comes in three different manners: it covers time lapses not included in other review articles, it covers problems not considered by others, and the scope covered by past and new references is compared and analysed. The results concluded the interest about methods and problems has changed through time. Although, genetic algorithms have remained the most popular approach in the literature. There are combinations of problems and solutions methods which are yet to be investigated.", } @InProceedings{aguirre:1999:EH, author = "Arturo Hernandez Aguirre and Carlos A. Coello Coello and Bill P. Buckles", title = "A Genetic Programming Approach to Logic Function Synthesis by Means of Multiplexers", booktitle = "Proceedings of the The First NASA/DOD Workshop on Evolvable Hardware", year = "1999", editor = "Adrian Stoica and Didier Keymeulen and Jason Lohn", pages = "46--53", address = "Pasadena, California", month = "19-21 " # jul, organisation = "Jet Propulsion Laboratory, California Institute of Technology", publisher = "IEEE Computer Society", keywords = "genetic algorithms, genetic programming, evolvable hardware, 1-control line multiplexer, Boolean functions, fitness function, genetic programming approach, logic function synthesis, minimisation, multiplexers, Boolean functions, logic design, minimisation, multiplexing equipment", ISBN = "0-7695-0256-3", DOI = "doi:10.1109/EH.1999.785434", abstract = "This paper presents an approach based on the use of genetic programming to synthesize logic functions. The proposed approach uses the 1-control line multiplexer as the only design unit, defining any logic function (defined by a truth table) through the replication of this single unit. Our fitness function first explores the search space trying to find a feasible design and then concentrates in the minimization of such (fully feasible) circuit. The proposed approach is illustrated using several sample Boolean functions.", notes = "EH-1999", } @InProceedings{aguirre:1999:CCMOGA, author = "Hernan E. Aguirre and Kiyoshi Tanaka and Tatsuo Sugimura", title = "Cooperative Crossover and Mutation Operators in Genetic Algorithms", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "772", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems, poster papers", ISBN = "1-55860-611-4", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @Article{Aguirre:2003:AIR, author = "Arturo Hernandez Aguirre and Carlos A. {Coello Coello}", title = "Evolutionary Synthesis of Logic Circuits Using Information Theory", journal = "Artificial Intelligence Review", year = "2003", volume = "20", number = "3-4", pages = "445--471", keywords = "genetic algorithms, genetic programming, circuit synthesis, computer-aided design, evolutionary algorithms, evolvable hardware, information theory", language = "English", publisher = "Kluwer Academic Publishers", ISSN = "0269-2821", annote = "The Pennsylvania State University CiteSeerX Archives", bibsource = "OAI-PMH server at citeseerx.ist.psu.edu", language = "en", oai = "oai:CiteSeerX.psu:10.1.1.378.9801", rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.9801", URL = "http://hera.ugr.es/doi/14977278.pdf", URL = "http://dx.doi.org/10.1023/B%3AAIRE.0000006603.98023.97", DOI = "doi:10.1023/B:AIRE.0000006603.98023.97", abstract = "In this paper, we propose the use of Information Theory as the basis for designing a fitness function for Boolean circuit design using Genetic Programming. Boolean functions are implemented by replicating binary multiplexers. Entropy-based measures, such as Mutual Information and Normalised Mutual Information are investigated as tools for similarity measures between the target and evolving circuit. Three fitness functions are built over a primitive one. We show that the landscape of Normalized Mutual Information is more amenable for being used as a fitness function than simple Mutual Information. The evolutionary synthesised circuits are compared to the known optimum size. A discussion of the potential of the Information-Theoretical approach is given.", } @InProceedings{Hernandez-Aguirre:2004:MIFFfECS, title = "Mutual Information-based Fitness Functions for Evolutionary Circuit Synthesis", author = "Arturo Hernandez-Aguirre and Carlos Coello-Coello", pages = "1309--1316", booktitle = "Proceedings of the 2004 IEEE Congress on Evolutionary Computation", year = "2004", publisher = "IEEE Press", month = "20-23 " # jun, address = "Portland, Oregon", volume = "2", keywords = "genetic algorithms, genetic programming, EHW, Evolutionary Design Automation, Evolutionary design \& evolvable hardware", ISBN = "0-7803-8515-2", URL = "http://delta.cs.cinvestav.mx/~ccoello/conferences/cec04-muxmutual.pdf.gz", DOI = "doi:10.1109/CEC.2004.1331048", size = "8 pages", abstract = "Mutual Information and Normalised Mutual Information measures are investigated. The goal is the analysis of some fitness functions based in mutual information and what problems prevent them from common use. We identify and find a clear explanation to them, thereafter, we propose new fitness functions and ran several experiments to investigate their effect on the search space, convergence time, and quality of solutions.", notes = "CEC 2004 - A joint meeting of the IEEE, the EPS, and the IEE.", } @Article{AGWU:2018:PT, author = "Okorie E. Agwu and Julius U. Akpabio and Sunday B. Alabi and Adewale Dosunmu", title = "Settling velocity of drill cuttings in drilling fluids: A review of experimental, numerical simulations and artificial intelligence studies", journal = "Powder Technology", volume = "339", pages = "728--746", year = "2018", keywords = "genetic algorithms, genetic programming, Artificial Intelligence, Drill cuttings, Numerical simulations, Settling velocity", ISSN = "0032-5910", DOI = "doi:10.1016/j.powtec.2018.08.064", URL = "http://www.sciencedirect.com/science/article/pii/S0032591018307022", abstract = "In this paper, a comprehensive review of experimental, numerical and artificial intelligence studies on the subject of cuttings settling velocity in drilling muds made by researchers over the last seven decades is brought to the fore. In this respect, 91 experimental, 13 numerical simulations and 7 artificial intelligence researches were isolated, reviewed, tabulated and discussed. A comparison of the three methods and the challenges facing each of these methods were also reviewed. The major outcomes of this review include: (1) the unanimity among experimental researchers that mud rheology, particle size and shape and wall effect are major parameters affecting the settling velocity of cuttings in wellbores; (2) the prevalence of cuttings settling velocity experiments done with the mud in static conditions and the wellbore in the vertical configuration; (3) the extensive use of rigid particles of spherical shape to represent drill cuttings due to their usefulness in experimental visualization, particle tracking, and numerical implementation; (4) the existence of an artificial intelligence technique - multi-gene genetic programming (MGGP) which can provide an explicit equation that can help in predicting settling velocity; (5) the limited number of experimental studies factoring in the effect of pipe rotation and well inclination effects on the settling velocity of cuttings and (6) the most applied numerical method for determining settling velocity is the finite element method. Despite these facts, there is need to perform more experiments with real drill cuttings and factor in the effects of conditions such as drillstring rotation and well inclination and use data emanating therefrom to develop explicit models that would include the effects of these. It should be noted however, that the aim of this paper is not to create an encyclopaedia of particle settling velocity research, but to provide to the researcher with a basic, theoretical, experimental and numerical overview of what has so far been achieved in the area of cuttings settling velocity in drilling muds", keywords = "genetic algorithms, genetic programming, Artificial Intelligence, Drill cuttings, Numerical simulations, Settling velocity", } @Article{AGWU:2021:UOGT, author = "Okorie Ekwe Agwu and Julius Udoh Akpabio and Adewale Dosunmu", title = "Modeling the downhole density of drilling muds using multigene genetic programming", journal = "Upstream Oil and Gas Technology", volume = "6", pages = "100030", year = "2021", ISSN = "2666-2604", DOI = "doi:10.1016/j.upstre.2020.100030", URL = "https://www.sciencedirect.com/science/article/pii/S266626042030030X", keywords = "genetic algorithms, genetic programming, Multigene genetic programming, Downhole mud density, Drilling mud, HTHP", abstract = "The main objective of this paper is to use experimental measurements of downhole pressure, temperature and initial mud density to predict downhole density using multigene genetic programming. From the results, the mean square error for the WBM density model was 0.0012, with a mean absolute error of 0.0246 and the square of correlation coefficient (R2) was 0.9998; while for the OBM, the MSE was 0.000359 with MAE of 0.01436 and R2 of 0.99995. In assessing the OBM model's generalization capability, the model had an MSE of 0.031, MAE of 0.138 and mean absolute percentage error (MAPE) of 0.95percent", } @Misc{nlin/0607029, author = "Dilip P. Ahalpara and Jitendra C. Parikh", title = "Modeling Time Series of Real Systems using Genetic Programming", howpublished = "ArXiv Nonlinear Sciences e-prints", year = "2006", month = "14 " # jul, note = "Submitted to Physical Review E", adsurl = "http://adsabs.harvard.edu/cgi-bin/nph-bib_query?bibcode=2006nlin......7029A&db_key=PRE", adsnote = "Provided by the Smithsonian/NASA Astrophysics Data System", keywords = "genetic algorithms, genetic programming", URL = "http://arxiv.org/PS_cache/nlin/pdf/0607/0607029v1.pdf", size = "10 pages", abstract = "Analytic models of two computer generated time series (Logistic map and Rossler system) and two real time series (ion saturation current in Aditya Tokamak plasma and NASDAQ composite index) are constructed using Genetic Programming (GP) framework. In each case, the optimal map that results from fitting part of the data set also provides a very good description of rest of the data. Predictions made using the map iteratively range from being very good to fair.", notes = "nlin/0607029 See also \cite{Ahalpara:2008:IJMPC}", } @Article{Ahalpara:2008:IJMPC, author = "Dilip P. Ahalpara and Jitendra C. Parikh", title = "Genetic Programming based approach for Modeling Time Series data of real systems", journal = "International Journal of Modern Physics C, Computational Physics and Physical Computation", year = "2008", volume = "19", number = "1", pages = "63--91", keywords = "genetic algorithms, genetic programming, Time series analysis, artificial neural networks", DOI = "doi:10.1142/S0129183108011942", abstract = "Analytic models of a computer generated time series (logistic map) and three real time series (ion saturation current in Aditya Tokamak plasma, NASDAQ composite index and Nifty index) are constructed using Genetic Programming (GP) framework. In each case, the optimal map that results from fitting part of the data set also provides a very good description of the rest of the data. Predictions made using the map iteratively are very good for computer generated time series but not for the data of real systems. For such cases, an extended GP model is proposed and illustrated. A comparison of these results with those obtained using Artificial Neural Network (ANN) is also carried out.", notes = "IJMPC PACS numbers: 05.45.Tp, 02.30.NW Institute for Plasma Research, Near Indira Bridge, Bhat, Gandhinagar-382428, India Physical Research Laboratory, Navrangpura, Ahmedabad-380009, India", } @Article{2008Prama..71..459A, author = "Dilip P. Ahalpara and Amit Verma and Jitendra C. Parikh and Prasanta K. Panigrahi", title = "Characterizing and modelling cyclic behaviour in non-stationary time series through multi-resolution analysis", journal = "Pramana", year = "2008", month = nov, volume = "71", pages = "459--485", publisher = "Springer India, in co-publication with Indian Academy of Sciences", keywords = "genetic algorithms, genetic programming, finance, Non-stationary time series, wavelet transform, Characterizing and modelling cyclic behaviour in non-stationary time series through multi-resolution analysis", ISSN = "0304-4289", DOI = "doi:10.1007/s12043-008-0125-x", adsurl = "http://adsabs.harvard.edu/abs/2008Prama..71..459A", adsnote = "Provided by the SAO/NASA Astrophysics Data System", abstract = "A method based on wavelet transform is developed to characterise variations at multiple scales in non-stationary time series. We consider two different financial time series, S&P CNX Nifty closing index of the National Stock Exchange (India) and Dow Jones industrial average closing values. These time series are chosen since they are known to comprise of stochastic fluctuations as well as cyclic variations at different scales. The wavelet transform isolates cyclic variations at higher scales when random fluctuations are averaged out; this corroborates correlated behaviour observed earlier in financial time series through random matrix studies. Analysis is carried out through Haar, Daubechies-4 and continuous Morlet wavelets for studying the character of fluctuations at different scales and show that cyclic variations emerge at intermediate time scales. It is found that Daubechies family of wavelets can be effectively used to capture cyclic variations since these are local in nature. To get an insight into the occurrence of cyclic variations, we then proceed to model these wavelet coefficients using genetic programming (GP) approach and using the standard embedding technique in the reconstructed phase space. It is found that the standard methods (GP as well as artificial neural networks) fail to model these variations because of poor convergence. A novel interpolation approach is developed that overcomes this difficulty. The dynamical model equations have, primarily, linear terms with additive Pade-type terms. It is seen that the emergence of cyclic variations is due to an interplay of a few important terms in the model. Very interestingly GP model captures smooth variations as well as bursty behaviour quite nicely.", notes = "(1) Institute for Plasma Research, Near Indira Bridge, Bhat, Gandhinagar, 382 428, India (2) Physical Research Laboratory, Navrangpura, Ahmedabad, 380 009, India (3) Indian Institute of Science Education and Research, Salt Lake City, Kolkata, 700 106, India", } @InProceedings{Ahalpara:2009:eurogp, author = "Dilip Ahalpara and Siddharth Arora and M Santhanam", title = "Genetic Programming Based Approach for Synchronization with Parameter Mismatches in EEG", booktitle = "Proceedings of the 12th European Conference on Genetic Programming, EuroGP 2009", year = "2009", editor = "Leonardo Vanneschi and Steven Gustafson and Alberto Moraglio and Ivanoe {De Falco} and Marc Ebner", volume = "5481", series = "LNCS", pages = "13--24", address = "Tuebingen", month = apr # " 15-17", organisation = "EvoStar", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-01180-1", DOI = "doi:10.1007/978-3-642-01181-8_2", notes = "Part of \cite{conf/eurogp/2009} EuroGP'2009 held in conjunction with EvoCOP2009, EvoBIO2009 and EvoWorkshops2009", } @InProceedings{Ahalpara:2010:gecco, author = "Dilip P. Ahalpara", title = "Improved forecasting of time series data of real system using genetic programming", booktitle = "GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation", year = "2010", editor = "Juergen Branke and Martin Pelikan and Enrique Alba and Dirk V. Arnold and Josh Bongard and Anthony Brabazon and Juergen Branke and Martin V. Butz and Jeff Clune and Myra Cohen and Kalyanmoy Deb and Andries P Engelbrecht and Natalio Krasnogor and Julian F. Miller and Michael O'Neill and Kumara Sastry and Dirk Thierens and Jano {van Hemert} and Leonardo Vanneschi and Carsten Witt", isbn13 = "978-1-4503-0072-8", pages = "977--978", keywords = "genetic algorithms, genetic programming, Poster", month = "7-11 " # jul, organisation = "SIGEVO", address = "Portland, Oregon, USA", DOI = "doi:10.1145/1830483.1830658", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "A study is made to improve short term forecasting of time series data of real system using Genetic Programming (GP) under the framework of time delayed embedding technique. GP based approach is used to make analytical model of time series data of real system using embedded vectors that help reconstruct the phase space. The map equations, involving non-linear symbolic expressions in the form of binary trees comprising of time delayed components in the immediate past, are first obtained by carrying out single-step GP fit for the training data set and usually they are found to give good fitness as well as single-step predictions. However while forecasting the time series based on multi-step predictions in the out-of-sample region in an iterative manner, these solutions often show rapid deterioration as we dynamically forward the solution in future time. With a view to improve on this limitation, it is shown that if the multi-step aspect is incorporated while making the GP fit itself, the corresponding GP solutions give multi-step predictions that are improved to a fairly good extent for around those many multi-steps as incorporated during the multi-step GP fit. Two different methods for multi-step fit are introduced, and the corresponding prediction results are presented. The modified method is shown to make better forecast for out-of-sample multi-step predictions for the time series of a real system, namely Electroencephelograph (EEG) signals.", notes = "Also known as \cite{1830658} GECCO-2010 A joint meeting of the nineteenth international conference on genetic algorithms (ICGA-2010) and the fifteenth annual genetic programming conference (GP-2010)", } @InProceedings{ahalpara:2011:EuroGP, author = "Dilip Ahalpara and Abhijit Sen", title = "A Sniffer Technique for an Efficient Deduction of Model Dynamical Equations using Genetic Programming", booktitle = "Proceedings of the 14th European Conference on Genetic Programming, EuroGP 2011", year = "2011", month = "27-29 " # apr, editor = "Sara Silva and James A. Foster and Miguel Nicolau and Mario Giacobini and Penousal Machado", series = "LNCS", volume = "6621", publisher = "Springer Verlag", address = "Turin, Italy", pages = "1--12", organisation = "EvoStar", keywords = "genetic algorithms, genetic programming, local search, hill climbing", isbn13 = "978-3-642-20406-7", DOI = "doi:10.1007/978-3-642-20407-4_1", abstract = "A novel heuristic technique that enhances the search facility of the standard genetic programming (GP) algorithm is presented. The method provides a dynamic sniffing facility to optimise the local search in the vicinity of the current best chromosomes that emerge during GP iterations. Such a hybrid approach, that combines the GP method with the sniffer technique, is found to be very effective in the solution of inverse problems where one is trying to construct model dynamical equations from either finite time series data or knowledge of an analytic solution function. As illustrative examples, some special function ordinary differential equations (ODEs) and integrable nonlinear partial differential equations (PDEs) are shown to be efficiently and exactly recovered from known solution data. The method can also be used effectively for solution of model equations (the direct problem) and as a tool for generating multiple dynamical systems that share the same solution space.", notes = "Mathematica. Order of partial or ordinary differential equation search in sequence starting with first order and increasing until satisfactory match found. Part of \cite{Silva:2011:GP} EuroGP'2011 held in conjunction with EvoCOP2011 EvoBIO2011 and EvoApplications2011", } @InProceedings{ahalpara:2007:EMBN, author = "Dilip P. Ahalpara and Prasanta K. Panigrahi and Jitendra C. Parikh", title = "Variations in Financial Time Series: Modelling Through Wavelets and Genetic Programming", booktitle = "Econophysics of Markets and Business Networks", year = "2007", publisher = "Springer", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/chapter/10.1007/978-88-470-0665-2_3", DOI = "doi:10.1007/978-88-470-0665-2_3", } @Article{Ahangar-Asr:2011:EC, author = "Alireza Ahangar-Asr and Asaad Faramarzi and Akbar A. Javadi and Orazio Giustolisi", title = "Modelling mechanical behaviour of rubber concrete using evolutionary polynomial regression", journal = "Engineering Computation", year = "2011", volume = "28", number = "4", pages = "492--507", keywords = "genetic algorithms, genetic programming, Mechanical \& Materials Engineering, Concretes, Mechanical behaviour of materials, Rubbers", ISSN = "0264-4401", DOI = "doi:10.1108/02644401111131902", publisher = "Emerald Group Publishing Limited", abstract = "Using discarded tyre rubber as concrete aggregate is an effective solution to the environmental problems associated with disposal of this waste material. However, adding rubber as aggregate in concrete mixture changes, the mechanical properties of concrete, depending mainly on the type and amount of rubber used. An appropriate model is required to describe the behaviour of rubber concrete in engineering applications. The purpose of this paper is to show how a new evolutionary data mining technique, evolutionary polynomial regression (EPR), is used to predict the mechanical properties of rubber concrete. Design/methodology/approach EPR is a data-driven method based on evolutionary computing, aimed to search for polynomial structures representing a system. In this technique, a combination of the genetic algorithm and the least square method is used to find feasible structures and the appropriate constants for those structures. Findings Data from 70 cases of experiments on rubber concrete are used for development and validation of the EPR models. Three models are developed relating compressive strength, splitting tensile strength, and elastic modulus to a number of physical parameters that are known to contribute to the mechanical behaviour of rubber concrete. The most outstanding characteristic of the proposed technique is that it provides a transparent, structured, and accurate representation of the behaviour of the material in the form of a polynomial function, giving insight to the user about the contributions of different parameters involved. The proposed model shows excellent agreement with experimental results, and provides an efficient method for estimation of mechanical properties of rubber concrete. Originality/value In this paper, a new evolutionary data mining approach is presented for the analysis of mechanical behaviour of rubber concrete. The new approach overcomes the shortcomings of the traditional and artificial neural network-based methods presented in the literature for the analysis of slopes. EPR provides a viable tool to find a structured representation of the system, which allows the user to gain additional information on how the system performs.", notes = "Research paper. Computational Geomechanics Group, College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, UK Civil and Environmental Engineering Department, Faculty of Engineering, Technical University of Bari, Taranto, Italy", } @PhdThesis{Ahangar-Asr:thesis, author = "Alireza AhangarAsr", title = "Application of an Evolutionary Data Mining Technique for Constitutive Modelling of Geomaterials", school = "University of Exeter", year = "2012", address = "UK", month = "31 " # dec, keywords = "genetic algorithms, genetic programming", URL = "http://hdl.handle.net/10871/9925", URL = "https://ore.exeter.ac.uk/repository/bitstream/handle/10871/9925/AhangarasrA.pdf", size = "214 pages", abstract = "Modelling behaviour of materials involves approximating the actual behaviour with that of an idealised material that deforms in accordance with some constitutive relationships. Several constitutive models have been developed for various materials many of which involve determination of material parameters with no physical meaning. ANN is a computer-based modelling technique for computation and knowledge representation inspired by the neural architecture and operation of the human brain. It has been shown by various researchers that ANNs offer outstanding advantages in constitutive modelling of material; however, these networks have some shortcoming. In this thesis, the Evolutionary Polynomial Regression (EPR) was introduced as an alternative approach to constitutive modelling of the complex behaviour of saturated and unsaturated soils and also modelling of a number of other civil and geotechnical engineering materials and systems. EPR overcomes the shortcomings of ANN by providing a structured and transparent model representing the behaviour of the system. In this research EPR is applied to modelling of stress-strain and volume change behaviour of unsaturated soils, modelling of SWCC in unsaturated soils, hydro-thermo-mechanical modelling of unsaturated soils, identification of coupling parameters between shear strength behaviour and chemical's effects in compacted soils, modelling of permeability and compaction characteristics of soils, prediction of the stability status of soil and rock slopes and modelling the mechanical behaviour of rubber concrete. Comparisons between EPR-based material model predictions, the experimental data and the predictions from other data mining and regression modelling techniques and also the results of the parametric studies revealed the exceptional capabilities of the proposed methodology in modelling the very complicated behaviour of geotechnical and civil engineering materials.", notes = "Ahangar-Asr Supervisor: Akbar Javadi 2nd supervisor: Slobodan Djordjevic", } @Article{DBLP:journals/ewc/AhangarAsrJJ23, author = "Alireza Ahangar-Asr and A. Johari and Akbar A. Javadi", title = "An evolutionary-based polynomial regression modeling approach to predicting discharge flow rate under sheet piles", journal = "Engineering with Computers", year = "2023", volume = "39", number = "6", pages = "4093--4101", keywords = "genetic algorithms, genetic programming, EPR, Sheet piles/cut-off walls, Seepage flow rate, Evolutionary computation, Data mining", timestamp = "Sat, 08 Jun 2024 13:15:18 +0200", biburl = "https://dblp.org/rec/journals/ewc/AhangarAsrJJ23.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://rdcu.be/dPatP", DOI = "doi:10.1007/S00366-023-01872-1", size = "9 pages", notes = "Contrast EPR and GP?", } @InProceedings{Aher:2012:ICSP, author = "R. P. Aher and K. C. Jodhanle", booktitle = "Signal Processing (ICSP), 2012 IEEE 11th International Conference on", title = "Removal of Mixed Impulse noise and Gaussian noise using genetic programming", year = "2012", volume = "1", pages = "613--618", abstract = "In this paper, we have put forward a nonlinear filtering method for removing mixed Impulse and Gaussian noise, based on the two step switching scheme. The switching scheme uses two cascaded detectors for detecting the noise and two corresponding estimators which effectively and efficiently filters the noise from the image. A supervised learning algorithm, Genetic programming, is employed for building the two detectors with complementary characteristics. Most of the noisy pixels are identified by the first detector. The remaining noises are searched by the second detector, which is usually hidden in image details or with amplitudes close to its local neighbourhood. Both the detectors designed are based on the robust estimators of location and scale i.e. Median and Median Absolute Deviation (MAD). Unlike many filters which are specialised only for a particular noise model, the proposed filters in this paper are capable of effectively suppressing all kinds of Impulse and Gaussian noise. The proposed two-step Genetic Programming filters removes impulse and Gaussian noise very efficiently, and also preserves the image details.", keywords = "genetic algorithms, genetic programming, Gaussian noise, image denoising, impulse noise, learning (artificial intelligence), nonlinear filters, Gaussian noise, Median Absolute Deviation, cascaded detectors, complementary characteristics, image details, impulse noise, local neighbourhood, noisy pixels, nonlinear filtering method, second detector, supervised learning algorithm, two step switching scheme, alpha trimmed mean estimator, CWM, Gaussian Noise, Impulse noise, Median, Median Absolute Deviation (MAD), Non-Linear filters, Supervised Learning, Switching scheme", DOI = "doi:10.1109/ICoSP.2012.6491563", ISSN = "2164-5221", notes = "Also known as \cite{6491563}", } @InProceedings{Ahlgren:2020:GI, author = "John Ahlgren and Maria Eugenia Berezin and Kinga Bojarczuk and Elena Dulskyte and Inna Dvortsova and Johann George and Natalija Gucevska and Mark Harman and Ralf Laemmel and Erik Meijer and Silvia Sapora and Justin Spahr-Summers", title = "{WES}: Agent-based User Interaction Simulation on Real Infrastructure", booktitle = "GI @ ICSE 2020", year = "2020", month = "3 " # jul, editor = "Shin Yoo and Justyna Petke and Westley Weimer and Bobby R. Bruce", publisher = "ACM", address = "internet", pages = "276--284", note = "Invited Keynote", keywords = "genetic algorithms, genetic programming, genetic improvement, SBSE, social testing, APR, Connectivity, Data Science, Facebook AI Research, Human Computer Interaction, UX Human, Machine Learning", isbn13 = "978-1-4503-7963-2", URL = "https://research.fb.com/wp-content/uploads/2020/04/WES-Agent-based-User-Interaction-Simulation-on-Real-Infrastructure.pdf", URL = "https://research.fb.com/publications/wes-agent-based-user-interaction-simulation-on-real-infrastructure/", video_url = "https://youtu.be/GsNKCifm44A", DOI = "doi:10.1145/3387940.3392089", size = "9 pages", abstract = "We introduce the Web-Enabled Simulation (WES) research agenda, and describe FACEBOOK WW system. We describe the application of WW to reliability, integrity and privacy at FACEBOOK, where it is used to simulate social media interactions on an infrastructure consisting of hundreds of millions of lines of code. The WES agenda draws on research from many areas of study, including Search Based Software Engineering, Machine Learning, Programming Languages, Multi Agent Systems, Graph Theory, Game AI, and AI Assisted Game Play. We conclude with a set of open problems and research challenges to motivate wider investigation.", notes = "London probable . The WES agenda draws on research from many areas of study, including (but not limited to) Search Based Software Engineering, Machine Learning, Programming Languages, Multi Agent Systems, Graph Theory, Game AI, AI Assisted Game Play. Intelligent learning/trainable Bots interact with The social graph. A/B testing. Automated Mechanism Design. Social bugs/social testing. scammer bot. Super-human bots. Big changes in machine learning classification performance, data pipeline line breakages. WES Test Oracle uses machine learning. Co-evolutionary Mechanism Learning. virtual speed humps to hinter anti-social behaviour. Video: https://youtu.be/GsNKCifm44A (13--55 minutes from start, followed by discussion, end 1:13:00) http://geneticimprovementofsoftware.com/gi2020icse.html FACEBOOK Inc", } @InProceedings{Ahlgren:2021:ICSE, author = "John Ahlgren and Maria Eugenia Berezin and Kinga Bojarczuk and Elena Dulskyte and Inna Dvortsova and Johann George and Natalija Gucevska and Mark Harman and Maria Lomeli and Erik Meijer and Silvia Sapora and Justin Spahr-Summers", title = "Testing Web Enabled Simulation at Scale Using Metamorphic Testing", booktitle = "Proceedings of the International Conference on Software Engineering, ICSE 2021", year = "2021", editor = "Arie {van Deursen} and Tao Xie and Natalia Juristo Oscar Dieste", pages = "140--149", month = "25-28 " # may, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Genetic Improvement, SBSE, Metamorphic Testing, Oracle Problem, Scalability, Testing, Test Flakiness, Web-Enabled Simulation", URL = "https://research.fb.com/publications/testing-web-enabled-simulation-at-scale-using-metamorphic-testing/", URL = "https://research.fb.com/wp-content/uploads/2021/03/Testing-Web-Enabled-Simulation-at-Scale-Using-Metamorphic-Testing.pdf", video_url = "https://www.youtube.com/watch?v=pNKqyn-90Ig", DOI = "doi:10.1109/ICSE-SEIP52600.2021.00023", size = "10 pages", abstract = "We report on Facebook deployment of MIA (Metamorphic Interaction Automaton). MIA is used to test Facebook's Web Enabled Simulation, built on a web infrastructure of hundreds of millions of lines of code. MIA tackles the twin problems of test flakiness and the unknowable oracle problem. It uses metamorphic testing to automate continuous integration and regression test execution. MIA also plays the role of a test bot, automatically commenting on all relevant changes submitted for code review. It currently uses a suite of over 40 metamorphic test cases. Even at this extreme scale, a non-trivial metamorphic test suite subset yields outcomes within 20 minutes (sufficient for continuous integration and review processes). Furthermore, our offline mode simulation reduces test flakiness from approximately 50percent (of all online tests) to 0percent (offline). Metamorphic testing has been widely-studied for 22 years. This paper is the first reported deployment into an industrial continuous integration system.", } @InProceedings{DBLP:conf/ease/AhlgrenBDDGGHLL21, author = "John Ahlgren and Kinga Bojarczuk and Sophia Drossopoulou and Inna Dvortsova and Johann George and Natalija Gucevska and Mark Harman and Maria Lomeli and Simon M. Lucas and Erik Meijer and Steve Omohundro and Rubmary Rojas and Silvia Sapora and Norm Zhou", title = "Facebook's Cyber-Cyber and Cyber-Physical Digital Twins", booktitle = "EASE 2021: Evaluation and Assessment in Software Engineering", year = "2021", editor = "Ruzanna Chitchyan and Jingyue Li and Barbara Weber and Tao Yue", address = "Trondheim, Norway", month = jun # " 21-24", publisher = "ACM", keywords = "genetic algorithms, genetic programming, genetic improvement, SBSE, Web Enabled Simulation, Digital Twin, facebook, meta, social media, online, software engineering", timestamp = "Mon, 21 Jun 2021 12:29:10 +0200", biburl = "https://dblp.org/rec/conf/ease/AhlgrenBDDGGHLL21.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://research.facebook.com/publications/facebooks-cyber-cyber-and-cyber-physical-digital-twins/", URL = "https://discovery.ucl.ac.uk/id/eprint/10139789/1/EASE21.pdf", URL = "https://doi.org/10.1145/3463274.3463275", DOI = "doi:10.1145/3463274.3463275", size = "9 pages", abstract = "A cyber/cyber digital twin is a simulation of a software system. By contrast, a cyber-physical digital twin is a simulation of a non-software (physical) system. Although cyberphysical digital twins have received a lot of recent attention, their cyber--cyber counterparts have been comparatively overlooked. In this paper we show how the unique properties of cyber cyber digital twins open up exciting opportunities for research and development. Like all digital twins, the cyber--cyber digital twin is both informed by and informs the behaviour of the twin it simulates. It is therefore a software system that simulates another software system, making it conceptually truly a twin, blurring the distinction between the simulated and the simulator. Cyber-cyber digital twins can be twins of other cyber--cyber digital twins, leading to a hierarchy of twins. As we shall see, these apparently philosophical observations have practical ramifications for the design, implementation and deployment of digital twins at Meta.", } @Unpublished{ahlschwede:2000:ugppm, author = "John Ahlschwede", title = "Using Genetic Programming to Play Mancala", year = "2000", note = "http://www.corngolem.com/john/gp/index.html", keywords = "genetic algorithms, genetic programming", abstract = "This paper will explain what genetic programming is, what mancala is, how I used genetic programming to evolve mancala-playing programs, and the results I got from doing so.", } @InProceedings{ahluwalia:1996:ccpGP, author = "Manu Ahluwalia and Terence C. Fogarty", title = "Co-Evolving Hierarchical Programs Using Genetic Programming", booktitle = "Genetic Programming 1996: Proceedings of the First Annual Conference", editor = "John R. Koza and David E. Goldberg and David B. Fogel and Rick L. Riolo", year = "1996", month = "28--31 " # jul, keywords = "genetic algorithms, genetic programming", pages = "419", address = "Stanford University, CA, USA", publisher = "MIT Press", size = "1 page", URL = "http://cognet.mit.edu/sites/default/files/books/9780262315876/pdfs/9780262315876_chap58.pdf", URL = "http://cognet.mit.edu/library/books/view?isbn=0262611279", notes = "GP-96", } @InProceedings{Ahluwalia:1997:, author = "Manu Ahluwalia and Larry Bull and Terence C. Fogarty", title = "Co-evolving Functions in Genetic Programming: A Comparison in ADF Selection Strategies", booktitle = "Genetic Programming 1997: Proceedings of the Second Annual Conference", editor = "John R. Koza and Kalyanmoy Deb and Marco Dorigo and David B. Fogel and Max Garzon and Hitoshi Iba and Rick L. Riolo", year = "1997", month = "13-16 " # jul, keywords = "genetic algorithms, genetic programming", pages = "3--8", address = "Stanford University, CA, USA", publisher_address = "San Francisco, CA, USA", publisher = "Morgan Kaufmann", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/gp1997/Ahluwalia_1997_.pdf", size = "6 pages", notes = "GP-97", } @InProceedings{ahluwalia:1997:cfGPea, author = "Manu Ahluwalia and Larry Bull and Terence C. Fogarty", title = "Co-evolving Functions in Genetic Programming: An Emergent Approach using ADFs and GLiB", booktitle = "Late Breaking Papers at the 1997 Genetic Programming Conference", year = "1997", editor = "John R. Koza", pages = "1--6", address = "Stanford University, CA, USA", publisher_address = "Stanford University, Stanford, California, 94305-3079, USA", month = "13--16 " # jul, publisher = "Stanford Bookstore", keywords = "genetic algorithms, genetic programming", ISBN = "0-18-206995-8", notes = "GP-97LB The email address for the bookstore for mail orders is mailorder@bookstore.stanford.edu Phone no 415-329-1217 or 800-533-2670", } @InProceedings{ahluwalia:1998:cfGP:ADF+GLiB, author = "M. Ahluwalia and L. Bull", title = "Co-evolving Functions in Genetic Programming: Dynamic ADF Creation using GLiB", booktitle = "Evolutionary Programming VII: Proceedings of the Seventh Annual Conference on Evolutionary Programming", year = "1998", editor = "V. William Porto and N. Saravanan and D. Waagen and A. E. Eiben", volume = "1447", series = "LNCS", pages = "809--818", address = "Mission Valley Marriott, San Diego, California, USA", publisher_address = "Berlin", month = "25-27 " # mar, publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-64891-7", DOI = "doi:10.1007/BFb0040753", notes = "EP-98. University of the West of England, UK", } @InProceedings{ahluwalia:1999:AGPCS, author = "Manu Ahluwalia and Larry Bull", title = "A Genetic Programming-based Classifier System", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "11--18", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms, genetic programming, classifier systems", ISBN = "1-55860-611-4", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/gecco1999/ahluwalia_1999_agpcs.pdf", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InProceedings{ahluwalia:1999:CFGPCK, author = "Manu Ahluwalia and Larry Bull", title = "Coevolving Functions in Genetic Programming: Classification using K-nearest-neighbour", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "2", pages = "947--952", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms, genetic programming", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GP-413.ps", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/GP-413.pdf", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @PhdThesis{Ahluwalia:thesis, author = "Manu Ahluwalia", title = "Co-evolving functions in genetic programming", school = "University of the West of England at Bristol", year = "2000", address = "UK", keywords = "genetic algorithms, genetic programming", URL = "http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.322427", notes = "uk.bl.ethos.322427", } @Article{Ahluwalia:2001:SA, author = "Manu Ahluwalia and Larry Bull", title = "Coevolving functions in genetic programming", journal = "Journal of Systems Architecture", volume = "47", pages = "573--585", year = "2001", number = "7", month = jul, keywords = "genetic algorithms, genetic programming, ADF, Classification, EDF, Feature selection/extraction, Hierarchical programs, Knn, Speciation", ISSN = "1383-7621", URL = "https://uwe-repository.worktribe.com/output/1090581", URL = "http://www.sciencedirect.com/science/article/B6V1F-43RV156-3/1/16dd3ab5502922479ef7bb1ca4f7b9c3", DOI = "doi:10.1016/S1383-7621(01)00016-9", size = "13 pages", abstract = "In this paper we introduce a new approach to the use of automatically defined functions (ADFs) within genetic programming. The technique consists of evolving a number of separate sub-populations of functions which can be used by a population of evolving main programs. We present and refine a set of mechanisms by which the number and constitution of the function sub-populations can be defined and compare their performance on two well-known classification tasks. A final version of the general approach, for use explicitly on classification tasks, is then presented. It is shown that in all cases the coevolutionary approach performs better than traditional genetic programming with and without ADFs.", } @InProceedings{Ahmad:2012:GECCO, author = "Arbab Masood Ahmad and Gul Muhammad Khan and Sahibzada Ali Mahmud and Julian Francis Miller", title = "Breast cancer detection using cartesian genetic programming evolved artificial neural networks", booktitle = "GECCO '12: Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference", year = "2012", editor = "Terry Soule and Anne Auger and Jason Moore and David Pelta and Christine Solnon and Mike Preuss and Alan Dorin and Yew-Soon Ong and Christian Blum and Dario Landa Silva and Frank Neumann and Tina Yu and Aniko Ekart and Will Browne and Tim Kovacs and Man-Leung Wong and Clara Pizzuti and Jon Rowe and Tobias Friedrich and Giovanni Squillero and Nicolas Bredeche and Stephen L. Smith and Alison Motsinger-Reif and Jose Lozano and Martin Pelikan and Silja Meyer-Nienberg and Christian Igel and Greg Hornby and Rene Doursat and Steve Gustafson and Gustavo Olague and Shin Yoo and John Clark and Gabriela Ochoa and Gisele Pappa and Fernando Lobo and Daniel Tauritz and Jurgen Branke and Kalyanmoy Deb", isbn13 = "978-1-4503-1177-9", pages = "1031--1038", keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, real world applications, Algorithms, Design, Performance, Breast Cancer, Fine Needle Aspiration, FNA, ANN, Artificial Neural Network, Neuro-evolution", month = "7-11 " # jul, organisation = "SIGEVO", address = "Philadelphia, Pennsylvania, USA", DOI = "doi:10.1145/2330163.2330307", publisher = "ACM", publisher_address = "New York, NY, USA", size = "8 pages", abstract = "A fast learning neuro-evolutionary technique that evolves Artificial Neural Networks using Cartesian Genetic Programming (CGPANN) is used to detect the presence of breast cancer. Features from breast mass are extracted using fine needle aspiration (FNA) and are applied to the CGPANN for diagnosis of breast cancer. FNA data is obtained from the Wisconsin Diagnostic Breast Cancer website and is used for training and testing the network. The developed system produces fast and accurate results when compared to contemporary work done in the field. The error of the model comes out to be as low as 1percent for Type-I (classifying benign sample falsely as malignant) and 0.5percent for Type-II (classifying malignant sample falsely as benign).", notes = "Also known as \cite{2330307} GECCO-2012 A joint meeting of the twenty first international conference on genetic algorithms (ICGA-2012) and the seventeenth annual genetic programming conference (GP-2012)", } @InProceedings{Ahmad:2012:FIT, author = "Arbab Masood Ahmad and Gul Muhammad Khan", booktitle = "Frontiers of Information Technology (FIT), 2012 10th International Conference on", title = "Bio-signal Processing Using Cartesian Genetic Programming Evolved Artificial Neural Network (CGPANN)", year = "2012", pages = "261--268", DOI = "doi:10.1109/FIT.2012.54", abstract = "The aim of this paper is to explore the application of Neuro-Evolutionary Techniques to the diagnosis of various diseases. We applied the evolutionary technique of Cartesian Genetic programming Evolved Artificial Neural Network (CG-PANN) for the detection of three important diseases. Some cases showed excellent results while others are in the process of experimentation. In the first case we worked on diagnosing the extent of Parkinson's disease using a computer based test. Experiments in this case are in progress. In the second case, we applied the Fine Needle Aspirate (FNA) data for Breast Cancer from the WDBC website to our network to classify the samples as either benign (non-cancerous) or malignant (cancerous). The results from these experiments were highly satisfactory. In the third case, we developed a modified form of Pan-Tompkins's algorithm to detect the fiducial points from ECG signals and extracted key features from them. The features shall be applied to our network to classify the signals for the different types of Arrhythmias. Experimentation is still in progress.", keywords = "genetic algorithms, genetic programming, cardiology, diseases, electrocardiography, feature extraction, medical signal processing, neural nets, signal classification, CG-PANN, Cartesian genetic programming evolved artificial neural network, ECG signal, FNA data, Pan-Tompkins algorithm, Parkinson disease, arrhythmia, benign cancer, bio-signal processing, breast cancer, electrocardiography, experimentation process, feature extraction, fiducial point, fine needle aspirate, malignant cancer, neuro-evolutionary technique, Artificial neural networks, Cancer, Diseases, Electrocardiography, Feature extraction, Training, Breast Cancer detection, CGPANN, Cardiac Arrhythmias, FNA, Parkinson's Disease", notes = "Also known as \cite{6424333}", } @InProceedings{conf/eann/AhmadKM13, author = "Arbab Masood Ahmad and Gul Muhammad Khan and Sahibzada Ali Mahmud", title = "Classification of Arrhythmia Types Using Cartesian Genetic Programming Evolved Artificial Neural Networks", editor = "Lazaros S. Iliadis and Harris Papadopoulos and Chrisina Jayne", booktitle = "Proceedings of 14th International Conference on Engineering Applications of Neural Networks (EANN 2013), Part {I}", year = "2013", volume = "383", series = "Communications in Computer and Information Science", pages = "282--291", address = "Halkidiki, Greece", month = sep # " 13-16", publisher = "Springer", keywords = "genetic algorithms, genetic programming, cartesian genetic programming, CGPANN, artificial neural network, neuro-evolution, CVD, cardiac arrhythmias, classification, fiducial points, LBBB beats, RBBB beats", isbn13 = "978-3-642-41012-3", bibdate = "2014-01-25", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/eann/eann2013-1.html#AhmadKM13", URL = "http://dx.doi.org/10.1007/978-3-642-41013-0", DOI = "doi:10.1007/978-3-642-41013-0_29", abstract = "Cartesian Genetic programming Evolved Artificial Neural Network (CGPANN) is explored for classification of different types of arrhythmia and presented in this paper. Electrocardiography (ECG) signal is preprocessed to acquire important parameters and then presented to the classifier. The parameters are calculated from the location and amplitudes of ECG fiducial points, determined with a new algorithm inspired by Pan-Tompkins's algorithm [14]. The classification results are satisfactory and better than contemporary methods introduced in the field.", } @InProceedings{conf/ifip12/AhmadKM14, author = "Arbab Masood Ahmad and Gul Muhammad Khan and Sahibzada Ali Mahmud", title = "Classification of Mammograms Using Cartesian Genetic Programming Evolved Artificial Neural Networks", booktitle = "Proceedings 10th IFIP WG 12.5 International Conference Artificial Intelligence Applications and Innovations, AIAI 2014", year = "2014", editor = "Lazaros S. Iliadis and Ilias Maglogiannis and Harris Papadopoulos", volume = "436", series = "IFIP Advances in Information and Communication Technology", pages = "203--213", address = "Rhodes, Greece, September 19-21, 2014", publisher = "Springer", keywords = "genetic algorithms, genetic programming, cartesian genetic programming, mammogram image classification, GLCM, CGPANN, haralick's parameters", isbn13 = "978-3-662-44654-6", DOI = "doi:10.1007/978-3-662-44654-6_20", URL = "http://dx.doi.org/10.1007/978-3-662-44654-6_20", bibdate = "2014-09-15", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/ifip12/aiai2014.html#AhmadKM14", URL = "http://dx.doi.org/10.1007/978-3-662-44654-6", abstract = "We developed a system that classifies masses or microcalcifications observed in a mammogram as either benign or malignant. The system assumes prior manual segmentation of the image. The image segment is then processed for its statistical parameters and applied to a computational intelligence system for classification. We used Cartesian Genetic Programming Evolved Artificial Neural Network (CGPANN) for classification. To train and test our system we selected 2000 mammogram images with equal number of benign and malignant cases from the well-known Digital Database for Screening Mammography (DDSM). To find the input parameters for our network we exploited the overlay files associated with the mammograms. These files mark the boundaries of masses or microcalcifications. A Gray Level Co-occurrence matrix (GLCM) was developed for a rectangular region enclosing each boundary and its statistical parameters computed. Five experiments were conducted in each fold of a 10-fold cross validation strategy. Testing accuracy of 100 percent was achieved in some experiments.", } @InProceedings{Ahmad:2018:GECCOcomp, author = "Hammad Ahmad and Thomas Helmuth", title = "A comparison of semantic-based initialization methods for genetic programming", booktitle = "GECCO '18: Proceedings of the Genetic and Evolutionary Computation Conference Companion", year = "2018", editor = "Carlos Cotta and Tapabrata Ray and Hisao Ishibuchi and Shigeru Obayashi and Bogdan Filipic and Thomas Bartz-Beielstein and Grant Dick and Masaharu Munetomo and Silvino {Fernandez Alzueta} and Thomas Stuetzle and Pablo Valledor Pellicer and Manuel Lopez-Ibanez and Daniel R. Tauritz and Pietro S. Oliveto and Thomas Weise and Borys Wrobel and Ales Zamuda and Anne Auger and Julien Bect and Dimo Brockhoff and Nikolaus Hansen and Rodolphe {Le Riche} and Victor Picheny and Bilel Derbel and Ke Li and Hui Li and Xiaodong Li and Saul Zapotecas and Qingfu Zhang and Stephane Doncieux and Richard Duro and Joshua Auerbach and Harold {de Vladar} and Antonio J. Fernandez-Leiva and JJ Merelo and Pedro A. Castillo-Valdivieso and David Camacho-Fernandez and Francisco {Chavez de la O} and Ozgur Akman and Khulood Alyahya and Juergen Branke and Kevin Doherty and Jonathan Fieldsend and Giuseppe Carlo Marano and Nikos D. Lagaros and Koichi Nakayama and Chika Oshima and Stefan Wagner and Michael Affenzeller and Boris Naujoks and Vanessa Volz and Tea Tusar and Pascal Kerschke and Riyad Alshammari and Tokunbo Makanju and Brad Alexander and Saemundur O. Haraldsson and Markus Wagner and John R. Woodward and Shin Yoo and John McCall and Nayat Sanchez-Pi and Luis Marti and Danilo Vasconcellos and Masaya Nakata and Anthony Stein and Nadarajen Veerapen and Arnaud Liefooghe and Sebastien Verel and Gabriela Ochoa and Stephen L. Smith and Stefano Cagnoni and Robert M. Patton and William {La Cava} and Randal Olson and Patryk Orzechowski and Ryan Urbanowicz and Ivanoe {De Falco} and Antonio {Della Cioppa} and Ernesto Tarantino and Umberto Scafuri and P. G. M. Baltus and Giovanni Iacca and Ahmed Hallawa and Anil Yaman and Alma Rahat and Handing Wang and Yaochu Jin and David Walker and Richard Everson and Akira Oyama and Koji Shimoyama and Hemant Kumar and Kazuhisa Chiba and Pramudita Satria Palar", isbn13 = "978-1-4503-5764-7", pages = "1878--1881", address = "Kyoto, Japan", DOI = "doi:10.1145/3205651.3208218", publisher = "ACM", publisher_address = "New York, NY, USA", month = "15-19 " # jul, organisation = "SIGEVO", keywords = "genetic algorithms, genetic programming", abstract = "During the initialization step, a genetic programming (GP) system traditionally creates a population of completely random programs to populate the initial population. These programs almost always perform poorly in terms of their total error---some might not even output the correct data type. In this paper, we present new methods for initialization that attempt to generate programs that are somewhat relevant to the problem being solved and/or increase the initial diversity (both error and behavioural diversity) of the population prior to the GP run. By seeding the population---and thereby eliminating worthless programs and increasing the initial diversity of the population---we hope to improve the performance of the GP system. Here, we present two novel techniques for initialization (Lexicase Seeding and Pareto Seeding) and compare them to a previous method (Enforced Diverse Populations) and traditional, non-seeded initialization. Surprisingly, we found that none of the initialization m", notes = "Also known as \cite{3208218} GECCO-2018 A Recombination of the 27th International Conference on Genetic Algorithms (ICGA-2018) and the 23rd Annual Genetic Programming Conference (GP-2018)", } @InProceedings{DBLP:conf/asplos/Ahmad0W22, author = "Hammad Ahmad and Yu Huang and Westley Weimer", title = "{CirFix}: automatically repairing defects in hardware design code", booktitle = "ASPLOS 2022: 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems", year = "2022", editor = "Babak Falsafi and Michael Ferdman and Shan Lu and Thomas F. Wenisch", pages = "990--1003", address = "Lausanne, Switzerland", month = "28 " # feb # "- 4 " # mar, publisher = "ACM", keywords = "genetic algorithms, genetic programming, genetic improvement, automated program repair, APR, hardware designs, HDL benchmark", timestamp = "Wed, 02 Mar 2022 18:22:59 +0100", biburl = "https://dblp.org/rec/conf/asplos/Ahmad0W22.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://doi.org/10.1145/3503222.3507763", DOI = "doi:10.1145/3503222.3507763", code_url = "https://github.com/hammad-a/verilog_repair", size = "14 pages", abstract = "CirFix, is a framework for automatically repairing defects in hardware designs implemented in languages like Verilog. We propose a novel fault localization approach based on assignments to wires and registers, and a fitness function tailored to the hardware domain to bridge the gap between software-level automated program repair and hardware descriptions. We also present a benchmark suite of 32 defect scenarios corresponding to a variety of hardware projects. Overall, CirFix produces plausible repairs for 21/32 and correct repairs for 16/32 of the defect scenarios. This repair rate is comparable to that of successful program repair approaches for software, indicating CirFix is effective at bringing over the benefits of automated program repair to the hardware domain for the first time.", } @InProceedings{DBLP:conf/ppsn/AhmadCFW22, author = "Hammad Ahmad and Padraic Cashin and Stephanie Forrest and Westley Weimer", title = "Digging into Semantics: Where Do Search-Based Software Repair Methods Search?", booktitle = "Parallel Problem Solving from Nature - PPSN XVII - 17th International Conference, PPSN 2022, Proceedings, Part II", year = "2022", editor = "Guenter Rudolph and Anna V. Kononova and Hernan E. Aguirre and Pascal Kerschke and Gabriela Ochoa and Tea Tusar", volume = "13399", series = "Lecture Notes in Computer Science", pages = "3--18", address = "Dortmund, Germany", month = sep # " 10-14", publisher = "Springer", keywords = "genetic algorithms, genetic programming, genetic improvement, APR, SBSE, Semantic search spaces, Program repair, Patch diversity, Daikon, Defects4J", timestamp = "Tue, 16 Aug 2022 16:15:42 +0200", biburl = "https://dblp.org/rec/conf/ppsn/AhmadCFW22.bib", bibsource = "dblp computer science bibliography, https://dblp.org", isbn13 = "978-3-031-14720-3", URL = "https://web.eecs.umich.edu/~weimerw/p/weimer-asplos2022.pdf", DOI = "doi:10.1007/978-3-031-14721-0_1", abstract = "Search-based methods are a popular approach for automatically repairing software bugs, a field known as automated program repair (APR). There is increasing interest in empirical evaluation and comparison of different APR methods, typically measured as the rate of successful repairs on benchmark sets of buggy programs. Such evaluations, however, fail to explain why some approaches succeed and others fail. Because these methods typically use syntactic representations, i.e., source code, we know little about how the different methods explore their semantic spaces, which is relevant for assessing repair quality and understanding search dynamics. We propose an automated method based on program semantics, which provides quantitative and qualitative information about different APR search-based techniques. Our approach requires no manual annotation and produces both mathematical and human-understandable insights. In an empirical evaluation of 4 APR tools and 34 defects, we investigate the relationship between search-space exploration, semantic diversity and repair success, examining both the overall picture and how the tools search unfolds. Our results suggest that population diversity alone is not sufficient for finding repairs, and that searching in the right place is more important than searching broadly, highlighting future directions for the research community.", notes = "Semantic distance between code mutants estimated by comparing their invariant sets using Canberra distance. 2D visualisation. CapGem, GenProg, SimFix, TBar. Java. p12 four to twenty times more syntactic variability than (useful?) semantic variation. (ie Java syntax-to-semantics is many-to-one mapping.) PPSN2022", } @Article{Ahmad:2000:CCGc, author = "Ishfaq Ahmad", title = "Genetic Programming In Clusters", journal = "IEEE Concurrency", volume = "8", number = "3", pages = "10--11, 13", month = jul # "\slash " # sep, year = "2000", CODEN = "IECMFX", ISSN = "1092-3063", bibdate = "Tue Jan 16 11:59:57 2001", keywords = "genetic algorithms, genetic programming", ISSN = "1092-3063", publisher = "IEEE Computer Society", address = "Los Alamitos, CA, USA", URL = "http://csdl.computer.org/comp/mags/pd/2000/03/p3toc.htm", acknowledgement = ack-nhfb, DOI = "doi:10.1109/MCC.2000.10016", } @InProceedings{conf/sac/AhmadRRJ19, author = "Qadeer Ahmad and Atif Rafiq and Muhammad Adil Raja and Noman Javed", title = "Evolving {MIMO} multi-layered artificial neural networks using grammatical evolution", booktitle = "Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, SAC 2019", publisher = "ACM", year = "2019", editor = "Chih-Cheng Hung and George A. Papadopoulos", pages = "1278--1285", address = "Limassol, Cyprus", month = apr # " 8-12", keywords = "genetic algorithms, genetic programming, grammatical evolution, ANN", isbn13 = "978-1-4503-5933-7", DOI = "doi:10.1145/3297280.3297408", bibdate = "2019-05-02", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/sac/sac2019.html#AhmadRRJ19", } @Article{Ahmadi:2021:AWM, author = "Farshad Ahmadi and Saeid Mehdizadeh and Babak Mohammadi and Quoc Bao Pham and Thi Ngoc Canh Doan and Ngoc Duong Vo", title = "Application of an artificial intelligence technique enhanced with intelligent water drops for monthly reference evapotranspiration estimation", journal = "Agricultural Water Management", year = "2021", volume = "244", pages = "106622", keywords = "genetic algorithms, genetic programming, gene expression programming, empirical models, intelligent water drops, reference evapotranspiration, support vector regression", ISSN = "0378-3774", bibsource = "OAI-PMH server at oai.repec.org", oai = "oai:RePEc:eee:agiwat:v:244:y:2021:i:c:s0378377420321697", URL = "https://www.sciencedirect.com/science/article/pii/S0378377420321697", DOI = "doi:10.1016/j.agwat.2020.106622", abstract = "Reference evapotranspiration (ET0) is one of the most important parameters, which is required in many fields such as hydrological, agricultural, and climatological studies. Therefore, its estimation via reliable and accurate techniques is a necessity. The present study aims to estimate the monthly ET0 time series of six stations located in Iran. To achieve this objective, gene expression programming (GEP) and support vector regression (SVR) were used as standalone models. A novel hybrid model was then introduced through coupling the classical SVR with an optimisation algorithm, namely intelligent water drops (IWD) (i.e., SVR{$-$}IWD). Two various types of scenarios were considered, including the climatic data- and antecedent ET0 data-based patterns. In the climatic data-based models, the effective climatic parameters were recognised by using two pre-processing techniques consisting of {$\tau$} Kendall and entropy. It is worthy to mention that developing the hybrid SVR-IWD model as well as using the {$\tau$} Kendall and entropy approaches to discern the most influential weather parameters on ET0 are the innovations of current research. The results illustrated that the applied pre-processing methods introduced different climatic inputs to feed the models. The overall results of present study revealed that the proposed hybrid SVR-IWD model outperformed the standalone SVR one under both the considered scenarios when estimating the monthly ET0. In addition to the mentioned models, two types of empirical equations were also used including the Hargreaves{$-$}Samani (H{$-$}S) and Priestley{$-$}Taylor (P{$-$}T) in their original and calibrated versions. It was concluded that the calibrated versions showed superior performances compared to their original ones.", } @Article{journals/eaai/AhmadizarSAT15, author = "Fardin Ahmadizar and Khabat Soltanian and Fardin AkhlaghianTab and Ioannis Tsoulos", title = "Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithm", journal = "Engineering Applications of Artificial Intelligence", year = "2015", volume = "39", bibdate = "2015-02-23", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/eaai/eaai39.html#AhmadizarSAT15", pages = "1--13", month = mar, keywords = "genetic algorithms, genetic programming, grammatical evolution, Neural networks, ANN, Adaptive penalty approach, Classification problems", ISSN = "0952-1976", URL = "http://www.sciencedirect.com/science/article/pii/S0952197614002759", URL = "http://dx.doi.org/10.1016/j.engappai.2014.11.003", abstract = "The most important problems with exploiting artificial neural networks (ANNs) are to design the network topology, which usually requires an excessive amount of expert's effort, and to train it. In this paper, a new evolutionary-based algorithm is developed to simultaneously evolve the topology and the connection weights of ANNs by means of a new combination of grammatical evolution (GE) and genetic algorithm (GA). GE is adopted to design the network topology while GA is incorporated for better weight adaptation. The proposed algorithm needs to invest a minimal expert's effort for customisation and is capable of generating any feedforward ANN with one hidden layer. Moreover, due to the fact that the generalisation ability of an ANN may decrease because of over fitting problems, the algorithm uses a novel adaptive penalty approach to simplify ANNs generated through the evolution process. As a result, it produces much simpler ANNs that have better generalization ability and are easy to implement. The proposed method is tested on some real world classification datasets, and the results are statistically compared against existing methods in the literature. The results indicate that our algorithm outperforms the other methods and provides the best overall performance in terms of the classification accuracy and the number of hidden neurons. The results also present the contribution of the proposed penalty approach in the simplicity and generalisation ability of the generated networks.", notes = "also known as \cite{AHMADIZAR20151}", } @InProceedings{Ahmed:2015:ieeeICIP, author = "Faisal Ahmed and Padma Polash Paul and Marina L. Gavrilova", booktitle = "2015 IEEE International Conference on Image Processing (ICIP)", title = "Evolutionary fusion of local texture patterns for facial expression recognition", year = "2015", pages = "1031--1035", abstract = "This paper presents a simple, yet effective facial feature descriptor based on evolutionary synthesis of different local texture patterns. Unlike the traditional face descriptors that exploit visually-meaningful facial features, the proposed method adopts a genetic programming-based feature fusion approach that uses different local texture patterns and a set of linear and nonlinear operators in order to synthesise new features. The strength of this approach lies in fusing the advantages of different state-of-the-art local texture descriptors and thus, obtaining more robust composite features. Recognition performance of the proposed method is evaluated using the Cohn-Kanade (CK) and the Japanese female facial expression (JAFFE) database. In our experiments, facial features synthesised based on the proposed approach yield an improved recognition performance, as compared to some well-known face feature descriptors.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/ICIP.2015.7350956", month = sep, notes = "Also known as \cite{7350956}", } @Article{ahmed:2020:IJDC, author = "Moataz Ahmed and Moustafa El-Gindy and Haoxiang Lang", title = "A novel genetic-programming based differential braking controller for an 8x8 combat vehicle", journal = "International Journal of Dynamics and Control", year = "2020", volume = "8", number = "4", keywords = "genetic algorithms, genetic programming, Stability control, Direct yaw control, Differential braking, Adaptive neuro-fuzzy, Fuzzy logic", URL = "http://link.springer.com/article/10.1007/s40435-020-00693-0", DOI = "doi:10.1007/s40435-020-00693-0", size = "15 pages", abstract = "Lateral stability of multi-axle vehicle’s was not considered and studied widely despite its advantages and use in different fields such as transportation, commercial, and military applications. In this research, a novel adaptive Direct Yaw moment Control based on Genetic-Programming (GPDB) is developed and compared with an Adaptive Neuro-Fuzzy Inference System (ANFIS). In addition, a phase-plane analysis of the vehicles nonlinear model is also discussed to introduce the activation criteria to the proposed controller in order to prevent excessive control effort. The controller is evaluated through a series of severe maneuvers in the simulator. The developed GPDB resulting in comparable performance to the ANFIS controller with better implementation facility and design procedure, where a single equation replaces multiple fuzzy rules. The results show fidelity and the ability of the developed controller to stabilize the vehicle near limit-handling driving conditions", } @PhdThesis{Aboelfadl_Ahmed_Moataz, author = "Moataz Aboelfadl Ahmed", title = "Integrated Chassis Control Strategies For Multi-Wheel Combat Vehicle", school = "Department of Automotive and Mechatronics Engineering Faculty of Engineering and Applied Science, University of Ontario Institute of Technology", year = "2021", address = "Oshawa, Ontario, Canada", month = nov, keywords = "genetic algorithms, genetic programming, Chassis control, Lateral stability, Intelligent control, Multi-axle, Combat vehicles", URL = "https://hdl.handle.net/10155/1380", URL = "https://ir.library.ontariotechu.ca/handle/10155/1380", URL = "https://ir.library.ontariotechu.ca/bitstream/handle/10155/1380/Aboelfadl_Ahmed_Moataz.pdf", size = "227 pages", abstract = "Combat vehicles are exposed to high risks due to their high ground clearance and nature of operation in harsh environments. This requires robust stability controllers to cope with the rapid change and uncertainty of driving conditions on various terrains. Moreover, it is required to enhance vehicle stability and increase safety to reduce accidents fatality probability. This research focuses on investigating the effectiveness of different lateral stability controllers and their integration in enhancing the cornering performance of an 8x8 combat vehicle when driving at limited handling conditions. In this research, a new Active Rear Steering (ARS) stability controller for an 8x8 combat vehicle is introduced. This technique is extensively investigated to show its merits and effectiveness for human and autonomous operation. For human operation, the ARS is developed using Linear Quadratic Regulator (LQR) control method, which is compared with previous techniques. Furthermore, the controller is extended and tested for working in a rough and irregular road profile using a novel adaptive Integral Sliding Mode Controller (ISMC). In the case of autonomous operation, a frequency domain analysis is conducted to show the benefits of considering the steering of the rear axles in the path-following performance at different driving conditions. The study compared two different objectives for the controller; the first is including the steering of the rear axles in the path following controller, while the second is to integrate it as a stability controller with a front-steering path-following controller. In addition, this research introduces a novel Differential Braking (DB) controller. The proposed control prevents the excessive use of braking forces and consequently the longitudinal dynamics deterioration. Besides, it introduces an effective DB controller with less dependency and sensitivity to the reference yaw model. Eventually, two various Integrated Chassis Controllers (ICC) are developed and compared. The first is developed by integrating the ISMC-ARS with the DB controller using a fuzzy logic controller. The second ICC integrates the ISMC-ARS with a developed robust Torque Vectoring Controller (TVC). This integration is designed based on a performance map that shows the effective region of each controller using a new technique based on Machine Learning (ML).", notes = "Ontario Tech University Supervisor: Moustafa El-Gindy", } @InProceedings{DBLP:conf/ausai/AhmedZP12, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "Genetic Programming for Biomarker Detection in Mass Spectrometry Data", booktitle = "25th Joint Conference Australasian Conference on Artificial Intelligence, AI 2012", year = "2012", editor = "Michael Thielscher and Dongmo Zhang", volume = "7691", series = "Lecture Notes in Computer Science", pages = "266--278", address = "Sydney, Australia", month = dec # " 4-7", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-35100-6", DOI = "doi:10.1007/978-3-642-35101-3_23", abstract = "Classification of mass spectrometry (MS) data is an essential step for biomarker detection which can help in diagnosis and prognosis of diseases. However, due to the high dimensionality and the small sample size, classification of MS data is very challenging. The process of biomarker detection can be referred to as feature selection and classification in terms of machine learning. Genetic programming (GP) has been widely used for classification and feature selection, but it has not been effectively applied to biomarker detection in the MS data. In this study we develop a GP based approach to feature selection, feature extraction and classification of mass spectrometry data for biomarker detection. In this approach, we firstly use GP to reduce the redundant features by selecting a small number of important features and constructing high-level features, then we use GP to classify the data based on selected features and constructed features. This approach is examined and compared with three well known machine learning methods namely decision trees, naive Bayes and support vector machines on two biomarker detection data sets. The results show that the proposed GP method can effectively select a small number of important features from thousands of original features for these problems, the constructed high-level features can further improve the classification performance, and the GP method outperforms the three existing methods, namely naive Bayes, SVMs and J48, on these problems.", } @InProceedings{Ahmed:2013:evobio, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "Feature Selection and Classification of High Dimensional Mass Spectrometry Data: A Genetic Programming Approach", booktitle = "11th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, {EvoBIO 2013}", year = "2013", editor = "Leonardo Vanneschi and William S. Bush and Mario Giacobini", month = apr # " 3-5", series = "LNCS", volume = "7833", publisher = "Springer Verlag", organisation = "EvoStar", address = "Vienna, Austria", pages = "43--55", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-37188-2", DOI = "doi:10.1007/978-3-642-37189-9_5", abstract = "Biomarker discovery using mass spectrometry (MS) data is very useful in disease detection and drug discovery. The process of biomarker discovery in MS data must start with feature selection as the number of features in MS data is extremely large (e.g. thousands) while the number of samples is comparatively small. In this study, we propose the use of genetic programming (GP) for automatic feature selection and classification of MS data. This GP based approach works by using the features selected by two feature selection metrics, namely information gain (IG) and relief-f (REFS-F) in the terminal set. The feature selection performance of the proposed approach is examined and compared with IG and REFS-F alone on five MS data sets with different numbers of features and instances. Naive Bayes (NB), support vector machines (SVMs) and J48 decision trees (J48) are used in the experiments to evaluate the classification accuracy of the selected features. Meanwhile, GP is also used as a classification method in the experiments and its performance is compared with that of NB, SVMs and J48. The results show that GP as a feature selection method can select a smaller number of features with better classification performance than IG and REFS-F using NB, SVMs and J48. In addition, GP as a classification method also outperforms NB and J48 and achieves comparable or slightly better performance than SVMs on these data sets.", } @InProceedings{Ahmed:2013:CEC, article_id = "1253", author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "Enhanced Feature Selection for Biomarker Discovery in LC-MS Data using GP", booktitle = "2013 IEEE Conference on Evolutionary Computation", volume = "1", year = "2013", month = jun # " 20-23", editor = "Luis Gerardo {de la Fraga}", pages = "584--591", address = "Cancun, Mexico", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-4799-0453-2", DOI = "doi:10.1109/CEC.2013.6557621", notes = "CEC 2013 - A joint meeting of the IEEE, the EPS and the IET.", } @InProceedings{Ahmed:evoapps14, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "GPMS: A Genetic Programming Based Approach to Multiple Alignment of Liquid Chromatography-Mass Spectrometry Data", booktitle = "17th European Conference on the Applications of Evolutionary Computation", year = "2014", editor = "Anna Isabel Esparcia-Alcazar and Antonio Miguel Mora", series = "LNCS", volume = "8602", publisher = "Springer", pages = "915--927", address = "Granada", month = "23-25 " # apr, organisation = "EvoStar", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-662-45522-7", DOI = "doi:10.1007/978-3-662-45523-4_74", abstract = "Alignment of samples from Liquid chromatography-mass spectrometry (LC-MS) measurements has a significant role in the detection of biomarkers and in metabolomic studies.The machine drift causes differences between LC-MS measurements, and an accurate alignment of the shifts introduced to the same peptide or metabolite is needed. In this paper, we propose the use of genetic programming (GP) for multiple alignment of LC-MS data. The proposed approach consists of two main phases. The first phase is the peak matching where the peaks from different LC-MS maps (peak lists) are matched to allow the calculation of the retention time deviation. The second phase is to use GP for multiple alignment of the peak lists with respect to a reference. In this paper, GP is designed to perform multiple-output regression by using a special node in the tree which divides the output of the tree into multiple outputs. Finally, the peaks that show the maximum correlation after dewarping the retention times are selected to form a consensus aligned map.The proposed approach is tested on one proteomics and two metabolomics LC-MS datasets with different number of samples. The method is compared to several benchmark methods and the results show that the proposed approach outperforms these methods in three fractions of the protoemics dataset and the metabolomics dataset with a larger number of maps. Moreover, the results on the rest of the datasets are highly competitive with the other methods", notes = "EvoApplications2014 held in conjunction with EuroGP'2014, EvoCOP2014, EvoBIO2014, and EvoMusArt2014", } @InProceedings{Ahmed:2014:CEC, title = "A New {GP}-Based Wrapper Feature Construction Approach to Classification and Biomarker Identification", author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", pages = "2756--2763", booktitle = "Proceedings of the 2014 IEEE Congress on Evolutionary Computation", year = "2014", month = "6-11 " # jul, editor = "Carlos A. {Coello Coello}", address = "Beijing, China", ISBN = "0-7803-8515-2", keywords = "genetic algorithms, genetic programming, Evolutionary programming, Biometrics, bioinformatics and biomedical applications", DOI = "doi:10.1109/CEC.2014.6900317", abstract = "Mass spectrometry (MS) is a technology used for identification and quantification of proteins and metabolites. It helps in the discovery of proteomic or metabolomic biomarkers, which aid in diseases detection and drug discovery. The detection of biomarkers is performed through the classification of patients from healthy samples. The mass spectrometer produces high dimensional data where most of the features are irrelevant for classification. Therefore, feature reduction is needed before the classification of MS data can be done effectively. Feature construction can provide a means of dimensionality reduction and aims at improving the classification performance. In this paper, genetic programming (GP) is used for construction of multiple features. Two methods are proposed for this objective. The proposed methods work by wrapping a Random Forest (RF) classifier to GP to ensure the quality of the constructed features. Meanwhile, five other classifiers in addition to RF are used to test the impact of the constructed features on the performance of these classifiers. The results show that the proposed GP methods improved the performance of classification over using the original set of features in five MS data sets.", notes = "WCCI2014", } @InProceedings{Ahmed:2014:GECCOa, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng and Bing Xue", title = "Multiple feature construction for effective biomarker identification and classification using genetic programming", booktitle = "GECCO '14: Proceedings of the 2014 conference on Genetic and evolutionary computation", year = "2014", editor = "Christian Igel and Dirk V. Arnold and Christian Gagne and Elena Popovici and Anne Auger and Jaume Bacardit and Dimo Brockhoff and Stefano Cagnoni and Kalyanmoy Deb and Benjamin Doerr and James Foster and Tobias Glasmachers and Emma Hart and Malcolm I. Heywood and Hitoshi Iba and Christian Jacob and Thomas Jansen and Yaochu Jin and Marouane Kessentini and Joshua D. Knowles and William B. Langdon and Pedro Larranaga and Sean Luke and Gabriel Luque and John A. W. McCall and Marco A. {Montes de Oca} and Alison Motsinger-Reif and Yew Soon Ong and Michael Palmer and Konstantinos E. Parsopoulos and Guenther Raidl and Sebastian Risi and Guenther Ruhe and Tom Schaul and Thomas Schmickl and Bernhard Sendhoff and Kenneth O. Stanley and Thomas Stuetzle and Dirk Thierens and Julian Togelius and Carsten Witt and Christine Zarges", isbn13 = "978-1-4503-2662-9", pages = "249--256", keywords = "genetic algorithms, genetic programming", month = "12-16 " # jul, organisation = "SIGEVO", address = "Vancouver, BC, Canada", URL = "http://doi.acm.org/10.1145/2576768.2598292", DOI = "doi:10.1145/2576768.2598292", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "Biomarker identification, i.e., detecting the features that indicate differences between two or more classes, is an important task in omics sciences. Mass spectrometry (MS) provide a high throughput analysis of proteomic and metabolomic data. The number of features of the MS data sets far exceeds the number of samples, making biomarker identification extremely difficult. Feature construction can provide a means for solving this problem by transforming the original features to a smaller number of high-level features. This paper investigates the construction of multiple features using genetic programming (GP) for biomarker identification and classification of mass spectrometry data. In this paper, multiple features are constructed using GP by adopting an embedded approach in which Fisher criterion and p-values are used to measure the discriminating information between the classes. This produces nonlinear high-level features from the low-level features for both binary and multi-class mass spectrometry data sets. Meanwhile, seven different classifiers are used to test the effectiveness of the constructed features. The proposed GP method is tested on eight different mass spectrometry data sets. The results show that the high-level features constructed by the GP method are effective in improving the classification performance in most cases over the original set of features and the low-level selected features. In addition, the new method shows superior performance in terms of biomarker detection rate.", notes = "Also known as \cite{2598292} GECCO-2014 A joint meeting of the twenty third international conference on genetic algorithms (ICGA-2014) and the nineteenth annual genetic programming conference (GP-2014)", } @InProceedings{Ahmed:2014:GECCOcomp, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "Prediction of detectable peptides in MS data using genetic programming", booktitle = "GECCO Comp '14: Proceedings of the 2014 conference companion on Genetic and evolutionary computation companion", year = "2014", editor = "Christian Igel and Dirk V. Arnold and Christian Gagne and Elena Popovici and Anne Auger and Jaume Bacardit and Dimo Brockhoff and Stefano Cagnoni and Kalyanmoy Deb and Benjamin Doerr and James Foster and Tobias Glasmachers and Emma Hart and Malcolm I. Heywood and Hitoshi Iba and Christian Jacob and Thomas Jansen and Yaochu Jin and Marouane Kessentini and Joshua D. Knowles and William B. Langdon and Pedro Larranaga and Sean Luke and Gabriel Luque and John A. W. McCall and Marco A. {Montes de Oca} and Alison Motsinger-Reif and Yew Soon Ong and Michael Palmer and Konstantinos E. Parsopoulos and Guenther Raidl and Sebastian Risi and Guenther Ruhe and Tom Schaul and Thomas Schmickl and Bernhard Sendhoff and Kenneth O. Stanley and Thomas Stuetzle and Dirk Thierens and Julian Togelius and Carsten Witt and Christine Zarges", isbn13 = "978-1-4503-2881-4", keywords = "genetic algorithms, genetic programming, biological and biomedical applications: Poster", pages = "37--38", month = "12-16 " # jul, organisation = "SIGEVO", address = "Vancouver, BC, Canada", URL = "http://doi.acm.org/10.1145/2598394.2598421", DOI = "doi:10.1145/2598394.2598421", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "The use of mass spectrometry to verify and quantify biomarkers requires the identification of the peptides that can be detectable. In this paper, we propose the use of genetic programming (GP) to measure the detection probability of the peptides. The new GP method is tested and verified on two different yeast data sets with increasing complexity and shows improved performance over other state-of-art classification and feature selection algorithms.", notes = "Also known as \cite{2598421} Distributed at GECCO-2014.", } @Article{Ahmed:2014:CS, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng", title = "Improving Feature Ranking for Biomarker Discovery in Proteomics Mass Spectrometry Data using Genetic Programming", journal = "Connection Science", year = "2014", volume = "26", number = "3", pages = "215--243", keywords = "genetic algorithms, genetic programming, biomarker discovery, feature selection, classification", ISSN = "0954-0091", DOI = "doi:10.1080/09540091.2014.906388", size = "29 pages", abstract = "Feature selection on mass spectrometry (MS) data is essential for improving classification performance and biomarker discovery. The number of MS samples is typically very small compared with the high dimensionality of the samples, which makes the problem of biomarker discovery very hard. In this paper, we propose the use of genetic programming for biomarker detection and classification of MS data. The proposed approach is composed of two phases: in the first phase, feature selection and ranking are performed. In the second phase, classification is performed. The results show that the proposed method can achieve better classification performance and biomarker detection rate than the information gain (IG) based and the RELIEF feature selection methods. Meanwhile, four classifiers, Naive Bayes, J48 decision tree, random forest and support vector machines, are also used to further test the performance of the top ranked features. The results show that the four classifiers using the top ranked features from the proposed method achieve better performance than the IG and the RELIEF methods. Furthermore, GP also outperforms a genetic algorithm approach on most of the used data sets.", } @InProceedings{conf/seal/AhmedZPX14, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng and Bing Xue", title = "Genetic Programming for Measuring Peptide Detectability", bibdate = "2014-11-12", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/seal/seal2014.html#AhmedZPX14", booktitle = "Simulated Evolution and Learning - 10th International Conference, {SEAL} 2014, Dunedin, New Zealand, December 15-18, 2014. Proceedings", publisher = "Springer", year = "2014", volume = "8886", editor = "Grant Dick and Will N. Browne and Peter A. Whigham and Mengjie Zhang and Lam Thu Bui and Hisao Ishibuchi and Yaochu Jin and Xiaodong Li and Yuhui Shi and Pramod Singh and Kay Chen Tan and Ke Tang", isbn13 = "978-3-319-13562-5", pages = "593--604", series = "Lecture Notes in Computer Science", keywords = "genetic algorithms, genetic programming", URL = "http://dx.doi.org/10.1007/978-3-319-13563-2", } @InProceedings{conf/evoW/AhmedZPX16, author = "Soha Ahmed and Mengjie Zhang and Lifeng Peng and Bing Xue", title = "A Multi-objective Genetic Programming Biomarker Detection Approach in Mass Spectrometry Data", booktitle = "19th European Conference on Applications of Evolutionary Computation, EvoApplications 2016", year = "2016", editor = "Giovanni Squillero and Paolo Burelli", volume = "9597", series = "Lecture Notes in Computer Science", pages = "106--122", address = "Porto, Portugal", month = mar # " 30 -- " # apr # " 1", organisation = "EvoStar", publisher = "Springer", keywords = "genetic algorithms, genetic programming", bibdate = "2016-03-23", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/evoW/evoappl2016-1.html#AhmedZPX16", isbn13 = "978-3-319-31204-0", DOI = "doi:10.1007/978-3-319-31204-0_8", abstract = "Mass spectrometry is currently the most commonly used technology in biochemical research for proteomic analysis. The main goal of proteomic profiling using mass spectrometry is the classification of samples from different clinical states. This requires the identification of proteins or peptides (biomarkers) that are expressed differentially between different clinical states. However, due to the high dimensionality of the data and the small number of samples, classification of mass spectrometry data is a challenging task. Therefore, an effective feature manipulation algorithm either through feature selection or construction is needed to enhance the classification performance and at the same time minimise the number of features. Most of the feature manipulation methods for mass spectrometry data treat this problem as a single objective task which focuses on improving the classification performance. This paper presents two new methods for biomarker detection through multi-objective feature selection and feature construction. The results show that the proposed multi-objective feature selection method can obtain better subsets of features than the single-objective algorithm and two traditional multi-objective approaches for feature selection. Moreover, the multi-objective feature construction algorithm further improves the performance over the multi-objective feature selection algorithm. This paper is the first multi-objective genetic programming approach for biomarker detection in mass spectrometry data", notes = "EvoApplications2016 held inconjunction with EuroGP'2016, EvoCOP2016 and EvoMUSART 2016", } @Article{ahmed:2021:Materials, author = "Waleed Ahmed and Hussien Hegab and Atef Mohany and Hossam Kishawy", title = "Analysis and Optimization of Machining Hardened Steel {AISI} 4140 with {Self-Propelled} Rotary Tools", journal = "Materials", year = "2021", volume = "14", number = "20", keywords = "genetic algorithms, genetic programming, modeling, machining, optimization, rotary tools", ISSN = "1996-1944", URL = "https://www.mdpi.com/1996-1944/14/20/6106", DOI = "doi:10.3390/ma14206106", abstract = "It is necessary to improve the machinability of difficult-to-cut materials such as hardened steel, nickel-based alloys, and titanium alloys as these materials offer superior properties such as chemical stability, corrosion resistance, and high strength to weight ratio, making them indispensable for many applications. Machining with self-propelled rotary tools (SPRT) is considered one of the promising techniques used to provide proper tool life even under dry conditions. In this work, an attempt has been performed to analyse, model, and optimise the machining process of AISI 4140 hardened steel using self-propelled rotary tools. Experimental analysis has been offered to (a) compare the fixed and rotary tools performance and (b) study the effect of the inclination angle on the surface quality and tool wear. Moreover, the current study implemented some artificial intelligence-based approaches (i.e., genetic programming and NSGA-II) to model and optimise the machining process of AISI 4140 hardened steel with self-propelled rotary tools. The feed rate, cutting velocity, and inclination angle were the selected design variables, while the tool wear, surface roughness, and material removal rate (MRR) were the studied outputs. The optimal surface roughness was obtained at a cutting speed of 240 m/min, an inclination angle of 20?, and a feed rate of 0.1 mm/rev. In addition, the minimum flank tool wear was observed at a cutting speed of 70 m/min, an inclination angle of 10?, and a feed rate of 0.15 mm/rev. Moreover, different weights have been assigned for the three studied outputs to offer different optimised solutions based on the designer's interest (equal-weighted, finishing, and productivity scenarios). It should be stated that the findings of the current work offer valuable recommendations to select the optimised cutting conditions when machining hardened steel AISI 4140 within the selected ranges.", notes = "also known as \cite{ma14206106}", } @Article{AHMED:2023:isatra, author = "Umair Ahmed and Fakhre Ali and Ian Jennions", title = "Acoustic monitoring of an aircraft auxiliary power unit", journal = "ISA Transactions", year = "2023", ISSN = "0019-0578", DOI = "doi:10.1016/j.isatra.2023.01.014", URL = "https://www.sciencedirect.com/science/article/pii/S0019057823000149", keywords = "genetic algorithms, genetic programming, Aircraft, Auxiliary power unit, Condition monitoring, Acoustics, Signal processing, Machine learning, Sensors, Feature extraction, Fault detection, Microphones", abstract = "In this paper, the development and implementation of a novel approach for fault detection of an aircraft auxiliary power unit (APU) has been demonstrated. The developed approach aims to target the proactive identification of faults, in order to streamline the required maintenance and maximize the aircraft's operational availability. The existing techniques rely heavily on the installation of multiple types of intrusive sensors throughout the APU and therefore present a limited potential for deployment on an actual aircraft due to space constraints, accessibility issues as well as associated development and certification requirements. To overcome these challenges, an innovative approach based on non-intrusive sensors i.e., microphones in conjunction with appropriate feature extraction, classification, and regression techniques, has been successfully demonstrated for online fault detection of an APU. The overall approach has been implemented and validated based on the experimental test data acquired from Cranfield University's Boeing 737-400 aircraft, including the quantification of sensor location sensitivities on the efficacy of the acquired models. The findings of the overall analysis suggest that the acoustic-based models can accurately enable near real-time detection of faulty conditions i.e., Inlet Guide Vane malfunction, reduced mass flows through the Load Compressor and Bleed Valve malfunction, using only two microphones installed in the periphery of the APU. This study constitutes an enabling technology for robust, cost-effective, and efficient in-situ monitoring of an aircraft APU and potentially other associated thermal systems i.e., environmental control system, fuel system, and engines", } @Article{Ahmed:JBHI, author = "Usman Ahmed and Jerry Chun-Wei Lin and Gautam Srivastava", journal = "IEEE Journal of Biomedical and Health Informatics", title = "Towards Early Diagnosis and Intervention: An Ensemble Voting Model for Precise Vital Sign Prediction in Respiratory Disease", year = "2023", abstract = "Worldwide, cardiovascular and chronic respiratory diseases account for approximately 19 million deaths annually. Evidence indicates that the ongoing COVID-19 pandemic directly contributes to increased blood pressure, cholesterol, as well as blood glucose levels. Timely screening of critical physiological vital signs benefits both healthcare providers and individuals by detecting potential health issues. This study aims to implement a machine learning-based prediction and classification system to forecast vital signs associated with cardiovascular and chronic respiratory diseases. The system predicts patients' health status and notifies caregivers and medical professionals when necessary. Using real-world data, a linear regression model inspired by the Facebook Prophet model was developed to predict vital signs for the upcoming 180 seconds. With 180 seconds of lead time, caregivers can potentially save patients' lives through early diagnosis of their health conditions. For this purpose, a Naive Bayes classification model, a Support Vector Machine model, a Random Forest model, and genetic programming-based hyper tunning were employed. The proposed model outdoes previous attempts at vital sign prediction. Compared with alternative methods, the Facebook Prophet model has the best mean square in predicting vital signs. A hyperparameter-tuning is used to refine the model, yielding improved short- and long-term outcomes for each and every vital sign. Furthermore, the F-measure for the proposed classification model is 0.98 with an increase of 0.21. The incorporation of additional elements, such as momentum indicators, could increase the model's flexibility with calibration. The findings of this study demonstrate that the proposed model is more accurate in predicting vital signs and trends.", keywords = "genetic algorithms, genetic programming, Diseases, Medical diagnostic imaging, Medical services, Heart, Predictive models, Machine learning, Decision trees, Artificial intelligence, Sensor readings, Heart disease, Long-term lung disease", DOI = "doi:10.1109/JBHI.2023.3270888", ISSN = "2168-2208", notes = "Also known as \cite{10121013}", } @Article{AHMED:2023:suscom, author = "Usman Ahmed and Jerry Chun-Wei Lin and Gautam Srivastava", title = "Multivariate time-series sensor vital sign forecasting of cardiovascular and chronic respiratory diseases", journal = "Sustainable Computing: Informatics and Systems", volume = "38", pages = "100868", year = "2023", ISSN = "2210-5379", DOI = "doi:10.1016/j.suscom.2023.100868", URL = "https://www.sciencedirect.com/science/article/pii/S2210537923000239", keywords = "genetic algorithms, genetic programming, Machine learning, Sensor data, Cardiovascular disease, Chronic respiratory disease. TPOT", abstract = "Approximately 19 million people die each year from cardiovascular and chronic respiratory diseases. As a result of the recent Covid-19 epidemic, blood pressure, cholesterol, and blood sugar levels have risen. Not only do healthcare institutions benefit from studying physiological vital signs, but individuals also benefit from being alerted to health problems in a timely manner. This study uses machine learning to categorize and predict cardiovascular and chronic respiratory diseases. By predicting a patient's health status, caregivers and medical professionals can be alerted when needed. We predicted vital signs for 180 seconds using real-world vital sign data. A person's life can be saved if caregivers react quickly and anticipate emergencies. The tree-based pipeline optimization method (TPOT) is used instead of manually adjusting machine learning classifiers. This paper focuses on optimizing classification accuracy by combining feature pre-processors and machine learning models with TPOT genetic programming making use of linear and Prophet models to predict important indicators. The TPOT tuning parameter combines predicted values with classical classification models such as Naive Bayes, Support Vector Machines, and Random Forests. As a result of this study, we show the importance of categorizing and increasing the accuracy of predictions. The proposed model achieves its adaptive behavior by conceptually incorporating different machine learning classifiers. We compare the proposed model with several state-of-the-art algorithms using a large amount of training data. Test results at the University of Queensland using 32 patient's data showed that the proposed model outperformed existing algorithms, improving the classification of cardiovascular disease from 0.58 to 0.71 and chronic respiratory disease from 0.49 to 0.70, respectively, while minimizing the mean percent error in vital signs. Our results suggest that the Facebook Prophet prediction model in conjunction with the TPOT classification model can correctly diagnose a patient's health status based on abnormal vital signs and enables patients to receive prompt medical attention", } @InProceedings{conf/fgit/AhnOO11, author = "Chang Wook Ahn and Sanghoun Oh and Moonyoung Oh", title = "A Genetic Programming Approach to Data Clustering", booktitle = "Proceedings of the International Conference on Multimedia, Computer Graphics and Broadcasting (MulGraB 2011) Part {II}", editor = "Tai-Hoon Kim and Hojjat Adeli and William I. Grosky and Niki Pissinou and Timothy K. Shih and Edward J. Rothwell and Byeong Ho Kang and Seung-Jung Shin", year = "2011", volume = "263", series = "Communications in Computer and Information Science", pages = "123--132", address = "Jeju Island, Korea", month = dec # " 8-10", publisher = "Springer", note = "Held as Part of the Future Generation Information Technology Conference, {FGIT} 2011, in Conjunction with {GDC} 2011", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-27186-1", DOI = "doi:10.1007/978-3-642-27186-1_15", size = "10 pages", abstract = "This paper presents a genetic programming (GP) to data clustering. The aim is to accurately classify a set of input data into their genuine clusters. The idea lies in discovering a mathematical function on clustering regularities and then use the rule to make a correct decision on the entities of each cluster. To this end, GP is incorporated into the clustering procedures. Each individual is represented by a parsing tree on the program set. Fitness function evaluates the quality of clustering with regard to similarity criteria. Crossover exchanges sub-trees between parental candidates in a positionally independent fashion. Mutation introduces (in part) a new sub-tree with a low probability. The variation operators (i.e., crossover, mutation) offer an effective search capability to obtain the improved quality of solution and the enhanced speed of convergence. Experimental results demonstrate that the proposed approach outperforms a well-known reference.", affiliation = "School of Information & Communication Engineering, Sungkyunkwan University, Suwon, 440-746 Korea", bibdate = "2011-12-08", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/fgit/mulgrab2011-2.html#AhnOO11", } @Article{Aho97, author = "Hannu Ahonen and Paulo A. {de Souza Jr.} and Vijayendra Kumar Garg", title = "A genetic algorithm for fitting Lorentzian line shapes in Mossbauer spectra", journal = "Nuclear Instruments and Methods in Physics Research B", year = "1997", volume = "124", pages = "633--638", month = "5 " # may, email = "souza@iacgu7.chemie.uni-mainz.de", keywords = "genetic algorithms", ISSN = "0168583X", abstract = "A genetic algorithm was implemented for finding an approximative solution to the problem of fitting a combination of Lorentzian lines to a measured Mossbauer spectrum. This iterative algorithm exploits the idea of letting several solutions (individuals) compete with each other for the opportunity of being selected to create new solutions (reproduction). Each solution was represend as a string of binary digits (chromossome). In addition, the bits in the new solutions may be switched randomly from zero to one or conversely (mutation). The input of the program that implements the genetic algorithm consists of the measured spectrum, the maximum velocity, the peak positions and the expected number of Lorentzian lines in the spectrum. Each line is represented with the help of three variables, which correspond to its intensity, full line width at hald maxima and peak position. An additional parameter was associated to the background level in the spectrum. A chi-2 test was used for determining the quality of each parameter combination (fitness). The results obtained seem to be very promising and encourage to further development of the algorithm and its implementation.", } @InProceedings{Ahsan:2020:IBCAST, author = "Usama Ahsan and Fayyaz ul Amir Afsar Minhas", booktitle = "2020 17th International Bhurban Conference on Applied Sciences and Technology (IBCAST)", title = "{AutoQP:} Genetic Programming for Quantum Programming", year = "2020", pages = "378--382", abstract = "Quantum computing is a new era in the field of computation which makes use of quantum mechanical phenomena such as superposition, entanglement, and quantum annealing. It is a very promising field and has given a new paradigm to efficiently solve complex computational problems. However, programming quantum computers is a difficult task. In this research, we have developed a system called AutoQP which can write quantum computer code through genetic programming on a classical computer provided the input and expected output of a quantum program. We have tested AutoQP on two different quantum algorithms: Deutsch Problem and the Bernstein-Vazirani problem. In our experimental analysis, AutoQP was able to generate quantum programs for solving both problems. The code generated by AutoQP was successfully tested on actual IBM quantum computers as well. It is expected that the proposed system can be very useful for the general development of quantum programs based on the IBM gate model. The source code for the proposed system is available at the URL: https://github.com/usamaahsan93/AutoQP.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/IBCAST47879.2020.9044554", ISSN = "2151-1411", month = jan, notes = "Also known as \cite{9044554}", } @Article{DBLP:journals/itiis/AhvanooeyLWW19, author = "Milad Taleby Ahvanooey and Qianmu Li and Ming Wu and Shuo Wang", title = "A Survey of Genetic Programming and Its Applications", journal = "{KSII} Trans. Internet Inf. Syst.", volume = "13", number = "4", pages = "1765--1794", year = "2019", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.3837/tiis.2019.04.002", DOI = "doi:10.3837/tiis.2019.04.002", timestamp = "Thu, 25 Jun 2020 01:00:00 +0200", biburl = "https://dblp.org/rec/journals/itiis/AhvanooeyLWW19.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @PhdThesis{Lifeng_Ai_Thesis, author = "Lifeng Ai", title = "{QoS-aware} web service composition using genetic algorithms", school = "Queensland University of Technology", year = "2011", address = "Australia", month = jun, keywords = "genetic algorithms, quality of service, web services, composite web services, optimisation", URL = "http://eprints.qut.edu.au/46666/1/Lifeng_Ai_Thesis.pdf", URL = "http://eprints.qut.edu.au/46666/", size = "pages", abstract = "Web service technology is increasingly being used to build various e-Applications, in domains such as e-Business and e-Science. Characteristic benefits of web service technology are its inter-operability, decoupling and just-in-time integration. Using web service technology, an e-Application can be implemented by web service composition, by composing existing individual web services in accordance with the business process of the application. This means the application is provided to customers in the form of a value-added composite web service. An important and challenging issue of web service composition, is how to meet Quality-of-Service (QoS) requirements. This includes customer focused elements such as response time, price, throughput and reliability as well as how to best provide QoS results for the composites. This in turn best fulfils customers' expectations and achieves their satisfaction. Fulfilling these QoS requirements or addressing the QoS-aware web service composition problem is the focus of this project. From a computational point of view, QoS-aware web service composition can be transformed into diverse optimisation problems. These problems are characterised as complex, large-scale, highly constrained and multi-objective problems. We therefore use genetic algorithms (GAs) to address QoS-based service composition problems. More precisely, this study addresses three important subproblems of QoS-aware web service composition; QoS-based web service selection for a composite web service accommodating constraints on inter-service dependence and conflict, QoS-based resource allocation and scheduling for multiple composite services on hybrid clouds, and performance-driven composite service partitioning for decentralised execution. Based on operations research theory, we model the three problems as a constrained optimisation problem, a resource allocation and scheduling problem, and a graph partitioning problem, respectively. Then, we present novel GAs to address these problems. We also conduct experiments to evaluate the performance of the new GAs. Finally, verification experiments are performed to show the correctness of the GAs. The major outcomes from the first problem are three novel GAs: a penaltybased GA, a min-conflict hill-climbing repairing GA, and a hybrid GA. These GAs adopt different constraint handling strategies to handle constraints on interservice dependence and conflict. This is an important factor that has been largely ignored by existing algorithms that might lead to the generation of infeasible composite services. Experimental results demonstrate the effectiveness of our GAs for handling the QoS-based web service selection problem with constraints on inter-service dependence and conflict, as well as their better scalability than the existing integer programming-based method for large scale web service selection problems. The major outcomes from the second problem has resulted in two GAs; a random-key GA and a cooperative coevolutionary GA (CCGA). Experiments demonstrate the good scalability of the two algorithms. In particular, the CCGA scales well as the number of composite services involved in a problem increases, while no other algorithms demonstrate this ability. The findings from the third problem result in a novel GA for composite service partitioning for decentralised execution. Compared with existing heuristic algorithms, the new GA is more suitable for a large-scale composite web service program partitioning problems. In addition, the GA outperforms existing heuristic algorithms, generating a better deployment topology for a composite web service for decentralised execution. These effective and scalable GAs can be integrated into QoS-based management tools to facilitate the delivery of feasible, reliable and high quality composite web services.", notes = "also know as \cite{quteprints46666} ID Code: 46666 Supervisor: Tang, Maolin & Fidge, Colin", } @InProceedings{Aichour:2007:NICSO, author = "Malek Aichour and Evelyne Lutton", title = "Cooperative Co-evolution Inspired Operators for Classical GP Schemes", booktitle = "Proceedings of International Workshop on Nature Inspired Cooperative Strategies for Optimization (NICSO '07)", year = "2007", pages = "169--178", editor = "Natalio Krasnogor and Giuseppe Nicosia and Mario Pavone and David Pelta", volume = "129", series = "Studies in Computational Intelligence", address = "Acireale, Italy", month = "8-10 " # nov, publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-540-78986-4", DOI = "doi:10.1007/978-3-540-78987-1_16", abstract = "This work is a first step toward the design of a cooperative-coevolution GP for symbolic regression, which first output is a selective mutation operator for classical GP. Cooperative co-evolution techniques rely on the imitation of cooperative capabilities of natural populations and have been successfully applied in various domains to solve very complex optimisation problems. It has been proved on several applications that the use of two fitness measures (local and global) within an evolving population allow to design more efficient optimization schemes. We currently investigate the use of a two-level fitness measurement for the design of operators, and present in this paper a selective mutation operator. Experimental analysis on a symbolic regression problem give evidence of the efficiency of this operator in comparison to classical subtree mutation", notes = "http://www.dmi.unict.it/nicso2007/ http://www.dmi.unict.it/nicso2007/NICSO2007-program.pdf", } @InProceedings{Ain:2022:ICDMW, author = "Qurrat Ul Ain and Bing Xue and Harith Al-Sahaf and Mengjie Zhang", booktitle = "2022 IEEE International Conference on Data Mining Workshops (ICDMW)", title = "A Genetic Programming Approach to Automatically Construct Informative Attributes for Mammographic Density Classification", year = "2022", pages = "378--387", abstract = "Breast density is widely used as an initial indicator of developing breast cancer. At present, current classification methods for mammographic density usually require manual operations or expert knowledge that makes them expensive in real-time situations. Such methods achieve only moderate classification accuracy due to the limited model capacity and computational resources. In addition, most existing studies focus on improving classification accuracy using only raw images or the entire set of original attributes and remain unable to identify hidden patterns or causal information necessary to discriminate breast density classes. It is challenging to find high-quality knowledge when some attributes defining the data space are redundant or irrelevant. In this study, we present a novel attribute construction method using genetic programming (GP) for the task of breast density classification. To extract informative features from the raw mammographic images, wavelet decomposition, local binary patterns, and histogram of oriented gradients are used to include texture, local and global image properties. The study evaluates the goodness of the proposed method on two benchmark real-world mammographic image datasets and compares the results of the proposed GP method with eight conventional classification methods. The experimental results reveal that the proposed method significantly outperforms most of the commonly used classification methods in binary and multi-class classification tasks. Furthermore, the study shows the potential of G P for mammographic breast density classification by interpreting evolved attributes that highlight important breast density characteristics.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/ICDMW58026.2022.00057", ISSN = "2375-9259", month = nov, notes = "Also known as \cite{10031110}", } @Article{Ain:2022:ieeeTC, author = "Qurrat Ul Ain and Harith Al-Sahaf and Bing Xue and Mengjie Zhang", journal = "IEEE Transactions on Cybernetics", title = "Automatically Diagnosing Skin Cancers From Multimodality Images Using Two-Stage Genetic Programming", year = "2022", abstract = "Developing a computer-aided diagnostic system for detecting various skin malignancies from images has attracted many researchers. Unlike many machine-learning approaches, such as artificial neural networks, genetic programming (GP) automatically evolves models with flexible representation. GP successfully provides effective solutions using its intrinsic ability to select prominent features (i.e., feature selection) and build new features (i.e., feature construction). Existing approaches have used GP to construct new features from the complete set of original features and the set of operators. However, the complete set of features may contain redundant or irrelevant features that do not provide useful information for classification. This study aims to develop a two-stage GP method, where the first stage selects prominent features, and the second stage constructs new features from these selected features and operators, such as multiplication in a wrapper approach to improve the classification performance. To include local, global, texture, color, and multiscale image properties of skin images, GP selects and constructs features extracted from local binary patterns and pyramid-structured wavelet decomposition. The accuracy of this GP method is assessed using two real-world skin image datasets captured from the standard camera and specialized instruments, and compared with commonly used classification algorithms, three state of the art, and an existing embedded GP method. The results reveal that this new approach of feature selection and feature construction effectively helps improve the performance of the machine-learning classification algorithms. Unlike other black-box models, the evolved models by GP are interpretable; therefore, the proposed method can assist dermatologists to identify prominent features, which has been shown by further analysis on the evolved models.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/TCYB.2022.3182474", ISSN = "2168-2275", notes = "Also known as \cite{9819829}", } @Article{AIN:2022:eswa, author = "Qurrat Ul Ain and Harith Al-Sahaf and Bing Xue and Mengjie Zhang", title = "Genetic programming for automatic skin cancer image classification", journal = "Expert Systems with Applications", volume = "197", pages = "116680", year = "2022", ISSN = "0957-4174", DOI = "doi:10.1016/j.eswa.2022.116680", URL = "https://www.sciencedirect.com/science/article/pii/S0957417422001634", keywords = "genetic algorithms, genetic programming, Image classification, Dimensionality reduction, Feature selection, Feature construction", abstract = "Developing a computer-aided diagnostic system for detecting various types of skin malignancies from images has attracted many researchers. However, analyzing the behaviors of algorithms is as important as developing new systems in order to establish the effectiveness of a system in real-time situations which impacts greatly how well it can assist the dermatologist in making a diagnosis. Unlike many machine learning approaches such as Artificial Neural Networks, Genetic Programming (GP) automatically evolves models with its dynamic representation and flexibility. This study aims at analyzing recently developed GP-based approaches to skin image classification. These approaches have used the intrinsic feature selection and feature construction ability of GP to effectively construct informative features from a variety of pre-extracted features. These features encompass local, global, texture, color and multi-scale image properties of skin images. The performance of these GP methods is assessed using two real-world skin image datasets captured from standard camera and specialized instruments, and compared with six commonly used classification algorithms as well as existing GP methods. The results reveal that these constructed features greatly help improve the performance of the machine learning classification algorithms. Unlike {"}black-box{"} algorithms like deep neural networks, GP models are interpretable, therefore, our analysis shows that these methods can help dermatologists identify prominent skin image features. Further, it can help researchers identify suitable feature extraction methods for images captured from a specific instrument. Being fast, these methods can be deployed for making a quick and effective diagnosis in actual clinic situations", } @InProceedings{ain:2023:GECCOcomp, author = "Qurrat Ul Ain and Harith Al-Sahaf and Bing Xue and Mengjie Zhang", title = "A New Genetic Programming Representation for Feature Learning in Skin Cancer Detection", booktitle = "Proceedings of the 2023 Genetic and Evolutionary Computation Conference", year = "2023", editor = "Sara Silva and Luis Paquete and Leonardo Vanneschi and Nuno Lourenco and Ales Zamuda and Ahmed Kheiri and Arnaud Liefooghe and Bing Xue and Ying Bi and Nelishia Pillay and Irene Moser and Arthur Guijt and Jessica Catarino and Pablo Garcia-Sanchez and Leonardo Trujillo and Carla Silva and Nadarajen Veerapen", pages = "707--710", address = "Lisbon, Portugal", series = "GECCO '23", month = "15-19 " # jul, organisation = "SIGEVO", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, feature learning, feature extraction, melanoma detection, image classification: Poster", isbn13 = "9798400701191", DOI = "doi:10.1145/3583133.3590550", size = "4 pages", abstract = "The process of automatically extracting informative high-level features from skin cancer images is enhanced by integrating well-developed feature descriptors into learning algorithms. This paper develops a new genetic programming-based feature learning approach to automatically select and combine six well-developed descriptors to extract high-level features for skin cancer image classification. The new approach can automatically learn various global features for image classification. The experimental results show that the new approach achieves significantly better classification performance than the baseline approach and six commonly used feature descriptors on two real-world skin image datasets.", notes = "GECCO-2023 A Recombination of the 32nd International Conference on Genetic Algorithms (ICGA) and the 28th Annual Genetic Programming Conference (GP)", } @InProceedings{ain:2023:AusDM, author = "Qurrat Ul Ain and Bing Xue and Harith Al-Sahaf and Mengjie Zhang", title = "Skin Cancer Detection with Multimodal Data: A Feature Selection Approach Using Genetic Programming", booktitle = "Australasian Conference on Data Science and Machine Learning, AusDM 2023", year = "2023", publisher = "Springer", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/chapter/10.1007/978-981-99-8696-5_18", DOI = "doi:10.1007/978-981-99-8696-5_18", notes = "Published in 2024", } @InProceedings{ain:2024:CEC, author = "Qurrat UI Ain and Harith Al-Sahaf and Bing Xue and Mengjie Zhang", title = "Exploring Genetic Programming Models in {Computer-Aided} Diagnosis of Skin Cancer Images", booktitle = "2024 IEEE Congress on Evolutionary Computation (CEC)", year = "2024", editor = "Bing Xue", address = "Yokohama, Japan", month = "30 " # jun # " - 5 " # jul, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Representation learning, Visualization, Computational modeling, Feature extraction, Skin, Lesions, Image Classification, Skin Cancer Detection", isbn13 = "979-8-3503-0837-2", DOI = "doi:10.1109/CEC60901.2024.10612105", abstract = "Extracting important information from complex skin lesion images is vital to effectively distinguish between different types of skin cancer images. In addition to providing high classification performance, such computer-aided diagnostic methods are needed where the models are interpretable and can provide knowledge about the discriminative features in skin lesion images. This underlying information can significantly assist dermatologists in identifying a particular stage or type of cancer. With its flexible representation and global search abilities, Genetic Programming (GP) is an ideal learning al-gorithm to evolve interpretable models and identify important features with significant information to discriminate between skin cancer classes. This paper provides an in-depth analysis of a recent GP-based feature learning method where different well-developed feature descriptors are integrated into the learning algorithms to extract high-level features for skin cancer image classification. The study explores the effectiveness of using feature learning for this complex task and designing program structure to suit the problem domain as it has shown promising results compared to commonly used feature descriptors and an existing GP-based feature learning method developed for general image classification. This study analyses the GP-evolved models to identify the prominent features and most effective feature descriptors important for the classification of these skin cancer images. The evolved models are interpretable, they provide knowledge that can assist dermatologists in making diagnoses in real-time clinical situations by identifying prominent skin cancer characteristics captured by the feature descriptors and learnt during the evolutionary process.", notes = "also known as \cite{10612105} WCCI 2024", } @InProceedings{aiyarak:1997:GPtootn, author = "P. Aiyarak and A. S. Saket and M. C. Sinclair", title = "Genetic Programming Approaches for Minimum Cost Topology Optimisation of Optical Telecommunication Networks", booktitle = "Second International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications, GALESIA", year = "1997", editor = "Ali Zalzala", pages = "415--420", address = "University of Strathclyde, Glasgow, UK", publisher_address = "Savoy Place, London, WC2R 0BL, UK", month = "1-4 " # sep, publisher = "IEE", email = "mcs@essex.ac.uk", keywords = "genetic algorithms, genetic programming, telecommunication networks, topology", ISBN = "0-85296-693-8", URL = "http://uk.geocities.com/markcsinclair/ps/galesia97_aiy.ps.gz", DOI = "doi:10.1049/cp:19971216", size = "6 pages", abstract = "This paper compares the relative efficiency of three approaches for the minimum-cost topology optimisation of the COST 239 European Optical Network (EON) using genetic programming. The GP was run for the central nine nodes using three approaches: relational function set, decision trees, and connected nodes. Only the best two, decision trees and connected nodes, were run for the full EON. The results are also compared with earlier genetic algorithm work on the EON.", notes = "Also known as \cite{681062} GALESIA'97", } @InProceedings{Ajcevic:2013:ISPA, author = "Milos Ajcevic and Andrea {De Lorenzo} and Agostino Accardo and Alberto Bartoli and Eric Medvet", booktitle = "8th International Symposium on Image and Signal Processing and Analysis (ISPA 2013)", title = "A novel estimation methodology for tracheal pressure in mechanical ventilation control", year = "2013", month = "4-6 " # sep, address = "Trieste, Italy", pages = "695--699", keywords = "genetic algorithms, genetic programming, biomechanics, biomedical electronics, biomedical equipment, diseases, injuries, medical control systems, patient treatment, physiological models, air flow pressure, air flow properties, barotrauma, endotracheal tubes, estimation methodology, high-frequency percussive ventilation, mechanical ventilation control, nonconventional mechanical ventilatory strategy, pathological conditions, patient airway, patient treatment, state-of-the-art baseline models, tracheal pressure, ventilator circuit, volutrauma, Electron tubes, Lungs, Physiology, Pressure measurement, Testing, Ventilation", DOI = "doi:10.1109/ISPA.2013.6703827", size = "5 pages", abstract = "High-frequency percussive ventilation (HFPV) is a non-conventional mechanical ventilatory strategy which has proved useful in the treatment of a number of pathological conditions. HFPV usually involves the usage of endotracheal tubes (EET) connecting the ventilator circuit to the airway of the patient. The pressure of the air flow insufflated by HFPV must be controlled very accurately in order to avoid barotrauma and volutrauma. Since the actual tracheal pressure cannot be measured, a model for estimating such a pressure based on the EET properties and on the air flow properties that can actually be measured in clinical practice is necessary. In this work we propose a novel methodology, based on Genetic Programming, for synthesising such a model. We experimentally evaluated our models against the state-of-the-art baseline models, crafted by human experts, and found that our models for estimating tracheal pressure are significantly more accurate.", notes = "Also known as \cite{6703827}", } @PhdThesis{Ajcevic:thesis, author = "Milos Ajcevic", title = "Personalized setup of high frequency percussive ventilator by estimation of respiratory system viscoelastic parameters", school = "Universita degli studi di Trieste", year = "2013/2014", year = "2013", address = "Italy", keywords = "genetic algorithms, genetic programming, High Frequency Percussive Ventilation, Respiratory signal processing, Parameter identification", URL = "http://hdl.handle.net/10077/10976", URL = "https://www.openstarts.units.it/bitstream/10077/10976/1/Ajcevic_PhD.pdf", size = "95 pages", abstract = "High Frequency Percussive Ventilation (HFPV) is a non-conventional ventilatory modality which has proven highly effective in patients with severe gas exchange impairment. However, at the present time, HFPV ventilator provides only airway pressure measurement. The airway pressure measurements and gas exchange analysis are currently the only parameters that guide the physician during the HFPV ventilator setup and treatment monitoring. The evaluation of respiratory system resistance and compliance parameters in patients undergoing mechanical ventilation is used for lung dysfunctions detection, ventilation setup and treatment effect evaluation. Furthermore, the pressure measured by ventilator represents the sum of the endotracheal tube pressure drop and the tracheal pressure. From the clinical point of view, it is very important to take into account the real amount of pressure dissipated by endotracheal tube to avoid lung injury. HFPV is pressure controlled logic ventilation, thus hypoventilation and hyperventilation cases are possible because of tidal volume variations in function of pulmonary and endotracheal tube impedance. This thesis offers a new approach for HFPV ventilator setup in accordance with protective ventilatory strategy and optimization of alveolar recruitment using estimation of the respiratory mechanics parameters and endotracheal pressure drop. Respiratory system resistance and compliance parameters were estimated, firstly in vitro and successively in patients undergoing HFPV, applying least squares regression on Dorkin high frequency model starting from measured respiratory signals. The Blasius model was identified as the most adequate to estimate pressure drop across the endotracheal tube during HFPV. Beside measurement device was developed in order to measure respiratory parameters in patients undergoing HFPV. The possibility to tailor HFPV ventilator setup, using respiratory signals measurement and estimation of respiratory system resistance, compliance and endotracheal tube pressure drop, provided by this thesis, opens a new prospective to this particular ventilatory strategy, improving its beneficial effects and minimizing ventilator-induced lung damage.", notes = "In vitro estimation of tracheal pressure by Genetic programming Supervisor: Agostino Accardo 10077_10976", } @Article{Ajibode:2020:A, author = "Adekunle Akinjobi Ajibode and Ting Shu and Zuohua Ding", title = "Evolving Suspiciousness Metrics From Hybrid Data Set for Boosting a Spectrum Based Fault Localization", journal = "IEEE Access", year = "2020", volume = "8", pages = "198451--198467", keywords = "genetic algorithms, genetic programming, Measurement, Debugging, Boosting, Debugging, fault localization, SBFL", DOI = "doi:10.1109/ACCESS.2020.3035413", ISSN = "2169-3536", abstract = "Spectrum Based Fault Localization (SBFL) uses different metrics called risk evaluation formula to guide and pinpoint faults in debugging process. The accuracy of a specific SBFL method may be limited by the used formulae and program spectra. However, it has been demonstrated recently that Genetic Programming could be used to automatically design formulae directly from the program spectra. Therefore, this article presents Genetic Programming approach for proposing risk evaluation formula with the inclusion of radicals to evolve suspiciousness metric directly from the program spectra. 92 faults from Unix utilities of SIR repository and 357 real faults from Defect4J repository were used. The approach combines these data sets, used 2percent of the total faults (113) to evolve the formulae and the remaining 7percent (336) to validate the effectiveness of the metrics generated by our approach. The proposed approach then uses Genetic Programming to run 30 evolution to produce different 30 metrics. The GP-generated metrics consistently out-performed all the classic formulae in both single and multiple faults, especially OP2 on average of 2.2percent in single faults and 3.4percent in multiple faults. The experiment results conclude that the combination of Hybrid data set and radical is a good technique to evolve effective formulae for spectra-based fault localization.", notes = "Also known as \cite{9247185}", } @InCollection{akalin:2002:DCOFSGGP, author = "Frederick R. Akalin", title = "Developing a Computer-Controller Opponent for a First-Person Simulation Game using Genetic Programming", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 2002", year = "2002", editor = "John R. Koza", pages = "11--20", address = "Stanford, California, 94305-3079 USA", month = jun, publisher = "Stanford Bookstore", keywords = "genetic algorithms, genetic programming", notes = "part of \cite{koza:2002:gagp}", } @Article{akbari-alashti:2015:WRM, author = "Habib Akbari-Alashti and Omid Bozorg Haddad and Miguel A. Marino", title = "Application of Fixed Length Gene Genetic Programming {(FLGGP)} in Hydropower Reservoir Operation", journal = "Water Resources Management", year = "2015", volume = "29", number = "9", keywords = "genetic algorithms, genetic programming", URL = "http://link.springer.com/article/10.1007/s11269-015-1003-1", DOI = "doi:10.1007/s11269-015-1003-1", } @InProceedings{Akbarzadeh:2008:fuzz, author = "Vahab Akbarzadeh and Alireza Sadeghian and Marcus V. {dos Santos}", title = "Derivation of Relational Fuzzy Classification Rules Using Evolutionary Computation", booktitle = "2008 IEEE World Congress on Computational Intelligence", year = "2008", editor = "Jun Wang", pages = "1689--1693", address = "Hong Kong", month = "1-6 " # jun, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", isbn13 = "978-1-4244-1819-0", file = "FS0398.pdf", DOI = "doi:10.1109/FUZZY.2008.4630598", ISSN = "1098-7584", keywords = "genetic algorithms, genetic programming, constrained-syntax genetic programming, evolutionary computation, knowledge-based systems, mutation-based evolutionary algorithm, relational fuzzy classification rules, fuzzy set theory, knowledge based systems", abstract = "An evolutionary system for derivation of fuzzy classification rules is presented. This system uses two populations: one of fuzzy classification rules, and one of membership function definitions. A constrained-syntax genetic programming evolves the first population and a mutation-based evolutionary algorithm evolves the second population. These two populations co-evolve to better classify the underlying dataset. Unlike other approaches that use fuzzification of continuous attributes of the dataset for discovering fuzzy classification rules, the system presented here fuzzifies the relational operators ``greater than'' and ``less than'' using evolutionary methods. For testing our system, the system is applied to the Iris dataset. Our experimental results show that our system outperforms previous evolutionary and non-evolutionary systems on accuracy of classification and derivation of interrelation between the attributes of the Iris dataset. The resulting fuzzy rules of the system can be directly used in knowledge-based systems.", notes = "Also known as \cite{4630598} WCCI 2008 - A joint meeting of the IEEE, the INNS, the EPS and the IET.", } @InProceedings{Akbarzadeh:1997:jce, author = "M.-R. Akbarzadeh-T. and E. Tunstel and M. Jamshidi", title = "Genetic Algorithms and Genetic Programming: Combining Strength in One Evolutionary Strategy", booktitle = "Proceedings of the 1997 WERC/HSRC Joint Conference on the Environment", year = "1997", pages = "373--377", address = "Albuquerque, NM, USA", month = "26-29 " # apr, organisation = "WERC Waste-management Education & Research Consortium New Mexico State University Box 30001, Department WERC Las Cruces, NM 88003-8001, USA HSRC Great Plains/Rocky Mountain Hazardous Substance Research Center Kansas State University 101 Ward Hall Manhattan, KS 66506-2502, USA", keywords = "genetic algorithms, genetic programming", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/Akbarzadeh_1997_jce.pdf", size = "5 pages", abstract = "Genetic Algorithms (GA) and Genetic Programs (GP) are two of the most widely used evolution strategies for parameter optimisation of complex systems. GAs have shown a great deal of success where the representation space is a string of binary or real-valued numbers. At the same time, GP has demonstrated success with symbolic representation spaces and where structure among symbols is explored. This paper discusses weaknesses and strengths of GA and GP in search of a combined and more evolved optimization algorithm. This combination is especially attractive for problem domains with non-homogeneous parameters. In particular, a fuzzy logic membership function is represented by numerical strings, whereas rule-sets are represented by symbols and structural connectives. Two examples are provided which exhibit how GA and GP are best used in optimising robot performance in manipulating hazardous waste. The first example involves optimisation for a fuzzy controller for a flexible robot using GA and the second example illustrates usage of GP in optimizing an intelligent navigation algorithm for a mobile robot. A novel strategy for combining GA and GP is presented.", } @InProceedings{Akbarzadeh:1998:wcci, author = "M. R. Akbarzadeh-T. and E. Tunstel and K. Kumbla and M. Jamshidi", title = "Soft computing paradigms for hybrid fuzzy controllers: experiments and applications", booktitle = "Proceedings of the 1998 IEEE World Congress on Computational Intelligence", year = "1998", pages = "1200--1205", volume = "2", address = "Anchorage, Alaska, USA", month = "5-9 " # may, publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, neurocontrollers, fuzzy control, hierarchical systems, mobile robots, path planning, brushless DC motors, machine control, manipulators, soft computing paradigms, hybrid fuzzy controllers, neural networks, genetic programs, fuzzy logic-based schemes, added intelligence, adaptation, learning ability, direct drive motor, genetic algorithm-fuzzy hierarchical controller, flexible robot link, genetic programming-fuzzy behavior-based controller, mobile robot navigation task", ISBN = "0-7803-4863-X", URL = "http://www-robotics.jpl.nasa.gov/people/Edward_Tunstel/fieee98.pdf", URL = "http://ieeexplore.ieee.org/iel4/5612/15018/00686289.pdf?isNumber=15018", DOI = "doi:10.1109/FUZZY.1998.686289", size = "6 pages", abstract = "Neural networks (NN), genetic algorithms (GA), and genetic programs (GP) are often augmented with fuzzy logic-based schemes to enhance artificial intelligence of a given system. Such hybrid combinations are expected to exhibit added intelligence, adaptation, and learning ability. In the paper, implementation of three hybrid fuzzy controllers are discussed and verified by experimental results. These hybrid controllers consist of a hierarchical NN-fuzzy controller applied to a direct drive motor, a GA-fuzzy hierarchical controller applied to a flexible robot link, and a GP-fuzzy behavior-based controller applied to a mobile robot navigation task. It is experimentally shown that all three architectures are capable of significantly improving the system response.", notes = "ICEC-98 Held In Conjunction With WCCI-98 --- 1998 IEEE World Congress on Computational Intelligence", } @Article{Akbarzadeh-T:2000:CEE, author = "M.-R. Akbarzadeh-T. and K. Kumbla and E. Tunstel and M. Jamshidi", title = "Soft computing for autonomous robotic systems", journal = "Computers and Electrical Engineering", volume = "26", pages = "5--32", year = "2000", number = "1", keywords = "genetic algorithms, genetic programming, Soft computing, Neural networks, Fuzzy logic, Robotic control, Articial intelligence", URL = "http://www.sciencedirect.com/science/article/B6V25-3Y6GXY5-2/1/6a6f9ff946815d4e95fe3884c98e74e5", URL = "http://citeseer.ist.psu.edu/373353.html", size = "28 pages", abstract = "Neural networks (NN), genetic algorithms (GA), and genetic programming (GP) are augmented with fuzzy logic-based schemes to enhance artificial intelligence of automated systems. Such hybrid combinations exhibit added reasoning, adaptation, and learning ability. In this expository article, three dominant hybrid approaches to intelligent control are experimentally applied to address various robotic control issues which are currently under investigation at the NASA Center for Autonomous Control Engineering. The hybrid controllers consist of a hierarchical NN-fuzzy controller applied to a direct drive motor, a GA-fuzzy hierarchical controller applied to position control of a flexible robot link, and a GP-fuzzy behavior based controller applied to a mobile robot navigation task. Various strong characteristics of each of these hybrid combinations are discussed and used in these control architectures. The NN-fuzzy architecture takes advantage of NN for handling complex data patterns, the GA-fuzzy architecture uses the ability of GA to optimize parameters of membership functions for improved system response, and the GP-fuzzy architecture uses the symbolic manipulation capability of GP to evolve fuzzy rule-sets.", notes = "citeseer 373353 version not identical to published version", } @InProceedings{Akbarzadeh:2003:ICNAFIPS, author = "M.-R. Akbarzadeh-T. and I. Mosavat and S. Abbasi", title = "Friendship Modeling for Cooperative Co-Evolutionary Fuzzy Systems: A Hybrid GA-GP Algorithm", booktitle = "Proceedings of the 22nd International Conference of North American Fuzzy Information Processing Society, NAFIPS 2003", year = "2003", pages = "61--66", month = "24-26 " # jul, keywords = "genetic algorithms, genetic programming, Artificial neural networks, Chaos, Computational modelling, Convergence, Evolutionary computation, Fuzzy logic, Fuzzy systems, Genetic programming, Humans, Stochastic processes, cooperative systems, fuzzy systems, groupware, modelling, table lookup, time series, chaotic time series prediction, cooperative co-evolutionary fuzzy systems, friendship modeling, function evaluations, fuzzy lookup tables, hybrid GA-GP algorithm, membership functions, rules sets", DOI = "doi:10.1109/NAFIPS.2003.1226756", size = "6 pages", abstract = "A novel approach is proposed to combine the strengths of GA and GP to optimise rule sets and membership functions of fuzzy systems in a co-evolutionary strategy in order to avoid the problem of dual representation in fuzzy systems. The novelty of proposed algorithm is twofold. One is that GP is used for the structural part (Rule sets) and GA for the string part (Membership functions). The goal is to reduce/eliminate the problem of competing conventions by co-evolving pieces of the problem separately and then in combination. Second is exploiting the synergism between rules sets and membership functions by imitating the effect of 'matching' and friendship in cooperating teams of humans, thereby significantly reducing the number of function evaluations necessary for evolution. The method is applied to a chaotic time series prediction problem and compared with the standard fuzzy table look-up scheme. demonstrate several significant improvements with the proposed approach; specifically, four times higher fitness and more steady fitness improvements as compared with epochal improvements observed in GP.", } @Misc{Akiba:2024:GGP, author = "Takuya Akiba", title = "Evolutionary Optimization of Model Merging Recipes", booktitle = "2nd GECCO workshop on Graph-based Genetic Programming", year = "2024", editor = "Dennis G. Wilson and Roman Kalkreuth and Eric Medvet and Giorgia Nadizar and Giovanni Squillero and Alberto Tonda and Yuri Lavinas", address = "Melbourne", series = "GECCO '24", month = "14 " # jul, organisation = "SIGEVO", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", note = "Invited talk", keywords = "genetic algorithms, genetic programming, ANN, LLM", URL = "https://arxiv.org/abs/2403.13187", URL = "https://sakana.ai/evolutionary-model-merge/", URL = "https://graphgp.com/program/#evolutionary-optimization-of-model-merging-recipes", code_url = "https://github.com/SakanaAI/evolutionary-model-merge", notes = "Abstract only. No paper in GECCO 2024 proceedings. GECCO-2024 A Recombination of the 33rd International Conference on Genetic Algorithms (ICGA) and the 29th Annual Genetic Programming Conference (GP)", } @InProceedings{Akira:1999:AJ, author = "Yoshida Akira", title = "Multiple-Organisms Learning and Evolution by Genetic Programming", booktitle = "Proceedings of The Third Australia-Japan Joint Workshop on Intelligent and Evolutionary Systems", year = "1999", editor = "Bob McKay and Yasuhiro Tsujimura and Ruhul Sarker and Akira Namatame and Xin Yao and Mitsuo Gen", address = "School of Computer Science Australian Defence Force Academy, Canberra, Australia", month = "22-25 " # nov, email = "akira-yo@is.aist-nara.ac.jp", keywords = "genetic algorithms, genetic programming", notes = "Broken Nov 2011 http://www.cs.adfa.edu.au/archive/conference/aj99/programme.html Nara Advanced Institute of Science and Technology http://www.f.ait.kyushu-u.ac.jp/achievements/pub1999.html", } @InProceedings{akira:2000:moelGP, author = "Yoshida Akira", title = "Intraspecific Evolution of Learning by Genetic Programming", booktitle = "Genetic Programming, Proceedings of EuroGP'2000", year = "2000", editor = "Riccardo Poli and Wolfgang Banzhaf and William B. Langdon and Julian F. Miller and Peter Nordin and Terence C. Fogarty", volume = "1802", series = "LNCS", pages = "209--224", address = "Edinburgh", publisher_address = "Berlin", month = "15-16 " # apr, organisation = "EvoNet", publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming: Poster", ISBN = "3-540-67339-3", DOI = "doi:10.1007/978-3-540-46239-2_15", abstract = "Spatial dynamic pattern formations or trails can be observed in a simple square world where individuals move to look for scattered foods. They seem to show the emergence of co-operation, job separation, or division of territories when genetic programming controls the reproduction, mutation, crossing over of the organisms. We try to explain the co-operative behaviours among multiple organisms by means of density of organisms and their environment. Next, we add some interactions between organisms, and between organism and their environment to see that the more interaction make the convergence of intraspecific learning faster. At last, we study that MDL-based fitness evaluation is effective for improvement of generalisation of genetic programming.", notes = "EuroGP'2000, part of \cite{poli:2000:GP}", } @Article{journals/ijossp/AkourM17, title = "Software Defect Prediction Using Genetic Programming and Neural Networks", author = "Mohammed Akour and Wasen Yahya Melhem", journal = "International Journal of Open Source Software and Processes", year = "2017", number = "4", volume = "8", pages = "32--51", keywords = "genetic algorithms, genetic programming, ANN, SBSE", ISSN = "1942-3926", DOI = "doi:10.4018/IJOSSP.2017100102", abstract = "This article describes how classification methods on software defect prediction is widely researched due to the need to increase the software quality and decrease testing efforts. However, findings of past researches done on this issue has not shown any classifier which proves to be superior to the other. Additionally, there is a lack of research that studies the effects and accuracy of genetic programming on software defect prediction. To find solutions for this problem, a comparative software defect prediction experiment between genetic programming and neural networks are performed on four datasets from the NASA Metrics Data repository. Generally, an interesting degree of accuracy is detected, which shows how the metric-based classification is useful. Nevertheless, this article specifies that the application and usage of genetic programming is highly recommended due to the detailed analysis it provides, as well as an important feature in this classification method which allows the viewing of each attributes impact in the dataset.", notes = "Mohammed Akour (Department of Computer Information Systems, Yarmouk University, Irbid, Jordan) and Wasen Yahya Melhem (Yarmouk university, Irbid, Jordan)", } @Article{Al-Saati:2014:mosul, author = "Najla Akram Al-Saati and Taghreed Riyadh Alreffaee", title = "Software Effort Estimation Using Multi Expression Programming", journal = "AL-Rafidain Journal of Computer Sciences and Mathematics", year = "2014", volume = "11", number = "2", pages = "53--71", keywords = "genetic algorithms, genetic programming, Effort Estimation, Multi Expression Programming", publisher = "Mosul University", ISSN = "1815-4816", eissn = "2311-7990", URL = "https://csmj.mosuljournals.com/article_163756.html", URL = "https://csmj.mosuljournals.com/article__2d593a444328ad02601f0d083038e400163756.pdf", DOI = "doi:10.33899/csmj.2014.163756", size = "19 pages", abstract = "The process of finding a function that can estimate the effort of software systems is considered to be the most important and most complex process facing systems developers in the field of software engineering. The accuracy of estimating software effort forms an essential part of the software development phases. A lot of experts applied different ways to find solutions to this issue, such as the COCOMO and other methods. Recently, many questions have been put forward about the possibility of using Artificial Intelligence to solve such problems, different scientists made ​​several studies about the use of techniques such as Genetic Algorithms and Artificial Neural Networks to solve estimation problems. We use one of the Linear Genetic Programming methods (Multi Expression programming) which apply the principle of competition between equations encrypted within the chromosomes to find the best formula for resolving the issue of software effort estimation. As for to the test data, benchmark known datasets are employed taken from previous projects, the results are evaluated by comparing them with the results of Genetic Programming (GP) using different fitness functions. The gained results indicate the surpassing of the employed method in finding more efficient functions for estimating about 7 datasets each consisting of many projects.", notes = "In Arabic", } @Article{Akram:2017:ijrr, author = "Najla Akram AL-Saati and Taghreed Riyadh Alreffaee", title = "Using Multi Expression Programming in Software Effort Estimation", journal = "International Journal of Recent Research and Review", year = "2017", volume = "X", number = "2", pages = "1--10", month = jun, keywords = "genetic algorithms, genetic programming, Multi Expression Programming, SBSE, Software Effort, Estimation, Software Engineering", ISSN = "2277-8322", URL = "http://www.ijrrr.com/papers10-2/paper1-Using%20Multi%20Expression%20Programming%20in%20Software%20Effort%20Estimation.pdf", URL = "http://www.ijrrr.com/issues10-2.htm", size = "10 pages", abstract = "Estimating the effort of software systems is an essential topic in software engineering, carrying out an estimation process reliably and accurately for a software forms a vital part of the software development phases. Many researchers have used different methods and techniques hopping to find solutions to this issue, such techniques include COCOMO, SEER-SEM,SLIM and others. Recently, Artificial Intelligent techniques are being used to solve such problems; different studies have been issued focusing on techniques such as Neural Networks NN, Genetic Algorithms GA, and Genetic Programming GP. This work uses one of the linear variations of GP, namely: Multi Expression Programming (MEP) aiming to find the equation that best estimates the effort of software. Benchmark datasets (based on previous projects) are used learning and testing. Results are compared with those obtained by GP using different fitness functions. Results show that MEP is far better in discovering effective functions for the estimation of about 6 datasets each comprising several projects.", notes = "See also \cite{Akram:2018:arxiv}", } @Misc{Akram:2018:arxiv, author = "Najla Akram Al-Saati and Taghreed Riyadh Alreffaee", title = "Using Multi Expression Programming in Software Effort Estimation", howpublished = "arXiv", year = "2018", month = "30 " # apr, keywords = "genetic algorithms, genetic programming, SBSE, ANN, software effort, estimation, multi expression programming", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/corr/corr1805.html#abs-1805-00090", URL = "http://arxiv.org/abs/1805.00090", size = "10 pages", abstract = "Estimating the effort of software systems is an essential topic in software engineering, carrying out an estimation process reliably and accurately for a software forms a vital part of the software development phases. Many researchers have used different methods and techniques hopping to find solutions to this issue, such techniques include COCOMO, SEER-SEM,SLIM and others. Recently, Artificial Intelligent techniques are being used to solve such problems; different studies have been issued focusing on techniques such as Neural Networks NN, Genetic Algorithms GA, and Genetic Programming GP. This work uses one of the linear variations of GP, namely: Multi Expression Programming (MEP) aiming to find the equation that best estimates the effort of software. Benchmark datasets (based on previous projects) are used learning and testing. Results are compared with those obtained by GP using different fitness functions. Results show that MEP is far better in discovering effective functions for the estimation of about 6 datasets each comprising several projects.", notes = "Published as International Journal of Recent Research and Review, Vol. X, Issue 2, June 2017 ISSN 2277-8322 \cite{Akram:2017:ijrr}. journals/corr/abs-1805-00090", } @Article{Aksu:2012:AAPS, author = "Buket Aksu and Anant Paradkar and Marcel Matas and Ozgen Ozer and Tamer Guneri and Peter York", title = "Quality by Design Approach: Application of Artificial Intelligence Techniques of Tablets Manufactured by Direct Compression", journal = "AAPS PharmSciTech", year = "2012", volume = "13", number = "4", pages = "1138--1146", month = sep # "~06", keywords = "genetic algorithms, genetic programming, gene expression programming, artificial neural networks, ANNs, GEP, optimisation, quality by design (qbd)", DOI = "doi:10.1208/s12249-012-9836-x", URL = "http://dx.doi.org/10.1208/s12249-012-9836-x", URL = "http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3513460", URL = "http://www.ncbi.nlm.nih.gov/pubmed/22956056", language = "English", bibsource = "OAI-PMH server at www.ncbi.nlm.nih.gov", oai = "oai:pubmedcentral.nih.gov:3513460", publisher = "American Association of Pharmaceutical Scientists", abstract = "The publication of the International Conference of Harmonization (ICH) Q8, Q9, and Q10 guidelines paved the way for the standardization of quality after the Food and Drug Administration issued current Good Manufacturing Practices guidelines in 2003. Quality by Design, mentioned in the ICH Q8 guideline, offers a better scientific understanding of critical process and product qualities using knowledge obtained during the life cycle of a product. In this scope, the knowledge space is a summary of all process knowledge obtained during product development, and the design space is the area in which a product can be manufactured within acceptable limits. To create the spaces, artificial neural networks (ANNs) can be used to emphasise the multidimensional interactions of input variables and to closely bind these variables to a design space. This helps guide the experimental design process to include interactions among the input variables, along with modelling and optimisation of pharmaceutical formulations. The objective of this study was to develop an integrated multivariate approach to obtain a quality product based on an understanding of the cause--effect relationships between formulation ingredients and product properties with ANNs and genetic programming on the ramipril tablets prepared by the direct compression method. In this study, the data are generated through the systematic application of the design of experiments (DoE) principles and optimisation studies using artificial neural networks and neurofuzzy logic programs.", } @InProceedings{conf/ecsqaru/AkyolYE07, title = "A Genetic Programming Classifier Design Approach for Cell Images", author = "Aydin Akyol and Yusuf Yaslan and Osman Kaan Erol", booktitle = "Proceedings of the 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU", bibdate = "2007-09-17", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/ecsqaru/ecsqaru2007.html#AkyolYE07", publisher = "Springer", year = "2007", volume = "4724", editor = "Khaled Mellouli", isbn13 = "978-3-540-75255-4", pages = "878--888", series = "Lecture Notes in Computer Science", address = "Hammamet, Tunisia", month = oct # " 31 - " # nov # " 2", keywords = "genetic algorithms, genetic programming, cell classification, classifier design, pollen classification", DOI = "doi:10.1007/978-3-540-75256-1_76", abstract = "This paper describes an approach for the use of genetic programming (GP) in classification problems and it is evaluated on the automatic classification problem of pollen cell images. In this work, a new reproduction scheme and a new fitness evaluation scheme are proposed as advanced techniques for GP classification applications. Also an effective set of pollen cell image features is defined for cell images. Experiments were performed on Bangor/Aberystwyth Pollen Image Database and the algorithm is evaluated on challenging test configurations. We reached at 96percent success rate on the average together with significant improvement in the speed of convergence.", notes = "cf email GP mailing list Mon, 24 Dec 2007 13:42:59 +0200 You may find MATLAB codes from my Web Page below: www3.itu.edu.tr/~okerol you may refer to: O.K. Erol, I.Eksin, 2006. A New Optimization Method: Big-Bang Big-Crunch, Advences in Engineering Software, Elsevier, Vol 37, No.2, 106-111 doi:10.1016/j.advengsoft.2005.04.005", } @Article{al-afandi:2021:Algorithms, author = "Jalal Al-Afandi and Andras Horvath", title = "Adaptive Gene Level Mutation", journal = "Algorithms", year = "2021", volume = "14", number = "1", keywords = "genetic algorithms, genetic programming", ISSN = "1999-4893", URL = "https://www.mdpi.com/1999-4893/14/1/16", DOI = "doi:10.3390/a14010016", abstract = "Genetic Algorithms are stochastic optimisation methods where solution candidates, complying to a specific problem representation, are evaluated according to a predefined fitness function. These approaches can provide solutions in various tasks even, where analytic solutions can not be or are too complex to be computed. In this paper we will show, how certain set of problems are partially solvable allowing us to grade segments of a solution individually, which results local and individual tuning of mutation parameters for genes. We will demonstrate the efficiency of our method on the N-Queens and travelling salesman problems where we can demonstrate that our approach always results faster convergence and in most cases a lower error than the traditional approach.", notes = "also known as \cite{a14010016}", } @MastersThesis{Al-Afeef:mastersthesis, author = "Ala' S. Al-Afeef", title = "Image Reconstructing in Electrical Capacitance Tomography of Manufacturing Processes Using Genetic Programming", school = "Al-Balqa Applied University", year = "2010", address = "Al-Salt, Jordan", month = jul, email = "alaa.afeef@gmail.com", keywords = "genetic algorithms, genetic programming, Image Reconstructing, Electrical Capacitance Tomography", URL = "https://sites.google.com/site/alaaalfeef/home/Alaa_afeef_Thesis_Final.pdf", size = "137", abstract = "Electrical capacitance tomography is considered the most attractive technique for industrial process imaging because of its low construction cost, safety, fast data acquisition , non-invasiveness, non-intrusiveness, simple structure, wide application field and suitability for most kinds of flask and vessels, however, the low accuracy of the reconstructed images is the main limitation of implementing an ECT system. In order to improve the imaging accuracy, one may 1) increase the number of measurements by raising number of electrodes, 2) improve the reconstruction algorithm so that more information can be extracted from the captured data, however, increasing the number of electrodes has a limited impact on the imaging accuracy improvement. This means that, in order to improve the reconstructed image, more accurate reconstruction algorithms must be developed. In fact, ECT image reconstruction is still an inefficiently resolved problem because of many limitations, mainly the Soft-field and Ill-condition characteristic of ECT. Although there are many algorithms to solve the image reconstruction problem, these algorithms are not yet able to present a single model that can relate between image pixels and capacitance measurements in a mathematical relationship. The originality of this thesis lies in introducing a new technique for solving the non-linear inverse problem in ECT based on Genetic Programming (GP) to handle the ECT imaging for conductive materials. GP is a technique that has not been applied to ECT. GP found to be efficient in dealing with the Non-linear relation between the measured capacitance and permittivity distribution in ECT. This thesis provides new implemented software that can handle the ECT based GP problem with a user-friendly interface. The developed simulation results are promising.", } @InProceedings{Al-Afeef:2010:ISDA, author = "Alaa Al-Afeef and Alaa F. Sheta and Adnan Al-Rabea", title = "Image reconstruction of a metal fill industrial process using Genetic Programming", booktitle = "10th International Conference on Intelligent Systems Design and Applications (ISDA), 2010", year = "2010", pages = "12--17", address = "Cairo", month = "29 " # nov # "-1 " # dec, email = "alaa.afeef@gmail.com", keywords = "genetic algorithms, genetic programming, electrical capacitance tomography, ill-condition characteristic, image reconstruction, industrial process imaging, metal fill industrial process, soft-field characteristic, image reconstruction, industrial engineering, tomography, Process Tomography", isbn13 = "978-1-4244-8134-7", URL = "http://sites.google.com/site/alaaalfeef/home/8.pdf", DOI = "doi:10.1109/ISDA.2010.5687299", size = "6 pages", abstract = "Electrical Capacitance Tomography (ECT) is one of the most attractive technique for industrial process imaging because of its low construction cost, safety, non-invasiveness, non-intrusiveness, fast data acquisition, simple structure, wide application field and suitability for most kinds of flask and vessels. However, image reconstruction based ECT suffers many limitations. They include the Soft-field and Ill-condition characteristic of ECT. The basic idea of the ECT for image reconstruction for a metal fill problem is to model the image pixels as a function of the capacitance measurements. Developing this relationship represents a challenge for systems engineering community. In this paper, we presents our innovative idea on solving the non-linear inverse problem for conductive materials of the ECT using Genetic Programming (GP). GP found to be a very efficient algorithm in producing a mathematical model of image pixels in the form of Lisp expression. The reported results are promising.", notes = "Also known as \cite{5687299}", } @Book{AfeefBook2011, author = "Alaa Al-Afeef and Alaa Sheta and Adnan Rabea", title = "Image Reconstruction of a Manufacturing Process: A Genetic Programming Approach", publisher = "Lambert Academic Publishing", year = "2011", edition = "1", month = apr, keywords = "genetic algorithms, genetic programming", isbn13 = "978-3844325690", URL = "https://www.morebooks.de/store/gb/book/image-reconstruction-of-a-manufacturing-process/isbn/978-3-8443-2569-0", URL = "http://www.amazon.co.uk/Image-Reconstruction-Manufacturing-Process-Programming/dp/3844325697", abstract = "Product Description Evolutionary Computation (EC) is one of the most attractive techniques in the area of Computer Science. EC includes Genetic Algorithms (GAs), Genetic Programming (GP), Evolutionary Strategy (ES) and Evolutionary Programming (EP). GP have been widely used to solve a variety of problems in image enhancement, analysis and segmentation. This book explores the use of GP as a powerful approach to solve the image reconstruction problem for Lost Foam Casting (LFC) manufacturing process. The data set was collected using the Electrical Capacitance Tomography (ECT) technique. ECT is one of the most attractive technique for industrial process imaging because of its low construction cost, safety, non-invasiveness, non-intrusiveness, fast data acquisition, simple structure, wide application field and suitability for most kinds of flask and vessels. GP found to be a very efficient algorithm in producing a mathematical model of image pixels in a form of Lisp expression. A Graphical User Interface (GUI) Toolbox based Matlab was developed to help analysing and visualising the reconstructed images based GP problem. The reported results are promising.", size = "100 pages", } @Article{Al-Bastaki:2010:JAI, title = "{GADS} and Reusability", author = "Y. Al-Bastaki and W. Awad", year = "2010", journal = "Journal of Artificial Intelligence", volume = "3", number = "2", pages = "67--77", keywords = "genetic algorithms, genetic programming, GADS, reusability", URL = "http://docsdrive.com/pdfs/ansinet/jai/2010/67-72.pdf", broken = "http://www.doaj.org/doaj?func=openurl\&genre=article\&issn=19945450\&date=2010\&volume=3\&issue=2\&spage=67", ISSN = "19945450", bibsource = "OAI-PMH server at www.doaj.org", language = "eng", oai = "oai:doaj-articles:8a4dfe5674530875df3b83ea84856118", publisher = "Asian Network for Scientific Information", size = "6 pages", abstract = "Genetic programming is a domain-independent method that genetically breeds population of computer programs to solve problems. Genetic programming is considered to be a machine learning technique used to optimise a population of computer programs according to a fitness landscape determined by a program's ability to perform a given computational task. There are a number of representation methods to illustrate these programs, such as LISP expressions and integer lists. This study investigated the effectiveness of genetic programming in solving the symbolic regression problem where, the population programs are expressed as integer sequences rather than lisp expressions. This study also introduced the concept of reusable program to genetic algorithm for developing software.", notes = "BNF grammar, ADF, linear GP", } @InProceedings{Al-Hajj:2016:ICRERA, author = "Rami Al-Hajj and Ali Assi and Farhan Batch", booktitle = "2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA)", title = "An evolutionary computing approach for estimating global solar radiation", year = "2016", pages = "285--290", month = "20-23 " # nov, address = "Birmingham, UK", keywords = "genetic algorithms, genetic programming, Decision support systems, Evolutionary computation, Hand-held computers, climatological data, evolutionary computation, global solar radiation", DOI = "doi:10.1109/ICRERA.2016.7884553", abstract = "This paper presents a non-linear regression model based on an evolutionary computing technique namely the genetic programming for estimating solar radiation. This approach aims to estimate the best formula that represents the function for estimating the global solar radiation on horizontals with respect to the measured climatological data. First, we present a reference approach to find one global formula that models the relation among the solar radiation amount and a set of weather factors. In the second step, we present an enhanced approach that consists of multi formulas of regression in a parallel structure. The performance of the proposed approaches has been evaluated using statistical analysis measures. The obtained results were promising and comparable to those obtained by other empirical and neural models conducted by other research groups.", notes = "Also known as \cite{7884553}", } @Article{al-hajj:2021:Processes, author = "Rami Al-Hajj and Ali Assi and Mohamad Fouad and Emad Mabrouk", title = "A Hybrid {LSTM-Based} Genetic Programming Approach for {Short-Term} Prediction of Global Solar Radiation Using Weather Data", journal = "Processes", year = "2021", volume = "9", number = "7", keywords = "genetic algorithms, genetic programming", ISSN = "2227-9717", URL = "https://www.mdpi.com/2227-9717/9/7/1187", DOI = "doi:10.3390/pr9071187", abstract = "The integration of solar energy in smart grids and other utilities is continuously increasing due to its economic and environmental benefits. However, the uncertainty of available solar energy creates challenges regarding the stability of the generated power the supply-demand balance's consistency. An accurate global solar radiation (GSR) prediction model can ensure overall system reliability and power generation scheduling. This article describes a nonlinear hybrid model based on Long Short-Term Memory (LSTM) models and the Genetic Programming technique for short-term prediction of global solar radiation. The LSTMs are Recurrent Neural Network (RNN) models that are successfully used to predict time-series data. We use these models as base predictors of GSR using weather and solar radiation (SR) data. Genetic programming (GP) is an evolutionary heuristic computing technique that enables automatic search for complex solution formulas. We use the GP in a post-processing stage to combine the LSTM models' outputs to find the best prediction of the GSR. We have examined two versions of the GP in the proposed model: a standard version and a boosted version that incorporates a local search technique. We have shown an improvement in terms of performance provided by the proposed hybrid model. We have compared its performance to stacking techniques based on machine learning for combination. The results show that the suggested method provides significant improvement in terms of performance and consistency.", notes = "also known as \cite{pr9071187}", } @InProceedings{DBLP:conf/acpr/Al-HelaliCXZ19, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", editor = "Shivakumara Palaiahnakote and Gabriella Sanniti di Baja and Liang Wang and Wei Qi Yan", title = "Genetic Programming-Based Simultaneous Feature Selection and Imputation for Symbolic Regression with Incomplete Data", booktitle = "Pattern Recognition - 5th Asian Conference, {ACPR} 2019, Auckland, New Zealand, November 26-29, 2019, Revised Selected Papers, Part {II}", series = "Lecture Notes in Computer Science", volume = "12047", pages = "566--579", publisher = "Springer", year = "2019", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.1007/978-3-030-41299-9_44", DOI = "doi:10.1007/978-3-030-41299-9_44", timestamp = "Mon, 24 Feb 2020 18:06:33 +0100", biburl = "https://dblp.org/rec/conf/acpr/Al-HelaliCXZ19.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @InProceedings{DBLP:conf/ausai/Al-Helali00Z19, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", editor = "Jixue Liu and James Bailey", title = "Genetic Programming for Imputation Predictor Selection and Ranking in Symbolic Regression with High-Dimensional Incomplete Data", booktitle = "{AI} 2019: Advances in Artificial Intelligence - 32nd Australasian Joint Conference, Adelaide, SA, Australia, December 2-5, 2019, Proceedings", series = "Lecture Notes in Computer Science", volume = "11919", pages = "523--535", publisher = "Springer", year = "2019", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.1007/978-3-030-35288-2_42", DOI = "doi:10.1007/978-3-030-35288-2_42", timestamp = "Mon, 25 Nov 2019 16:31:45 +0100", biburl = "https://dblp.org/rec/conf/ausai/Al-Helali00Z19.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @InProceedings{Al-Helali:2019:SSCI, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", booktitle = "2019 IEEE Symposium Series on Computational Intelligence (SSCI)", title = "A Genetic Programming-based Wrapper Imputation Method for Symbolic Regression with Incomplete Data", year = "2019", pages = "2395--2402", month = dec, keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/SSCI44817.2019.9002861", abstract = "Dealing with missing values is one of the challenges in symbolic regression on many real-world data sets. One of the popular approaches to address this challenge is to use imputation. Traditional imputation methods are usually performed based on the predictive features without considering the original target variable. In this work, a genetic programming-based wrapper imputation method is proposed, which wrappers a regression method to consider the target variable when constructing imputation models for the incomplete features. In addition to the imputation performance, the regression performance is considered for evaluating the imputation models. Genetic programming (GP) is used for building the imputation models and decision tree (DT) is used for evaluating the regression performance during the GP evolutionary process. The experimental results show that the proposed method has a significant advance in enhancing the symbolic regression performance compared with some state-of- the-art imputation methods.", notes = "Also known as \cite{9002861}", } @InProceedings{Al-Helali:2020:SSCI, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Data Imputation for Symbolic Regression with Missing Values: A Comparative Study", booktitle = "2020 IEEE Symposium Series on Computational Intelligence (SSCI)", year = "2020", pages = "2093--2100", abstract = "Symbolic regression via genetic programming is considered as a crucial machine learning tool for empirical modelling. However, in reality, it is common for real-world data sets to have some data quality problems such as noise, outliers, and missing values. Although several approaches can be adopted to deal with data incompleteness in machine learning, most studies consider the classification tasks, and only a few have considered symbolic regression with missing values. In this work, the performance of symbolic regression using genetic programming on real-world data sets that have missing values is investigated. This is done by studying how different imputation methods affect symbolic regression performance. The experiments are conducted using thirteen real-world incomplete data sets with different ratios of missing values. The experimental results show that although the performance of the imputation methods differs with the data set, CART has a better effect than others. This might be due to its ability to deal with categorical and numerical variables. Moreover, the superiority of the use of imputation methods over the commonly used deletion strategy is observed.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/SSCI47803.2020.9308216", month = dec, notes = "Also known as \cite{9308216}", } @InProceedings{Al-Helali:2020:EuroGP, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Hessian Complexity Measure for Genetic Programming-based Imputation Predictor Selection in Symbolic Regression with Incomplete Data", booktitle = "EuroGP 2020: Proceedings of the 23rd European Conference on Genetic Programming", year = "2020", month = "15-17 " # apr, editor = "Ting Hu and Nuno Lourenco and Eric Medvet", series = "LNCS", volume = "12101", publisher = "Springer Verlag", address = "Seville, Spain", pages = "1--17", organisation = "EvoStar, Species", keywords = "genetic algorithms, genetic programming, Symbolic regression, Incomplete data, Feature selection, Imputation, Model complexity", isbn13 = "978-3-030-44093-0", video_url = "https://www.youtube.com/watch?v=zeZvFJElkBM", DOI = "doi:10.1007/978-3-030-44094-7_1", abstract = "Missing values bring several challenges when learning from real-world data sets. Imputation is a widely adopted approach to estimating missing values. However, it has not been adequately investigated in symbolic regression. When imputing the missing values in an incomplete feature, the other features that are used in the prediction process are called imputation predictors. In this work, a method for imputation predictor selection using regularized genetic programming (GP) models is presented for symbolic regression tasks on incomplete data. A complexity measure based on the Hessian matrix of the phenotype of the evolving models is proposed. It is employed as a regularizer in the fitness function of GP for model selection and the imputation predictors are selected from the selected models. In addition to the baseline which uses all the available predictors, the proposed selection method is compared with two GP-based feature selection variations: the standard GP feature selector and GP with feature selection pressure. The trends in the results reveal that in most cases, using the predictors selected by regularized GP models could achieve a considerable reduction in the imputation error and improve the symbolic regression performance as well.", notes = "fitness = error + lamda * complexity. (Lamda fixed linear weighting) Model complexity based on second order partial derivaties (not tree size). Form n by n Hessian matrix, where n is number of inputs (terminal set size). Each element is 2nd order partial dertivative of GP tree with respect to input i and input j. Hessian is symetric matrix. Matrix C is Hessian with all constant terms set to zero. Complexity = determinant of C divided by the determinant of H. (calculated with python package SymPy). Division replaced by analytic quotiant \cite{Ni:2012:ieeeTEC}. Data missing at random. Five OpenML benchmarks. Compare python DEAP with Linear Regression, PMM, KNN (R package Simpulation). http://www.evostar.org/2020/cfp_eurogp.php Part of \cite{Hu:2020:GP} EuroGP'2020 held in conjunction with EvoCOP2020, EvoMusArt2020 and EvoApplications2020", } @InProceedings{Al-Helali:2020:CEC, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Genetic Programming with Noise Sensitivity for Imputation Predictor Selection in Symbolic Regression with Incomplete Data", booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC 2020", year = "2020", editor = "Yaochu Jin", pages = "paper id24344", address = "internet", month = "19-24 " # jul, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-7281-6929-3", DOI = "doi:10.1109/CEC48606.2020.9185526", abstract = "This paper presents a feature selection method that incorporates a sensitivity-based single feature importance measure in a context-based feature selection approach. The single-wise importance is based on the sensitivity of the learning performance with respect to adding noise to the predictive features. Genetic programming is used as a context-based selection mechanism, where the selection of features is determined by the change in the performance of the evolved genetic programming models when the feature is injected with noise. Imputation is a key strategy to mitigate the data incompleteness problem. However, it has been rarely investigated for symbolic regression on incomplete data. In this work, an attempt to contribute to filling this gap is presented. The proposed method is applied to selecting imputation predictors (features/variables) in symbolic regression with missing values. The evaluation is performed on real-world data sets considering three performance measures: imputation accuracy, symbolic regression performance, and features' reduction ability. Compared with the benchmark methods, the experimental evaluation shows that the proposed method can achieve an enhanced imputation, improve the symbolic regression performance, and use smaller sets of selected predictors.", notes = "https://wcci2020.org/ Victoria University of Wellington, New Zealand. Also known as \cite{9185526}", } @InProceedings{Al-Helali:2020:CEC2, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Multi-Tree Genetic Programming-based Transformation for Transfer Learning in Symbolic Regression with Highly Incomplete Data", booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC 2020", year = "2020", editor = "Yaochu Jin", pages = "paper id24250", address = "internet", month = "19-24 " # jul, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-7281-6929-3", DOI = "doi:10.1109/CEC48606.2020.9185670", abstract = "Transfer learning has been considered a key solution for the problem of learning when there is a lack of knowledge in some target domains. Its idea is to benefit from the learning on different (but related in some way) domains that have adequate knowledge and transfer what can improve the learning in the target domains. Although incompleteness is one of the main causes of knowledge shortage in many machine learning real-world tasks, it has received a little effort to be addressed by transfer learning. In particular, to the best of our knowledge, there is no single study to use transfer learning for the symbolic regression task when the underlying data are incomplete. The current work addresses this point by presenting a transfer learning method for symbolic regression on data with high ratios of missing values. A multi-tree genetic programming algorithm based feature-based transformation is proposed for transferring data from a complete source domain to a different, incomplete target domain. The experimental work has been conducted on real-world data sets considering different transfer learning scenarios each is determined based on three factors: missingness ratio, domain difference, and task similarity. In most cases, the proposed method achieved positive transductive transfer learning in both homogeneous and heterogeneous domains. Moreover, even with less significant success, the obtained results show the applicability of the proposed approach for inductive transfer learning.", notes = "https://wcci2020.org/ Victoria University of Wellington, New Zealand", } @InProceedings{Al-Helali:2020:GECCO, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Multi-Tree Genetic Programming for Feature Construction-Based Domain Adaptation in Symbolic Regression with Incomplete Data", year = "2020", editor = "Carlos Artemio {Coello Coello} and Arturo Hernandez Aguirre and Josu Ceberio Uribe and Mario Garza Fabre and Gregorio {Toscano Pulido} and Katya Rodriguez-Vazquez and Elizabeth Wanner and Nadarajen Veerapen and Efren Mezura Montes and Richard Allmendinger and Hugo Terashima Marin and Markus Wagner and Thomas Bartz-Beielstein and Bogdan Filipic and Heike Trautmann and Ke Tang and John Koza and Erik Goodman and William B. Langdon and Miguel Nicolau and Christine Zarges and Vanessa Volz and Tea Tusar and Boris Naujoks and Peter A. N. Bosman and Darrell Whitley and Christine Solnon and Marde Helbig and Stephane Doncieux and Dennis G. Wilson and Francisco {Fernandez de Vega} and Luis Paquete and Francisco Chicano and Bing Xue and Jaume Bacardit and Sanaz Mostaghim and Jonathan Fieldsend and Oliver Schuetze and Dirk Arnold and Gabriela Ochoa and Carlos Segura and Carlos Cotta and Michael Emmerich and Mengjie Zhang and Robin Purshouse and Tapabrata Ray and Justyna Petke and Fuyuki Ishikawa and Johannes Lengler and Frank Neumann", isbn13 = "9781450371285", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", URL = "https://doi.org/10.1145/3377930.3390160", DOI = "doi:10.1145/3377930.3390160", booktitle = "Proceedings of the 2020 Genetic and Evolutionary Computation Conference", pages = "913--921", size = "9 pages", keywords = "genetic algorithms, genetic programming, transfer tearning, incomplete data, symbolic regression", address = "internet", series = "GECCO '20", month = jul # " 8-12", organisation = "SIGEVO", abstract = "Nowadays, transfer learning has gained a rapid popularity in tasks with limited data available. While traditional learning limits the learning process to knowledge available in a specific (target) domain, transfer learning can use parts of knowledge extracted from learning in a different (source) domain to help learning in the target domain. This concept is of special importance when there is a lack of knowledge in the target domain. Consequently, since data incompleteness is a serious cause of knowledge shortage in real-world learning tasks, it can be typically addressed using transfer learning. One way to achieve that is feature construction-based domain adaptation. However, although it is considered as a powerful feature construction algorithm, Genetic Programming has not been fully for domain adaptation. In this work, a multi-tree genetic programming method is proposed for feature construction-based domain adaptation. The main idea is to construct a transformation from the source feature space to the target feature space, which maps the source domain close to the target domain. This method is used for symbolic regression with missing values. The experimental work shows encouraging potential of the proposed approach when applied to real-world tasks considering different transfer learning scenarios.", notes = "Nominated for Best Paper. multi-tree GP. R packages. Missing data created randomly. Also known as \cite{10.1145/3377930.3390160} GECCO-2020 A Recombination of the 29th International Conference on Genetic Algorithms (ICGA) and the 25th Annual Genetic Programming Conference (GP)", } @Article{DBLP:journals/soco/Al-Helali00021, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "A new imputation method based on genetic programming and weighted {KNN} for symbolic regression with incomplete data", journal = "Soft Computing", volume = "25", number = "8", pages = "5993--6012", year = "2021", month = apr, keywords = "genetic algorithms, genetic programming, Symbolic regression, Incomplete data, KNN, Imputation", ISSN = "1432-7643", URL = "https://doi.org/10.1007/s00500-021-05590-y", DOI = "doi:10.1007/s00500-021-05590-y", timestamp = "Wed, 07 Apr 2021 01:00:00 +0200", biburl = "https://dblp.org/rec/journals/soco/Al-Helali00021.bib", bibsource = "dblp computer science bibliography, https://dblp.org", abstract = "Incompleteness is one of the problematic data quality challenges in real-world machine learning tasks. A large number of studies have been conducted for addressing this challenge. However, most of the existing studies focus on the classification task and only a limited number of studies for symbolic regression with missing values exist. a new imputation method for symbolic regression with incomplete data is proposed. The method aims to improve both the effectiveness and efficiency of imputing missing values for symbolic regression. This method is based on genetic programming (GP) and weighted K-nearest neighbors (KNN). It constructs GP-based models using other available features to predict the missing values of incomplete features. The instances used for constructing such models are selected using weighted KNN. The experimental results on real-world data sets show that the proposed method outperforms a number of state-of-the-art methods with respect to the imputation accuracy, the symbolic regression performance, and the imputation time.", } @Article{Al-Helali:ieeeTEC, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", title = "Multi-Tree Genetic Programming with New Operators for Transfer Learning in Symbolic Regression with Incomplete Data", journal = "IEEE Transactions on Evolutionary Computation", year = "2021", volume = "25", number = "6", pages = "1049--1063", month = dec, keywords = "genetic algorithms, genetic programming, Symbolic Regression, Incomplete Data, Transfer Learning, Evolutionary Learning", ISSN = "1089-778X", DOI = "doi:10.1109/TEVC.2021.3079843", size = "15 pages", abstract = "Lack of knowledge is a common consequence of data incompleteness when learning from real-world data. To deal with such a situation, this work uses transfer learning to re-use knowledge from different (yet related) but complete domains. Due to its powerful feature construction ability, genetic programming is used to construct feature-based transformations that map the feature space of the source domain to that of the target domain such that their differences are reduced. Particularly, this work proposes a new multi-tree genetic programming-based feature construction approach to transfer learning in symbolic regression with missing values. It transfers knowledge related to the importance of the features and instances in the source domain to the target domain to improve the learning performance. Moreover, new genetic operators are developed to encourage minimising the distribution discrepancy between the transformed domain and the target domain. A new probabilistic crossover is developed to make the well-constructed trees in the individuals more likely to be mated than the other trees. A new mutation operator is designed to give more probability for the poorly-constructed trees to be mutated. The experimental results show that the proposed method not only achieves better performance compared with different traditional learning methods but also advances two recent transfer learning methods on real-world data sets with various incompleteness and learning scenarios.", notes = "also known as \cite{9429709}", } @InProceedings{DBLP:conf/ausai/Al-Helali00Z20, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", editor = "Marcus Gallagher and Nour Moustafa and Erandi Lakshika", title = "Genetic Programming-Based Selection of Imputation Methods in Symbolic Regression with Missing Values", booktitle = "{AI} 2020: Advances in Artificial Intelligence - 33rd Australasian Joint Conference, {AI} 2020, Canberra, ACT, Australia, November 29-30, 2020, Proceedings", series = "Lecture Notes in Computer Science", volume = "12576", pages = "163--175", publisher = "Springer", year = "2020", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.1007/978-3-030-64984-5_13", DOI = "doi:10.1007/978-3-030-64984-5_13", timestamp = "Mon, 15 Feb 2021 00:00:00 +0100", biburl = "https://dblp.org/rec/conf/ausai/Al-Helali00Z20.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @InProceedings{Al-Helali:2021:CEC, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", booktitle = "2021 IEEE Congress on Evolutionary Computation (CEC)", title = "{GP} with a Hybrid Tree-vector Representation for Instance Selection and Symbolic Regression on Incomplete Data", year = "2021", editor = "Yew-Soon Ong", pages = "604--611", address = "Krakow, Poland", month = "28 " # jun # "-1 " # jul, isbn13 = "978-1-7281-8393-0", abstract = "Data incompleteness is a pervasive problem in symbolic regression, and machine learning in general. Unfortunately, most symbolic regression methods are only applicable when the given data is complete. One common approach to handling this situation is data imputation. It works by estimating missing values based on existing data. However, which existing data should be used for imputing the missing values? The answer to this question is important when dealing with incomplete data. To address this question, this work proposes a mixed tree-vector representation for genetic programming to perform instance selection and symbolic regression on incomplete data. In this representation, each individual has two components: an expression tree and a bit vector. While the tree component constructs symbolic regression models, the vector component selects the instances that are used to impute missing values by the weighted k-nearest neighbour (WKNN) imputation method. The complete imputed instances are then used to evaluate the GP-based symbolic regression model. The obtained experimental results show the applicability of the proposed method on real-world data sets with different missingness scenarios. When compared with existing methods, the proposed method not only produces more effective symbolic regression models but also achieves more efficient imputations.", keywords = "genetic algorithms, genetic programming, Computational modeling, Machine learning, Evolutionary computation, Regression tree analysis, Symbolic Regression, Incomplete Data, Imputation, Instance Selection", DOI = "doi:10.1109/CEC45853.2021.9504767", notes = "Also known as \cite{9504767}", } @Article{Al-Helali:ETCI, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", journal = "IEEE Transactions on Emerging Topics in Computational Intelligence", title = "Genetic Programming for Feature Selection Based on Feature Removal Impact in High-Dimensional Symbolic Regression", note = "Early access", abstract = "Symbolic regression is increasingly important for discovering mathematical models for various prediction tasks. It works by searching for the arithmetic expressions that best represent a target variable using a set of input features. However, as the number of features increases, the search process becomes more complex. To address high-dimensional symbolic regression, this work proposes a genetic programming for feature selection method based on the impact of feature removal on the performance of SR models. Unlike existing Shapely value methods that simulate feature absence at the data level, the proposed approach suggests removing features at the model level. This approach circumvents the production of unrealistic data instances, which is a major limitation of Shapely value and permutation-based methods. Moreover, after calculating the importance of the features, a cut-off strategy, which works by injecting a number of random features and using their importance to automatically set a threshold, is proposed for selecting important features. The experimental results on artificial and real-world high-dimensional data sets show that, compared with state-of-the-art feature selection methods using the permutation importance and Shapely value, the proposed method not only improves the SR accuracy but also selects smaller sets of features.", keywords = "genetic algorithms, genetic programming, Feature extraction, Data models, Computational modelling, Task analysis, Predictive models, Machine learning, Feature selection, high dimensionality, symbolic regression", DOI = "doi:10.1109/TETCI.2024.3369407", ISSN = "2471-285X", notes = "Also known as \cite{10466603}", } @Article{Al-Helali:CYB, author = "Baligh Al-Helali and Qi Chen and Bing Xue and Mengjie Zhang", journal = "IEEE Transactions on Cybernetics", title = "Multitree Genetic Programming With Feature-Based Transfer Learning for Symbolic Regression on Incomplete Data", note = "Early access", abstract = "Data incompleteness is a serious challenge in real-world machine-learning tasks. Nevertheless, it has not received enough attention in symbolic regression (SR). Data missingness exacerbates data shortage, especially in domains with limited available data, which in turn limits the learning ability of SR algorithms. Transfer learning (TL), which aims to transfer knowledge across tasks, is a potential solution to solve this issue by making amends for the lack of knowledge. However, this approach has not been adequately investigated in SR. To fill this gap, a multitree genetic programming-based TL method is proposed in this work to transfer knowledge from complete source domains (SDs) to incomplete related target domains (TDs). The proposed method transforms the features from a complete SD to an incomplete TD. However, having many features complicates the transformation process. To mitigate this problem, we integrate a feature selection mechanism to eliminate unnecessary transformations. The method is examined on real-world and synthetic SR tasks with missing values to consider different learning scenarios. The obtained results not only show the effectiveness of the proposed method but also show its training efficiency compared with the existing TL methods. Compared to state-of-the-art methods, the proposed method reduced an average of more than 2.58percent and 4percent regression error on heterogeneous and homogeneous domains, respectively.", keywords = "genetic algorithms, genetic programming, Task analysis, Feature extraction, Data models, Transfer learning, Contracts, Adaptation models, Routing, incomplete data, symbolic regression (SR), transfer learning (TL)", DOI = "doi:10.1109/TCYB.2023.3270319", ISSN = "2168-2275", notes = "Also known as \cite{10120936}", } @PhdThesis{WaleedAljandal2009, author = "Waleed A. Aljandal", title = "Itemset size-sensitive interestingness measures for association rule mining and link prediction", school = "Department of Computing and Information Sciences, Kansas State University", year = "2009", address = "Manhattan, Kansas, USA", month = may, keywords = "genetic algorithms, data Mining, Association Rule, Interestingness Measures, Link Prediction", URL = "https://krex.k-state.edu/dspace/handle/2097/1245", URL = "https://krex.k-state.edu/dspace/bitstream/handle/2097/1245/WaleedAljandal2009.pdf", size = "144 pages", abstract = "Association rule learning is a data mining technique that can capture relationships between pairs of entities in different domains. The goal of this research is to discover factors from data that can improve the precision, recall, and accuracy of association rules found using interestingness measures and frequent itemset mining. Such factors can be calibrated using validation data and applied to rank candidate rules in domain-dependent tasks such as link existence prediction. In addition, I use interestingness measures themselves as numerical features to improve link existence prediction. The focus of this dissertation is on developing and testing an analytical framework for association rule interestingness measures, to make them sensitive to the relative size of itemsets. I survey existing interestingness measures and then introduce adaptive parametric models for normalizing and optimizing these measures, based on the size of itemsets containing a candidate pair of co-occurring entities. The central thesis of this work is that in certain domains, the link strength between entities is related to the rarity of their shared memberships (i.e., the size of itemsets in which they co-occur), and that a data-driven approach can capture such properties by normalizing the quantitative measures used to rank associations. To test this hypothesis under different levels of variability in itemset size, I develop several test bed domains, each containing an association rule mining task and a link existence prediction task. The definitions of itemset membership and link existence in each domain depend on its local semantics. My primary goals are: to capture quantitative aspects of these local semantics in normalization factors for association rule interestingness measures; to represent these factors as quantitative features for link existence prediction, to apply them to significantly improve precision and recall in several real-world domains; and to build an experimental framework for measuring this improvement, using information theory and classification-based validation.", notes = "Not on GP Supervisor William H. Hsu", } @Article{ThunderStormGP, author = "Ruba Al-Jundi and Mais Yasen and Nailah Al-Madi", title = "Thunderstorms Prediction using Genetic Programming", journal = "International Journal of Information Systems and Computer Sciences", year = "2018", volume = "7", number = "1", note = "Special Issue of ICSIC 2017, Held during 23-24 September 2017 in Amman Arab University, Amman, Jordan", keywords = "genetic algorithms, genetic programming, Evolutionary computation, Machine Learning, Weather Prediction.", publisher = "WARSE", ISSN = "2319-7595", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/al-madi/Thunderstorm_Prediction.pdf", URL = "http://www.warse.org/IJISCS/static/pdf/Issue/icsic2017sp14.pdf", size = "7 pages", abstract = "Thunderstorms prediction is a major challenge for efficient flight planning and air traffic management. As the inaccurate forecasting of weather poses a danger to aviation, it increases the need to build a good prediction model. Genetic Programming (GP) is one of the evolutionary computation techniques that is used for classification process. Genetic Programming has proven its efficiency especially for dynamic and nonlinear classification. This research proposes a thunderstorm prediction model that makes use of Genetic Programming and takes real data of Lake Charles Airport (LCH) as a case study. The proposed model is evaluated using different metrics such as recall, F-measure and compared with other well-known classifiers. The results show that Genetic Programming got higher recall value of predicting thunderstorms in comparison with the other classifiers.", notes = "Lake Charles Metar and SYNOP data (LCH) broken aug 2018 http://www.warse.org/IJISCS/archives", } @InProceedings{Al-Madi:2012:NaBIC, author = "N. Al-Madi and S. A. Ludwig", booktitle = "Proceedings of the Fourth World Congress on Nature and Biologically Inspired Computing, NaBIC 2012", title = "Adaptive genetic programming applied to classification in data mining", year = "2012", pages = "79--85", keywords = "genetic algorithms, genetic programming, data mining, pattern classification, adaptive GP, adaptive genetic programming, classification accuracies, crossover rates, data mining, mutation rates, Accuracy, Evolutionary computation, Sociology, Standards, Statistics, Adaptive Genetic Programming, Classification, Evolutionary Computation", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/al-madi/Adaptive_Genetic_Programming_applied_to_Classification_in_Data_Mining.pdf", DOI = "doi:10.1109/NaBIC.2012.6402243", abstract = "Classification is a data mining method that assigns items in a collection to target classes with the goal to accurately predict the target class for each item in the data. Genetic programming (GP) is one of the effective evolutionary computation techniques to solve classification problems, however, it suffers from a long run time. In addition, there are many parameters that need to be set before the GP is run. In this paper, we propose an adaptive GP that automatically determines the best parameters of a run, and executes the classification faster than standard GP. This adaptive GP has three variations. The first variant consists of an adaptive selection process ensuring that the produced solutions in the next generation are better than the solutions in the previous generation. The second variant adapts the crossover and mutation rates by modifying the probabilities ensuring that a solution with a high fitness is protected. And the third variant is an adaptive function list that automatically changes the functions used by deleting the functions that do not favourably contribute to the classification. These proposed variations were implemented and compared to the standard GP. The results show that a significant speedup can be achieved by obtaining similar classification accuracies.", notes = "Also known as \cite{6402243}", } @InProceedings{Al-Madi:2013:SSCI, author = "Nailah Al-Madi and Simone A. Ludwig", title = "Improving genetic programming classification for binary and multiclass datasets", booktitle = "IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013", year = "2013", editor_ssci-2013 = "P. N. Suganthan", editor = "Barbara Hammer and Zhi-Hua Zhou and Lipo Wang and Nitesh Chawla", pages = "166--173", address = "Singapore", month = "16-19 " # apr, keywords = "genetic algorithms, genetic programming, Evolutionary Computation, Classification, Multiclass, Binary Classification", isbn13 = "978-1-4673-5895-8", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/al-madi/improving_GP.pdf", DOI = "doi:10.1109/CIDM.2013.6597232", size = "8 pages", abstract = "Genetic Programming (GP) is one of the evolutionary computation techniques that is used for the classification process. GP has shown that good accuracy values especially for binary classifications can be achieved, however, for multiclass classification unfortunately GP does not obtain high accuracy results. In this paper, we propose two approaches in order to improve the GP classification task. One approach (GP-K) uses the K-means clustering technique in order to transform the produced value of GP into class labels. The second approach (GP-D) uses a discretization technique to perform the transformation. A comparison of the original GP, GP-K and GP-D was conducted using binary and multiclass datasets. In addition, a comparison with other state-of-the-art classifiers was performed. The results reveal that GP-K shows good improvement in terms of accuracy compared to the original GP, however, it has a slightly longer execution time. GP-D also achieves higher accuracy values than the original GP as well as GP-K, and the comparison with the state-of-the-art classifiers reveal competitive accuracy values.", notes = "CIDM 2013, Broken March 2023 http://www.ntu.edu.sg/home/epnsugan/index_files/SSCI2013/CIDM2013.htm Also known as \cite{6597232}", } @InProceedings{AL-Madi:2013:GECCOcomp, author = "Nailah Al-Madi and Simone A. Ludwig", title = "Segment-based genetic programming", booktitle = "GECCO '13 Companion: Proceeding of the fifteenth annual conference companion on Genetic and evolutionary computation conference companion", year = "2013", editor = "Christian Blum and Enrique Alba and Thomas Bartz-Beielstein and Daniele Loiacono and Francisco Luna and Joern Mehnen and Gabriela Ochoa and Mike Preuss and Emilia Tantar and Leonardo Vanneschi and Kent McClymont and Ed Keedwell and Emma Hart and Kevin Sim and Steven Gustafson and Ekaterina Vladislavleva and Anne Auger and Bernd Bischl and Dimo Brockhoff and Nikolaus Hansen and Olaf Mersmann and Petr Posik and Heike Trautmann and Muhammad Iqbal and Kamran Shafi and Ryan Urbanowicz and Stefan Wagner and Michael Affenzeller and David Walker and Richard Everson and Jonathan Fieldsend and Forrest Stonedahl and William Rand and Stephen L. Smith and Stefano Cagnoni and Robert M. Patton and Gisele L. Pappa and John Woodward and Jerry Swan and Krzysztof Krawiec and Alexandru-Adrian Tantar and Peter A. N. Bosman and Miguel Vega-Rodriguez and Jose M. Chaves-Gonzalez and David L. Gonzalez-Alvarez and Sergio Santander-Jimenez and Lee Spector and Maarten Keijzer and Kenneth Holladay and Tea Tusar and Boris Naujoks", isbn13 = "978-1-4503-1964-5", keywords = "genetic algorithms, genetic programming", pages = "133--134", month = "6-10 " # jul, organisation = "SIGEVO", address = "Amsterdam, The Netherlands", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/al-madi/Segment-Based_Genetic_Programming.pdf", DOI = "doi:10.1145/2464576.2464648", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "Genetic Programming (GP) is one of the successful evolutionary computation techniques applied to solve classification problems, by searching for the best classification model applying the fitness evaluation. The fitness evaluation process greatly impacts the overall execution time of GP and is therefore the focus of this research study. This paper proposes a segment-based GP (SegGP) technique that reduces the execution time of GP by partitioning the dataset into segments, and using the segments in the fitness evaluation process. Experiments were done using four datasets and the results show that SegGP can obtain higher or similar accuracy results in shorter execution time compared to standard GP.", notes = "Also known as \cite{2464648} Distributed at GECCO-2013.", } @InProceedings{Al-Madi:2013:nabic, author = "Nailah Al-Madi and Simone A. Ludwig", title = "Scaling Genetic Programming for Data Classification using {MapReduce} Methodology", booktitle = "5th World Congress on Nature and Biologically Inspired Computing", year = "2013", editor = "Simone Ludwig and Patricia Melin and Ajith Abraham and Ana Maria Madureira and Kendall Nygard and Oscar Castillo and Azah Kamilah Muda and Kun Ma and Emilio Corchado", pages = "132--139", address = "Fargo, USA", month = "12-14 " # aug, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Evolutionary computation, data classification, Parallel Processing, MapReduce, Hadoop", isbn13 = "978-1-4799-1415-9", URL = "http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/al-madi/MRGP.pdf", URL = "http://www.mirlabs.net/nabic13/proceedings/html/paper34.xml", DOI = "doi:10.1109/NaBIC.2013.6617851", size = "8 pages", abstract = "Genetic Programming (GP) is an optimisation method that has proved to achieve good results. It solves problems by generating programs and applying natural operations on these programs until a good solution is found. GP has been used to solve many classifications problems, however, its drawback is the long execution time. When GP is applied on the classification task, the execution time proportionally increases with the dataset size. Therefore, to manage the long execution time, the GP algorithm is parallelised in order to speed up the classification process. Our GP is implemented based on the MapReduce methodology (abbreviated as MRGP), in order to benefit from the MapReduce concept in terms of fault tolerance, load balancing, and data locality. MRGP does not only accelerate the execution time of GP for large datasets, it also provides the ability to use large population sizes, thus finding the best result in fewer numbers of generations. MRGP is evaluated using different population sizes ranging from 1,000 to 100,000 measuring the accuracy, scalability, and speedup", notes = "USB only?, IEEE Catalog Number: CFP1395H-POD Also known as \cite{6617851}", } @PhdThesis{Al-Madi:thesis, author = "Nailah Shikri Al-Madi", title = "Improved genetic programming techniques for data classification", school = "Computer Science, North Dakota State University", year = "2013", address = "Fargo, North Dakota, USA", month = dec, keywords = "genetic algorithms, genetic programming, Artificial intelligence, Computer science, Applied sciences, Data classification, Data mining, MRGP", URL = "https://library.ndsu.edu/ir/handle/10365/27097", URL = "https://library.ndsu.edu/ir/bitstream/handle/10365/27097/Improved%20Genetic%20Programming%20Techniques%20For%20Data%20Classification.pdf", broken = "http://gradworks.umi.com/36/14/3614489.html", URL = "http://search.proquest.com/docview/1518147523", size = "123 pages", abstract = "Evolutionary algorithms are one category of optimisation techniques that are inspired by processes of biological evolution. Evolutionary computation is applied to many domains and one of the most important is data mining. Data mining is a relatively broad field that deals with the automatic knowledge discovery from databases and it is one of the most developed fields in the area of artificial intelligence. Classification is a data mining method that assigns items in a collection to target classes with the goal to accurately predict the target class for each item in the data. Genetic programming (GP) is one of the effective evolutionary computation techniques to solve classification problems. GP solves classification problems as an optimization tasks, where it searches for the best solution with highest accuracy. However, GP suffers from some weaknesses such as long execution time, and the need to tune many parameters for each problem. Furthermore, GP can not obtain high accuracy for multiclass classification problems as opposed to binary problems. In this dissertation, we address these drawbacks and propose some approaches in order to overcome them. Adaptive GP variants are proposed in order to automatically adapt the parameter settings and shorten the execution time. Moreover, two approaches are proposed to improve the accuracy of GP when applied to multiclass classification problems. In addition, a Segment-based approach is proposed to accelerate the GP execution time for the data classification problem. Furthermore, a parallelisation of the GP process using the MapReduce methodology was proposed which aims to shorten the GP execution time and to provide the ability to use large population sizes leading to a faster convergence. The proposed approaches are evaluated using different measures, such as accuracy, execution time, sensitivity, specificity, and statistical tests. Comparisons between the proposed approaches with the standard GP, and with other classification techniques were performed, and the results showed that these approaches overcome the drawbacks of standard GP by successfully improving the accuracy and execution time.", notes = "Advisor: Simone A. Ludwig ProQuest, UMI Dissertations Publishing, 2014. 3614489", } @Article{Al-Madi:2016:GPEM, author = "Nailah Al-Madi", title = "Mike Preuss: Multimodal optimization by means of evolutionary algorithms", journal = "Genetic Programming and Evolvable Machines", year = "2016", volume = "17", number = "3", pages = "315--316", month = sep, note = "Book review", keywords = "genetic algorithms", ISSN = "1389-2576", URL = "https://rdcu.be/dR8cf", DOI = "doi:10.1007/s10710-016-9272-x", size = "2 pages", } @Article{Al-Maqaleh:2007:isi, author = "Basheer M. Al-Maqaleh and Kamal K. Bharadwaj", title = "Genetic Programming Approach to Hierarchical Production Rule Discovery", journal = "International Science Index", year = "2007", volume = "1", number = "11", pages = "531--534", keywords = "genetic algorithms, genetic programming, hierarchy, knowledge discovery in database, subsumption matrix. k", publisher = "World Academy of Science, Engineering and Technology", index = "International Science Index 11, 2007", bibsource = "http://waset.org/Publications", bibsource = "OAI-PMH server at citeseerx.ist.psu.edu", language = "en", oai = "oai:CiteSeerX.psu:10.1.1.308.1481", ISSN = "1307-6892", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.1481", URL = "http://waset.org/publications/10022", size = "4 pages", abstract = "Automated discovery of hierarchical structures in large data sets has been an active research area in the recent past. This paper focuses on the issue of mining generalised rules with crisp hierarchical structure using Genetic Programming (GP) approach to knowledge discovery. The post-processing scheme presented in this work uses flat rules as initial individuals of GP and discovers hierarchical structure. Suitable genetic operators are proposed for the suggested encoding. Based on the Subsumption Matrix(SM), an appropriate fitness function is suggested. Finally, Hierarchical Production Rules (HPRs) are generated from the discovered hierarchy. Experimental results are presented to demonstrate the performance of the proposed algorithm.", } @InProceedings{Al-Maqaleh:2012:ACCT, author = "Basheer Mohamad Ahmad Al-Maqaleh", title = "Genetic Algorithm Approach to Automated Discovery of Comprehensible Production Rules", booktitle = "Second International Conference on Advanced Computing Communication Technologies (ACCT 2012)", year = "2012", month = jan, pages = "69--71", size = "3 pages", abstract = "In the recent past, there has been an increasing interest in applying evolutionary methods to Knowledge Discovery in Databases (KDD) and a number of successful applications of Genetic Algorithms (GA) and Genetic Programming (GP) to KDD have been demonstrated. The most predominant representation of the discovered knowledge is the standard Production Rules (PRs) in the form If P Then D. This paper presents a classification algorithm based on GA approach that discovers comprehensible rules in the form of PRs. The proposed approach has flexible chromosome encoding, where each chromosome corresponds to a PR. For the proposed scheme a suitable and effective fitness function and appropriate genetic operators are proposed for the suggested representation. Experimental results are presented to demonstrate the performance of the proposed algorithm.", keywords = "genetic algorithms, GA, KDD, PR, automated discovery, chromosome encoding, comprehensible production rules, genetic algorithm approach, genetic operators, knowledge discovery in databases, production rules, data mining, database management systems", DOI = "doi:10.1109/ACCT.2012.57", notes = "Faculty of Computer Sciences & Information Systems Thamar University, Thamar, Republic of Yemen. Also known as \cite{6168335}", } @Article{Al-Rahamneh:2011:JSEA, author = "Zainab Al-Rahamneh and Mohammad Reyalat and Alaa F. Sheta and Sulieman Bani-Ahmad and Saleh Al-Oqeili", title = "A New Software Reliability Growth Model: Genetic-Programming-Based Approach", journal = "Journal of Software Engineering and Applications", year = "2011", volume = "4", number = "8", pages = "476--481", month = aug, publisher = "Scientific Research Publishing", keywords = "genetic algorithms, genetic programming, SBSE, software reliability, modelling, software faults", ISSN = "19453116", URL = "http://www.scirp.org/journal/PaperDownload.aspx?DOI=10.4236/jsea.2011.48054", broken = "http://www.doaj.org/doaj?func=openurl\&genre=article\&issn=19453116\&date=2011\&volume=04\&issue=08\&spage=476", DOI = "doi:10.4236/jsea.2011.48054", size = "6 pages", abstract = "A variety of Software Reliability Growth Models (SRGM) have been presented in literature. These models suffer many problems when handling various types of project. The reason is; the nature of each project makes it difficult to build a model which can generalise. In this paper we propose the use of Genetic Programming (GP) as an evolutionary computation approach to handle the software reliability modelling problem. GP deals with one of the key issues in computer science which is called automatic programming. The goal of automatic programming is to create, in an automated way, a computer program that enables a computer to solve problems. GP will be used to build a SRGM which can predict accumulated faults during the software testing process. We evaluate the GP developed model and compare its performance with other common growth models from the literature. Our experiments results show that the proposed GP model is superior compared to Yamada S-Shaped, Generalised Poisson, NHPP and Schneidewind reliability models.", bibsource = "OAI-PMH server at www.doaj.org", language = "eng", oai = "oai:doaj-articles:05291f1c8d43b618b364d9e2fbc587cc", } @InProceedings{Al-Ratrout:2010:SSD, author = "Serein Al-Ratrout and Francois Siewe and Omar Al-Dabbas and Mai Al-Fawair", title = "Hybrid Multi-Agent Architecture (HMAA) for meeting scheduling", booktitle = "2010 7th International Multi- Conference on Systems, Signals and Devices", year = "2010", address = "Amman, Jordan", month = "27-30 " # jun, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, multiagent, meeting scheduling, heuristic", language = "en", oai = "oai:CiteSeerX.psu:10.1.1.1011.3891", rights = "Metadata may be used without restrictions as long as the oai identifier remains attached to it.", URL = "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1011.3891", URL = "http://www.cse.dmu.ac.uk/%7Efsiewe/papers/serein_siewe_2010.pdf", DOI = "doi:10.1109/SSD.2010.5585505", size = "6 pages", abstract = "This paper presents a novel multi-agent architecture for meeting scheduling. The proposed architecture is a new Hybrid Multi-Agent Architecture (HMAA) that generates new heuristics for solving NP-hard problems. Moreover, the paper investigates the feasibility of running computationally intensive algorithms on multi-agent architectures while preserving the ability of small agents to run on small devices, including mobile devices. Three experimental groups are conducted in order to test the feasibility of the proposed architecture. The results show that the performance of the proposed architecture is better than those of many existing meeting scheduling frameworks. Moreover, it has been proved that HMAA preserves small agents' mobility (i.e. the ability to run on small devices) while implementing evolutionary algorithms.", notes = "Serein Al-Ratrout Department of Software Engineering, Alzytoonah University, Jordan Francois Siewe Software Technology Research Laboratory, Demontfort University, UK Omar Al-Dabbas Faculty of Engineering, Al-Balqa Applied University, Jordan Mai Al-Fawair Department of Software Engineering, Alzytoonah University, Jordan Also known as \cite{5585505}", } @Article{Al-Saati:2018:IJCA, author = "Najla Akram Al-Saati and Taghreed Riyadh Al-Reffaee", title = "Employing Gene Expression Programming in Estimating Software Effort", journal = "International Journal of Computer Applications", year = "2018", volume = "182", number = "8", pages = "1--8", month = aug, keywords = "genetic algorithms, genetic programming, Gene Expression Programming, Effort Estimation, Software Engineering, Artificial Intelligence", publisher = "Foundation of Computer Science (FCS), NY, USA", address = "New York, USA", ISSN = "0975-8887", URL = "http://www.ijcaonline.org/archives/volume182/number8/29837-2018917619", URL = "https://www.ijcaonline.org/archives/volume182/number8/alsaati-2018-ijca-917619.pdf", DOI = "doi:10.5120/ijca2018917619", size = "8 pages", abstract = "The problem of estimating the effort for software packages is one of the most significant challenges encountering software designers. The precision in estimating the effort or cost can have a huge impact on software development. Various methods have been investigated in order to discover good enough solutions to this problem; lately evolutionary intelligent techniques are explored like Genetic Algorithms, Genetic Programming, Neural Networks, and Swarm Intelligence. In this work, Gene Expression Programming (GEP) is investigated to show its efficiency in acquiring equations that best estimates software effort. Datasets employed are taken from previous projects. The comparisons of learning and testing results are carried out with COCOMO, Analogy, GP and four types of Neural Networks, all show that GEP outperforms all these methods in discovering effective functions for the estimation with robustness and efficiency.", notes = "Also known as \cite{10.5120/ijca2018917619} www.ijcaonline.org Software Engineering Dept. College of Computer Sciences and Mathematics, University of Mosul, Iraq", } @Misc{journals/corr/abs-2001-09923, author = "Najla Akram Al-Saati", title = "Applying Gene Expression Programming for Solving One-Dimensional Bin-Packing Problems", howpublished = "arXiv", year = "2020", month = nov, keywords = "genetic algorithms, genetic programming, gene expression programming", volume = "abs/2001.09923", bibdate = "2020-01-30", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/corr/corr2001.html#abs-2001-09923", URL = "https://arxiv.org/abs/2001.09923", } @InProceedings{Al-Sahaf:2019:GECCOcomp, author = "Harith. Al-Sahaf and Ian Welch", title = "A genetic programming approach to feature selection and construction for ransomware, phishing and spam detection", booktitle = "GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion", year = "2019", editor = "Richard Allmendinger and Carlos Cotta and Carola Doerr and Pietro S. Oliveto and Thomas Weise and Ales Zamuda and Anne Auger and Dimo Brockhoff and Nikolaus Hansen and Tea Tusar and Konstantinos Varelas and David Camacho-Fernandez and Massimiliano Vasile and Annalisa Riccardi and Bilel Derbel and Ke Li and Xiaodong Li and Saul Zapotecas and Qingfu Zhang and Ozgur Akman and Khulood Alyahya and Juergen Branke and Jonathan Fieldsend and Tinkle Chugh and Jussi Hakanen and Josu {Ceberio Uribe} and Valentino Santucci and Marco Baioletti and John McCall and Emma Hart and Daniel R. Tauritz and John R. Woodward and Koichi Nakayama and Chika Oshima and Stefan Wagner and Michael Affenzeller and Eneko Osaba and Javier {Del Ser} and Pascal Kerschke and Boris Naujoks and Vanessa Volz and Anna I Esparcia-Alcazar and Riyad Alshammari and Erik Hemberg and Tokunbo Makanju and Brad Alexander and Saemundur O. Haraldsson and Markus Wagner and Silvino {Fernandez Alzueta} and Pablo {Valledor Pellicer} and Thomas Stuetzle and David Walker and Matt Johns and Nick Ross and Ed Keedwell and Masaya Nakata and Anthony Stein and Takato Tatsumi and Nadarajen Veerapen and Arnaud Liefooghe and Sebastien Verel and Gabriela Ochoa and Stephen Smith and Stefano Cagnoni and Robert M. Patton and William {La Cava} and Randal Olson and Patryk Orzechowski and Ryan Urbanowicz and Akira Oyama and Koji Shimoyama and Hemant Kumar Singh and Kazuhisa Chiba and Pramudita Satria Palar and Alma Rahat and Richard Everson and Handing Wang and Yaochu Jin and Marcus Gallagher and Mike Preuss and Olivier Teytaud and Fernando Lezama and Joao Soares and Zita Vale", isbn13 = "978-1-4503-6748-6", pages = "332--333", address = "Prague, Czech Republic", DOI = "doi:10.1145/3319619.3322083", publisher = "ACM", publisher_address = "New York, NY, USA", month = "13-17 " # jul, organisation = "SIGEVO", keywords = "genetic algorithms, genetic programming", notes = "Also known as \cite{3322083} GECCO-2019 A Recombination of the 28th International Conference on Genetic Algorithms (ICGA) and the 24th Annual Genetic Programming Conference (GP)", } @Article{Al-Sahaf:2019:JRSNZ, author = "Harith Al-Sahaf and Ying Bi and Qi Chen and Andrew Lensen and Yi Mei and Yanan Sun and Binh Tran and Bing Xue and Mengjie Zhang", title = "A survey on evolutionary machine learning", journal = "Journal of the Royal Society of New Zealand", year = "2019", volume = "49", number = "2", pages = "205--228", note = "The 2019 Annual Collection of Reviews", keywords = "genetic algorithms, genetic programming, TPOT, AI, ANN, EML, GPU, EMO, autoML, artificial intelligence, machine learning, evolutionary computation, classification, regression, clustering, combinatorial optimisation, deep learning, transfer learning, ensemble learning", publisher = "Taylor \& Francis", URL = "https://doi.org/10.1080/03036758.2019.1609052", DOI = "doi:10.1080/03036758.2019.1609052", size = "24 pages", abstract = "Artificial intelligence (AI) emphasises the creation of intelligent machines/systems that function like humans. AI has been applied to many real-world applications. Machine learning is a branch of AI based on the idea that systems can learn from data, identify hidden patterns, and make decisions with little/minimal human intervention. Evolutionary computation is an umbrella of population-based intelligent/learning algorithms inspired by nature, where New Zealand has a good international reputation. This paper provides a review on evolutionary machine learning, i.e. evolutionary computation techniques for major machine learning tasks such as classification, regression and clustering, and emerging topics including combinatorial optimisation, computer vision, deep learning, transfer learning, and ensemble learning. The paper also provides a brief review of evolutionary learning applications, such as supply chain and manufacturing for milk/dairy, wine and seafood industries, which are important to New Zealand. Finally, the paper presents current issues with future perspectives in evolutionary machine learning.", } @InProceedings{DBLP:conf/ijcci/ShormanFCGA18, author = "Amaal R. {Al Shorman} and Hossam Faris and Pedro A. Castillo and Juan Julian Merelo Guervos and Nailah Al-Madi", editor = "Christophe Sabourin and Juan Julian Merelo Guervos and Alejandro Linares-Barranco and Kurosh Madani and Kevin Warwick", title = "The Influence of Input Data Standardization Methods on the Prediction Accuracy of Genetic Programming Generated Classifiers", booktitle = "Proceedings of the 10th International Joint Conference on Computational Intelligence, {IJCCI} 2018, Seville, Spain, September 18-20, 2018", pages = "79--85", publisher = "SciTePress", year = "2018", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.5220/0006959000790085", DOI = "doi:10.5220/0006959000790085", timestamp = "Thu, 26 Sep 2019 16:43:57 +0200", biburl = "https://dblp.org/rec/conf/ijcci/ShormanFCGA18.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @PhdThesis{Al-Zubaidi:thesis, author = "Wisam Haitham Abbood {Al-Zubaidi}", title = "Multi-objective search-based approach for software project management", school = "University of Wollongong", year = "2019", address = "Wollongong, NSW 2522, Australia", month = "31 " # mar, keywords = "genetic algorithms, genetic programming, SBSE, Iteration Planning, Agile Development, Effort Estimation, MOGP", URL = "https://ro.uow.edu.au/theses1/690/", URL = "https://ro.uow.edu.au/theses1/690/Al-Zubaidi_thesis.pdf", URL = "https://ro.uow.edu.au/cgi/viewcontent.cgi?article=1678&context=theses1", size = "254 pages", abstract = "Project management covers the entire lifecycle of software, underpinning the success or failure of many software projects. Managing modern software projects often follows the incremental and iterative process where a software product is incrementally developed through a number of iterations. In each iteration, the development team needs to complete a number of issues, each of which can be implementing a new feature for the software, modifying an existing functionality, fixing a bug or conducting some other project tasks. Although this agile approach reduces the risk of project failures, managing projects at the level of issues and iterations is still highly difficult due to the inherent dynamic nature of software, especially in large-scale software projects. Challenges in this context can be in many forms such as making accurate estimations of the resolution time and effort of resolving issues or selecting suitable issues for upcoming iterations. These integral parts of planning is highly challenging since many factors need considering such as customer business value and the team historical estimations, capability and performance. Challenges also exist at the implementation level, such as managing the reviewing of code changes made to resolve issues. There is currently a serious lack of automated support which help project managers and software development teams address those challenges. This thesis aims to fill those gaps. We leverage a huge amount of historical data in software projects to generate valuable insight for dealing with those challenges in managing iterations and issues. We reformulate those project management problems as search-based optimization problems and employ a range of evolutionary meta-heuristics search techniques to solve them. The search is simultaneously guided by a number of multiple fitness functions that express different objectives (e.g. customer business value, developer expertise and workload, and complexity of estimation models) and constraints (e.g. a team historical capability and performance) in the context of modern software projects. Using this approach, we build novel models for estimating issue resolution time and effort, suggesting appropriate issues for upcoming iterations in iteration planning and recommending suitable reviewers for code changes made to resolve issues. An extensive empirical evaluation on a range of large software projects (including Mesos, Usergrid, Aurora, Slider, Kylin, Mahout, Common, Hdfs, MapReduce, Yarn, Apstud, Mule, Dnn, Timob, Tisud, Xd, Nexus, Android, LibreOffice, Qt, and Openstack) demonstrates the highly effective performance of our approach against other alternative techniques (improvement between 1.83 to 550 percent) to show the effectiveness of our approach.", notes = "supervisor: Hoa Khanh Dam", } @InProceedings{Alagesan:2008:AHS, author = "Shri Vidhya Alagesan and Sruthi Kannan and G. Shanthi and A. P. Shanthi and Ranjani Parthasarathi", title = "Intrinsic Evolution of Large Digital Circuits Using a Modular Approach", booktitle = "NASA/ESA Conference on Adaptive Hardware and Systems, AHS '08", year = "2008", month = jun, pages = "19--26", keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, Xilinx Virtex II Pro board, evolvable hardware, large digital circuits, modular approach, modular developmental Cartesian genetic programming, scalability problem, software platform, time consuming fitness evaluation, digital circuits", DOI = "doi:10.1109/AHS.2008.52", abstract = "This work pioneers a generic and flexible approach to intrinsically evolve large digital circuits. One of the popular ways of handling the scalability problem prevalent in evolvable hardware (EHW) and evolve large circuits is to partition the circuit, evolve the individual partitions and then compact them. However, as the partition sizes become larger, this method also fails. This drawback is overcome by the modular developmental Cartesian genetic programming (MDCGP) technique, which still uses partitioning, but augments it further with horizontal and vertical reuse. The results obtained are promising and show that there is 100percent evolvability for 128-bit partitions, the largest partitions evolved so far. The fitness evaluation for the evolved partitions is done by downloading them onto Xilinx Virtex II Pro board. This work is the first step towards the development of a flexible evolvable framework which harnesses the power of hardware for the time consuming fitness evaluation and at the same time provides flexibility by carrying out the other parts using the easily modifiable software platform.", notes = "Also known as \cite{4584250}", } @Article{ALAGHBARI:2023:geoen, author = "Mohammed Al-Aghbari and Ashish {M. Gujarathi}", title = "Hybrid approach of using bi-objective genetic programming in well control optimization of waterflood management", journal = "Geoenergy Science and Engineering", volume = "228", pages = "211967", year = "2023", ISSN = "2949-8910", DOI = "doi:10.1016/j.geoen.2023.211967", URL = "https://www.sciencedirect.com/science/article/pii/S2949891023005547", keywords = "genetic algorithms, genetic programming, Multi-objective optimization, Bi-objective genetic programming, BioGP, NSGA-II, Net-flow method, Waterflood optimization, Reservoir simulation", abstract = "A new hybrid optimization approach is proposed by applying bi-objective genetic programming (BioGP) algorithm along with NSGA-II algorithm to expand the diversity of the Pareto solutions and speed up the convergence. The novel methodology is used in two distinct cases: the benchmark model for the Brugge field and a Middle Eastern oil-field sector model. The Brugge field includes twenty producing wells and ten injecting wells, but the real sector model has three injectors and four producers. The two primary objectives applied are to optimize the total volume of produced oil and reduce cumulative produced water. In the optimization process, the injection rate (qwi) and the bottom-hole pressure (BHP) are the control parameters for injection and producing wells, respectively. The hybrid technique of applying BioGP guided NSGA-II in the Brugge field model demonstrated a 50percent acceleration in the convergence speed when compared to the NSGA-II solution. The calculated Pareto solutions for the Middle-Eastern sector model by the proposed methodology at various generations exhibited better diversity and convergence in comparison to the NSGA-II solutions. The highest cumulative produced oil of 550.45 times 103 m3 is obtained by the proposed hybrid methodology in comparison to the NSGA-II's highest cumulative of 522 times 103 m3. The two solution points A' and B' achieved using the BioGP guided NSGA-II have lower WOR by 17percent and 15percent, respectively, than A and B solutions established by NSGA-II alone. Pareto solution ranking is performed using the net flow method (NFM) and the best optimum solution determined for BioGP guided NSGA-II is 532.38 times 103 m3 oil using equal-based weight compared to 505.44 times 103 m3 using the entropy-based weights of 41percent oil & 59percent water. Overall, the optimal Pareto solutions achieved by the proposed methodology of using BioGP guided NSGA-II algorithm has better diversity with improvement in convergence speed in comparison to the NSGA-II", } @InProceedings{Alajas:2022:IEMTRONICS, author = "Oliver John Alajas and Ronnie Concepcion and Argel Bandala and Edwin Sybingco and Ryan Rhay Vicerra and Elmer P. Dadios and Christan Hail Mendigoria and Heinrick Aquino and Leonard Ambata and Bernardo Duarte", booktitle = "2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)", title = "Detection and Quantitative Prediction of Diplocarpon earlianum Infection Rate in Strawberry Leaves using Population-based Recurrent Neural Network", year = "2022", abstract = "Fragaria ananassa, a member of the rose family's flowering plants, commonly recognized as strawberry, is prone to Diplocarpon earlianum infection that causes leaf scorch. Assessment via visual inspection of strawberries by farmers is normally ineffective, destructive, and laborious. To address this challenge, the use of integrated computer vision and machine learning techniques was done to classify a healthy from a scorch-infected strawberry leaf image and to estimate the leaf region infection rate (LRIR). A dataset made up of 204 normally healthy and 161 scorch-infected strawberry leaf images was used. Images were initially preprocessed and segmented via graph-cut segmentation to extract the region of interest for feature extraction and selection. The hybrid combination of neighborhood and principal component analysis (NCA-PCA) was used to select desirable features. Multigene genetic programming (MGGP) was used to formulate the fitness function that will be essential for determining the optimized neuron configurations of the recurrent neural network (RNN) through genetic algorithm (GA), and cuckoo search algorithm (CSA), and artificial bee colony (ABC). Four classification machine learning models were configured in which the classification tree (CTree) bested other detection models with an accuracy of 10percent and exhibited the shortest inference time of 14.746 s. The developed ABC-RNN3 model outperformed GA-RNN3 and CSA-RNN3 in performing non-invasive LRIR prediction with an R2 value of 0.948. With the use of the NCA-PCA-CTree3-ABC-RNN3 hybrid model, for crop disease detection and infection rate prediction, plant disease assessment proved to be more efficient and labor cost-effective than manual disease inspection methods.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/IEMTRONICS55184.2022.9795744", month = jun, notes = "Also known as \cite{9795744}", } @InProceedings{Alajas:2022:HNICEM, author = "Oliver John Alajas and Ronnie {Concepcion II} and Argel Bandala and Edwin Sybingco and Elmer Dadios and Christan Hail Mendigoria and Heinrick Aquino", title = "Grape Phaeomoniella chlamydospora Leaf Blotch Recognition and Infected Area Approximation Using Hybrid Linear Discriminant Analysis and Genetic Programming", booktitle = "2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM)", year = "2022", address = "Boracay Island, Philippines", month = "01-04 " # dec, month = dec, keywords = "genetic algorithms, genetic programming, Support vector machines, SVM, Image segmentation, Visualization, Image recognition, Computational modelling, Pipelines, Process control, image processing, plant disease detection, machine learning, computer vision, soft computing, black measles", ISSN = "2770-0682", isbn13 = "978-1-6654-6493-2", DOI = "doi:10.1109/HNICEM57413.2022.10109613", size = "6 pages", abstract = "Grapes, scientifically called Vitis vinifera, are vulnerable against Phaeomoniella chlamydospora, the microorganism that causes Esca (black measles) to the leaves, trunks, cordons, and fruit of a young vineyard. Manual visual examination via the naked eye can prove to be challenging especially if done in large-scale vineyards. To address this issue, merging the use of computer vision, image processing, and machine learning was employed as a means of performing blotch identification and leaf blotch area prediction. The dataset is made up of 543 images, comprised of healthy and Esca infected leaves which were captured by an RGB camera. Images were preprocessed and segmented to isolate the diseased pixels and compute the ground truth pixel area. Desirable leaf signatures (G, B, contrast, H, R, S, a*, b*, Cb, and Cr) derived from the feature extraction process using a classification tree. The LDA12 was able to accurately distinguish the healthy from the blotch-infected leaves with a whopping 98.77percent accuracy compared to NB, KNN, and SVM. The MGSR12, with an R2 of 0.9208, topped other models such as RTree, GPR, and RLinear. The hybrid CTree-LDA12-MGSR12 algorithm proved to be ideal in performing leaf health classification and blotched area assessment of grape phenotypes which is important in plant disease identification and fungal spread prevention.", notes = "Also known as \cite{10109613}", } @TechReport{Alander:1995:ibGP, author = "Jarmo T. Alander", title = "An Indexed Bibliography of Genetic Programming", institution = "Department of Information Technology and Industrial Management, University of Vaasa", year = "1995", type = "Report Series no", number = "94-1-GP", address = "Finland", URL = "ftp://ftp.uwasa.fi/cs/report94-1/gaGPbib.ps.Z", keywords = "genetic algorithms, genetic programming", abstract = "220 references. Indexed by subject, publication type and author", notes = "http url reference not working Jan 95. ftp ok. Part of Alander's index of genetic algorithm publications (older versions, ie up to ~1993, are available via ftp, see ENCORE sites). New version dated May 18, 1995. See also Jarmo T. Alander. An indexed bibliography of genetic algorithms: Years 1957-1993. Art of CAD Ltd., Vaasa (Finland), 1994. (over 3000 GA references).", size = "46 pages", } @Book{Alander:1994:bib, author = "Jarmo T. Alander", title = "An Indexed Bibliography of Genetic Algorithms: Years 1957--1993", year = "1994", publisher = "Art of CAD ltd", address = "Vaasa, Finland", keywords = "genetic algorithms, genetic programming", URL = "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.53.4481&rep=rep1&type=pdf", notes = "All GAs some 3000+ references", } @InProceedings{ga96fAlander, annote = "*on,*FIN,genetic programming,mathematics /algebra", author = "Jarmo T. Alander and Ghodrat Moghadampour and Jari Ylinen", title = "2nd order equation", pages = "215--218", year = "1996", editor = "Jarmo T. Alander", booktitle = "Proceedings of the Second Nordic Workshop on Genetic Algorithms and their Applications (2NWGA)", series = "Proceedings of the University of Vaasa, Nro. 13", publisher = "University of Vaasa", address = "Vaasa (Finland)", month = "19.-23.~" # aug, organisation = "Finnish Artificial Intelligence Society", keywords = "genetic algorithms, genetic programming, mathematics, algebra", URL = "ftp://ftp.uwasa.fi/cs/2NWGA/Ghodrat2.ps.Z", size = "4 pages", abstract = "In this work we have tried to use genetic programming to solve the simple second order equation", notes = "2NWGA.bib gives title as 'Solving the second order equation using genetic programming' lil-gp evolution of formular for quadratic roots. lil-gp does not seem to be robust to find the solution formula of 2nd order equation", } @Article{ALANZI:2024:jer, author = "Hamdan Alanzi and Hamoud Alenezi and Oladayo Adeyi and Abiola J. Adeyi and Emmanuel Olusola and Chee-Yuen Gan and Olusegun Abayomi Olalere", title = "Process optimization, multi-gene genetic programming modeling and reliability assessment of bioactive extracts recovery from Phyllantus emblica", journal = "Journal of Engineering Research", year = "2024", ISSN = "2307-1877", DOI = "doi:10.1016/j.jer.2024.02.020", URL = "https://www.sciencedirect.com/science/article/pii/S2307187724000476", keywords = "genetic algorithms, genetic programming, leaf, bioactive extract, Heat-assisted technology, multi gene genetic programming, reliability assessment", abstract = "This study investigates the feasibility of extracting bioactive antioxidants from Phyllantus emblica leaves using a combination of ethanol-water mixture (0-100percent) and heat-assisted extraction technology (HAE-T). Operating temperature (30-50degreeC), solid-to-liquid ratio (1:20-1:60g/mL), and extraction time (45-180min) were varied to determine their effects on extract total phenolic content (TPC), yield (EY), and antioxidant activity (AA). The Box-Behnken experimental design (BBD) within response surface methodology (RSM) was employed, with multi-objective process optimization using the desirability function algorithm to find the optimal process variables for maximizing TPC, EY, and AA simultaneously. The extraction process was modeled using BBD-RSM and multi-gene genetic programming (MGGP) algorithm, with model reliability assessed via Monte Carlo simulation. HPLC characterization identified betulinic acid, gallic acid, chlorogenic acid, caffeic acid, ellagic acid, and ferulic acid as bioactive constituents in the extract. The study found that a 50percent ethanol solution yielded the best extraction efficiency. The optimal process parameters for maximum EY (21.6565percent), TPC (67.116mg GAE/g), and AA (3.68583uM AAE/g) were determined as OT of 41.61degreeC, S:L of 1:60g/mL, and ET of 180min. Both BBD-RSM and MGGP-based models satisfactorily predicted the observed process responses, with BBD-RSM models showing slightly better performance. Reliability analysis indicated high certainty in the predictions, with BBD-RSM models achieving 99.985percent certainty for TPC, 97.569percent for EY, and 98.661percent for AA values", } @Article{ALARFAJ:2024:cscm, author = "Mohammed Alarfaj and Hisham Jahangir Qureshi and Muhammad Zubair Shahab and Muhammad Faisal Javed and Md Arifuzzaman and Yaser Gamil", title = "Machine learning based prediction models for spilt tensile strength of fiber reinforced recycled aggregate concrete", journal = "Case Studies in Construction Materials", volume = "20", pages = "e02836", year = "2024", ISSN = "2214-5095", DOI = "doi:10.1016/j.cscm.2023.e02836", URL = "https://www.sciencedirect.com/science/article/pii/S2214509523010173", keywords = "genetic algorithms, genetic programming, Gene expression programming, Fiber reinforced Recycled Aggregate Concrete, Machine Learning, Sustainability, Eco-friendly Concrete, Spilt Tensile Strength, Deep neural networks, ANN, Optimizable gaussian process regression", abstract = "The demand for concrete production has led to a significant annual requirement for raw materials, resulting in a substantial amount of waste concrete. In response, recycled aggregate concrete has emerged as a promising solution. However, it faces challenges due to the vulnerability of the hardened mortar attached to natural aggregates, leading to susceptibility to cracking and reduced strength. This study focuses on predicting the split tensile strength of fiber reinforced recycled aggregate concrete using five prediction models, including two deep neural network models DNN1 and DNN2, one optimizable Gaussian process regression (OGPR), and two genetic programming based GEP1 and GEP2 models. The models exhibited high accuracy in predicting spilt tensile strength with robust R2, RMSE, and MAE values. DNN2 has the highest R2 value of 0.94 and GEP1 has the lowest R2 value of 0.76. DNN2 model R2 was 3.3percent and 13.5percent higher than OGPR and GEP2. Similarly, DNN2 and GEP2 model performed 9.3percent and 9.21percent better than DNN1 and GEP1 respectively in terms of R2. DNN2 model performed 20.32percent and 31.5percent better than OGPR and GEP2 in terms of MAE. Similarly, GEP2 and DNN2 MAE were 13.1percent and 31.5percent better than GEP1 and DNN1. Sensitivity analysis using the relevance factor and permutation feature importance revealed that the most significant positive factors are cement, natural coarse aggregates, density of recycle aggregates, and superplasticizer while recycle aggregate concrete, max size, and water content of recycle aggregates and water content have the most negative effect on STS values. The proposed ML methods, especially DNN2 and OGPR can be effectively used in practical projects, saving time and cost for eco-friendly fiber reinforced recycled aggregate concrete mixes. However, it is required to study more input variables and use hybrid models to further enhance the accuracy and reliability of the models", } @Article{ALASKAR:2023:cscm, author = "Abdulaziz Alaskar and Ghasan Alfalah and Fadi Althoey and Mohammed Awad Abuhussain and Muhammad Faisal Javed and Ahmed Farouk Deifalla and Nivin A. Ghamry", title = "Comparative study of genetic programming-based algorithms for predicting the compressive strength of concrete at elevated temperature", journal = "Case Studies in Construction Materials", volume = "18", pages = "e02199", year = "2023", keywords = "genetic algorithms, genetic programming, gene expression programming", ISSN = "2214-5095", DOI = "doi:10.1016/j.cscm.2023.e02199", URL = "https://www.sciencedirect.com/science/article/pii/S2214509523003790", abstract = "The elevated temperature severely influences the mixed properties of concrete, causing a decrease in its strength properties. Accurate proportioning of concrete components for obtaining the required compressive strength (C-S) at elevated temperatures is a complicated and time-taking process. However, using evolutionary programming techniques such as gene expression programming (GEP) and multi-expression programming (MEP) provides the accurate prediction of concrete C-S. This article presents the genetic programming-based models (such as gene expression programming (GEP) and multi-expression programming (MEP)) for forecasting the concrete compressive strength (C-S) at elevated temperatures. In this regard, 207 C-S values at elevated temperatures were obtained from previous studies. In the model's development, C-S was considered as the output parameter with the nine most influential input parameters, including; Nano silica, cement, fly ash, water, temperature, silica fume, superplasticizer, sand, and gravels. The efficacy and accuracy of the GEP and MEP-based models were assessed by using statistical measures such as mean absolute error (MAE), correlation coefficient (R2), and root mean square error (RMSE). Moreover, models were also evaluated for external validation using different validation criteria recommended by previous studies. In comparing GEP and MEP models, GEP gave higher R2 and lower RMSE and MAE values of 0.854, 5.331 MPa, and 0.018 MPa respectively, indicating a strong correlation between actual and anticipated outputs. Thus, the GEP-based model was used further for sensitivity analysis, which revealed that cement is the most influencing factor. In addition, the proposed GEP model provides simple mathematical expression that can be easily implemented in practice", } @Article{ALATEFI:2024:cherd, author = "Saad Alatefi and Okorie Ekwe Agwu and Reda Abdel Azim and Ahmad Alkouh and Iskandar Dzulkarnain", title = "Development of multiple explicit data-driven models for accurate prediction of {CO2} minimum miscibility pressure", journal = "Chemical Engineering Research and Design", year = "2024", ISSN = "0263-8762", DOI = "doi:10.1016/j.cherd.2024.04.033", URL = "https://www.sciencedirect.com/science/article/pii/S0263876224002351", keywords = "genetic algorithms, genetic programming, Artificial intelligence, CO2, Explicit models, Gas flooding, Minimum miscibility pressure", abstract = "multiple data-driven models for predicting CO2 minimum miscibility pressure (MMP). The aim is to address the issue of existing models lacking explicit presentation. With a database of 155 data points, five models were developed using artificial neural network (ANN), multigene genetic programming (MGGP), support vector regression (SVR), multivariate adaptive regression splines (MARS), and multiple linear regression (MLR). Comparative analysis was conducted using statistical metrics (R2, MSE, MAE, RMSE), and sensitivity analysis was performed on input variables. The results showed that ANN and SVR had comparable predictive performance (ANN: R2 = 0.982, MSE = 0.00676, MAE = 0.9765, RMSE = 0.082), SVR (R2 = 0.935, MSE = 0.0041, MAE = 0.72, RMSE = 0.064) followed by MARS, MLR, and MGGP. Sensitivity analysis revealed that reservoir temperature was the most influential parameter across all models, except for the MLR algorithm where injected CO2 amount was crucial. These models can be used for a wide range of CO2 MMP ranging from 940psi to 5830psi, thus rendering them useful for any reservoir globally. These models offer improved accuracy and computational efficiency compared to existing ones, potentially reducing costs associated with laboratory experiments and providing rapid and precise CO2 MMP predictions", } @InProceedings{Alattas:2016:CT-IETA, author = "R. Alattas", booktitle = "2016 Annual Connecticut Conference on Industrial Electronics, Technology Automation (CT-IETA)", title = "Hybrid evolutionary designer of modular robots", year = "2016", abstract = "The majority of robotic design approaches start with designing morphology, then designing the robot control. Even in evolutionary robotics, the morphology tends to be fixed while evolving the robot control, which considered insufficient since the robot control and morphology are interdependent. Moreover, both control and morphology are highly interdependent with the surrounding environment, which affects the used optimisation strategies. Therefore, we propose in this paper a novel hybrid GP/GA method for designing autonomous modular robots that co-evolves the robot control and morphology and also considers the surrounding environment to allow the robot of achieving behaviour specific tasks and adapting to the environmental changes. The introduced method is automatically designing feasible robots made up of various modules. Then, our new evolutionary designer is evaluated using a benchmark problem in modular robotics, which is a walking task where the robot has to move a certain distance.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CT-IETA.2016.7868256", month = oct, notes = "Also known as \cite{7868256}", } @InProceedings{Alavi:2008:ICECT, author = "A. H. Alavi and A. A. Heshmati and H. Salehzadeh and A. H. Gandomi and A. Askarinejad", title = "Soft Computing Based Approaches for High Performance Concrete", booktitle = "Proceedings of the Sixth International Conference on Engineering Computational Technology", year = "2008", editor = "M. Papadrakakis and B. H. V. Topping", volume = "89", series = "Civil-Comp Proceedings", pages = "Paper 86", address = "Athens", publisher_address = "Stirlingshire, UK", month = "2-5 " # sep, publisher = "Civil-Comp Press", keywords = "genetic algorithms, genetic programming, linear genetic programming, high performance concrete, multilayer perceptron, compressive strength, workability, mix design", isbn13 = "978-1905088263", ISSN = "1759-3433", URL = "http://www.civil-comp.com/pubs/catalog.htm?t=contents&f=26_3", URL = "http://www.amazon.co.uk/Proceedings-International-Conference-Engineering-Computational/dp/1905088264", DOI = "doi:10.4203/ccp.89.86", abstract = "High performance concrete (HPC) is a class of concrete that provides superior performance than those of conventional types. The enhanced performance characteristics of HPC are generally achieved by the addition of various cementitious materials and chemical and mineral admixtures to conventional concrete mix designs. These parameters considerably influence the compressive strength and workability properties of HPC mixes. An extensive understanding of the relation between these parameters and properties of the resulting matrix is required for developing a standard mix design procedure for HPC mix. To avoid testing several mix proportions to generate a successful mix and also simulating the behaviour of strength and workability improvement to an arbitrary degree of accuracy that often lead to savings in cost and time, it is idealistic to develop prediction models so that the performance characteristics of HPC mixes can be evaluated from the influencing parameters. Therefore, in this paper, linear genetic programming (LGP) is used for the first time in the literature to develop mathematical models to be able to predict the strength and slump flow of HPC mixes in terms of the variables responsible. Subsequently, the LGP based prediction results are compared with the results of proposed multilayer perceptron (MLP) in terms of prediction performance. Sand-cement ratio, coarse aggregate-cement ratio, water-cement ratio, percentage of silica fume and percentage of superplasticiser are used as the input variables to the models to predict the strength and slump flow of HPC mixes. A reliable database was obtained from the previously published literature in order to develop the models. The results of the present study, based on the values of performance measures for the models, demonstrated that for the prediction of compressive strength the optimum MLP model outperforms both the best team and the best single solution that have been created by LGP. It can be seen that for the slump flow the best LGP team solution has produced better results followed by the LGP best single solution and the MLP model. It can be concluded that LGPs are able to reach a prediction performance very close to or even better than the MLP model and as promising candidates can be used for solving such complex prediction problems.", notes = "A.H. Alavi1, A.A. Heshmati1, H. Salehzadeh1, A.H. Gandomi2 and A. Askarinejad3 1College of Civil Engineering, Iran University of Science & Technology (IUST), Tehran, Iran 2College of Civil Engineering, Tafresh University, Iran 3Department of Civil, Environmental and Geomatic Engineering, Swiss Federal Institute of Technology, Zurich, Switzerland", } @InProceedings{Alavi:2008:ICECT2, author = "A. H. Alavi and A. A. Heshmati and A. H. Gandomi and A. Askarinejad and M. Mirjalili", title = "Utilisation of Computational Intelligence Techniques for Stabilised Soil", booktitle = "Proceedings of the Sixth International Conference on Engineering Computational Technology", year = "2008", editor = "M. Papadrakakis and B. H. V. Topping", volume = "89", series = "Civil-Comp Proceedings", pages = "Paper 175", address = "Athens", publisher_address = "Stirlingshire, UK", month = "2-5 " # sep, publisher = "Civil-Comp Press", keywords = "genetic algorithms, genetic programming, linear genetic programming, stabilised soil, multilayer perceptron, textural properties of soil, cement, lime, asphalt, unconfined compressive strength", isbn13 = "978-1905088263", ISSN = "1759-3433", URL = "http://www.civil-comp.com/pubs/catalog.htm?t=contents&f=26_3", URL = "http://www.amazon.co.uk/Proceedings-International-Conference-Engineering-Computational/dp/1905088264", DOI = "doi:10.4203/ccp.89.175", abstract = "In the present study, two branches of computational intelligence techniques namely, the multilayer perceptron (MLP) and linear genetic programming (LGP), are employed to simulate the complex behaviour of the strength improvement in a chemical stabilisation process. Due to a need to avoid extensive and cumbersome experimental stabilisation tests on soils on every new occasion, it was decided to develop mathematical models to be able to estimate the unconfined compressive strength (UCS) as a quality of the stabilised soil after both compaction and curing by using particle size distribution, liquid limit, plasticity index, linear shrinkage as the properties of natural soil before compaction and stabilisation and the quantities and types of stabiliser. A comprehensive and reliable set of data including 219 previously published UCS test results were used to develop the prediction models. Based on the values of performance measures for the models, it was observed that all models are able to predict the UCS value to an acceptable degree of accuracy. The results demonstrated that the optimum MLP model with one hidden layer and thirty six neurons outperforms both the best single and the best team program that have been created by LGP. It can also be concluded that the best team program evolved by LGP has a better performance than the best single evolved program. This investigation revealed that, on average, LGP is able to reach a prediction performance similar to the MLP model. Moreover, LGP as a white-box model provides the programs of an imperative language or machine language that can be inspected and evaluated to provide a better understanding of the underlying relationship between the different interrelated input and output data.", notes = "A.H. Alavi1, A.A. Heshmati1, A.H. Gandomi2, A. Askarinejad3 and M. Mirjalili4 1College of Civil Engineering, Iran University of Science and Technology, Tehran, Iran 2College of Civil Engineering, Tafresh University, Iran 3Department of Civil, Environmental and Geomatic Engineering, Swiss Federal Institute of Technology, Zurich, Switzerland 4Department of Civil & Earth Resources Engineering, Graduate School of Engineering, Kyoto University, Japan", } @Article{Alavi:2010:HP, author = "A. H. Alavi and A. H. Gandomi and M. Gandomi", title = "Comment on 'Sivapragasam C, Maheswaran R, Venkatesh V. 2008. Genetic programming approach for flood routing in natural channels. Hydrological Processes 22: 623-628'", journal = "Hydrological Processes", year = "2010", volume = "24", number = "6", pages = "798--799", month = "15 " # mar, keywords = "genetic algorithms, genetic programming, AIMGP, Discipulus", publisher = "John Wiley & Sons, Ltd.", ISSN = "1099-1085", URL = "http://onlinelibrary.wiley.com/doi/10.1002/hyp.7511/abstract", DOI = "doi:10.1002/hyp.7511", size = "1.5 pages", notes = "no abstract About \cite{Sivapragasam:2007:HP}. See also \cite{Sivapragasam:2010:HP}", } @Article{Alavi:2010:EwC, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Mohammad Ghasem Sahab and Mostafa Gandomi", title = "Multi Expression Programming: A New Approach to Formulation of Soil Classification", journal = "Engineering with Computers", year = "2010", volume = "26", number = "2", pages = "111--118", month = apr, email = "ah_alavi@hotmail.com, a.h.gandomi@gmail.com", keywords = "genetic algorithms, genetic programming, Multi expression programming, Soil classification, Formulation", DOI = "doi:10.1007/s00366-009-0140-7", size = "8 pages", abstract = "This paper presents an alternative approach to formulation of soil classification by means of a promising variant of genetic programming (GP), namely multi expression programming (MEP). Properties of soil, namely plastic limit, liquid limit, colour of soil, percentages of gravel, sand, and fine-grained particles are used as input variables to predict the classification of soils. The models are developed using a reliable database obtained from the previously published literature. The results demonstrate that the MEP-based formulae are able to predict the target values to high degree of accuracy. The MEP-based formulation results are found to be more accurate compared with numerical and analytical results obtained by other researchers.", notes = "M. Gandomi School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran", } @Article{Alavi:2010:GeoMechEng, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Mehdi Mousavi and Ali Mollahasani", title = "High-Precision Modeling of Uplift Capacity of Suction Caissons Using a Hybrid Computational Method", journal = "Geomechanics and Engineering", year = "2010", volume = "2", number = "4", pages = "253--280", month = dec, keywords = "genetic algorithms, genetic programming, suction caissons, uplift capacity, simulated annealing, nonlinear modelling", URL = "http://technopress.kaist.ac.kr/?page=container&journal=gae&volume=2&num=4", DOI = "doi:10.12989/gae.2010.2.4.253", abstract = "A new prediction model is derived for the uplift capacity of suction caissons using a hybrid method coupling genetic programming (GP) and simulated annealing (SA), called GP/SA. The predictor variables included in the analysis are the aspect ratio of caisson, shear strength of clayey soil, load point of application, load inclination angle, soil permeability, and loading rate. The proposed model is developed based on well established and widely dispersed experimental results gathered from the literature. To verify the applicability of the proposed model, it is employed to estimate the uplift capacity of parts of the test results that are not included in the modelling process. Traditional GP and multiple regression analyses are performed to benchmark the derived model. The external validation of the GP/SA and GP models was further verified using several statistical criteria recommended by researchers. Contributions of the parameters affecting the uplift capacity are evaluated through a sensitivity analysis. A subsequent parametric analysis is carried out and the obtained trends are confirmed with some previous studies. Based on the results, the GP/SA-based solution is effectively capable of estimating the horizontal, vertical and inclined uplift capacity of suction caissons. Furthermore, the GP/SA model provides a better prediction performance than the GP, regression and different models found in the literature. The proposed simplified formulation can reliably be employed for the pre-design of suction caissons. It may be also used as a quick check on solutions developed by more time consuming and in-depth deterministic analyses.", } @Article{Alavi:2010:ijcamieec, author = "Amir Hossein Alavi and Amir Hossein Gandomi", title = "A Robust Data Mining Approach for Formulation of Geotechnical Engineering Systems", journal = "International Journal of Computer Aided Methods in Engineering-Engineering Computations", year = "2011", volume = "28", number = "3", pages = "242--274", email = "ah_alavi@hotmail.com, a.h.gandomi@gmail.com", keywords = "genetic algorithms, genetic programming, gene expression programming, multi expression programming, Linear-based genetic programming, Data mining, Data collection, Geotechnical engineering, Programming and algorithm theory, Systems analysis, Formulation", ISSN = "0264-4401", URL = "http://www.emeraldinsight.com/journals.htm?articleid=1912293", DOI = "doi:10.1108/02644401111118132", size = "33 pages", abstract = "Purpose- The complexity of analysis of geotechnical behaviour is due to multivariable dependencies of soil and rock responses. In order to cope with this complex behavior, traditional forms of engineering design solutions are reasonably simplified. Incorporating simplifying assumptions into the development of the traditional models may lead to very large errors. In the present study, capabilities of promising variants of genetic programming (GP), namely linear genetic programming (LGP), gene expression programming (GEP) and multi expression programming (MEP) are illustrated by applying them to the formulation of several complex geotechnical engineering problems. Design/methodology/approach- LGP, GEP and MEP are new variants of GP that make a clear distinction between the genotype and the phenotype of an individual. Compared with the traditional GP, the LGP, GEP and MEP techniques are more compatible with computer architectures. This results in a significant speedup in their execution. These methods have a great ability to directly capture the knowledge contained in the experimental data without making assumptions about the underlying rules governing the system. This is one their major advantages over most of the traditional constitutive modeling methods. Findings- In order to demonstrate the simulation capabilities of LGP, GEP and MEP, they were applied to the prediction of (i) relative crest settlement of concrete-faced rockfill dams, (ii) slope stability, (iii) settlement around tunnels, and (iv) soil liquefaction. The results are compared with those obtained by other models presented in the literature and found to be more accurate. LGP has the best overall behaviour for the analysis of the considered problems in comparison with GEP and MEP. The simple and straightforward constitutive models developed using LGP, GEP and MEP provide valuable analysis tools accessible to practising engineers. Originality/value- The LGP, GEP and MEP approaches overcome the shortcomings of different methods previously presented in the literature for the analysis of geotechnical engineering systems. Contrary to artificial neural networks and many other soft computing tools, LGP, GEP and MEP provide prediction equations that can readily be used for routine design practice. The constitutive models derived using these methods can efficiently be incorporated into the finite element or finite difference analyses as material models. They may also be used as a quick check on solutions developed by more time consuming and in-depth deterministic analyses.", } @InProceedings{Alavi:2010:HBE, author = "Amir Hossein Alavi and Amir Hossein Gandomi", title = "Nonlinear Modeling of Liquefaction Behavior of Sand-Silt Mixtures in terms of Strain Energy", booktitle = "Proceedings of the 8th International Symposium on Highway and Bridge Engineering, Technology and Innovation in Transportation Infrastructure, 2010", year = "2010", editor = "Rodian Scinteie and Costel Plescan", pages = "50--69", address = "Iasi, Romania", month = "10 " # dec, organisation = "Editura Societatii Academice Matei - Teiu Botez", keywords = "genetic algorithms, genetic programming, GPLAB, Discipulus, simulated annealing, capacity energy, Matlab", isbn13 = "978-606-582-000-5", URL = "http://www.intersections.ro/Conferences/HBE2010.pdf", size = "20 pages", notes = "http://www.intersections.ro/Conferences/ HBE2010@intersections.ro", } @Article{Alavi:2010:CBM, author = "Amir Hossein Alavi and Mahmoud Ameri and Amir Hossein Gandomi and Mohammad Reza Mirzahosseini", title = "Formulation of Flow Number of Asphalt Mixes Using a Hybrid Computational Method", journal = "Construction and Building Materials", year = "2011", volume = "25", number = "3", pages = "1338--1355", month = mar, keywords = "genetic algorithms, genetic programming, Asphalt concrete mixture, Flow number, Simulated annealing, Marshall mix design, Regression analysis", ISSN = "0950-0618", DOI = "doi:10.1016/j.conbuildmat.2010.09.010", size = "18 pages", abstract = "A high-precision model was derived to predict the flow number of dense asphalt mixtures using a novel hybrid method coupling genetic programming and simulated annealing, called GP/SA. The proposed constitutive model correlates the flow number of Marshall specimens with the percentages of filler, bitumen, voids in mineral aggregate, Marshall stability and flow. The comprehensive experimental database used for the development of the model was established upon a series of uniaxial dynamic creep tests conducted in this study. Generalised regression neural network and multiple regression-based analyses were performed to benchmark the GP/SA model. The contributions of the variables affecting the flow number were evaluated through a sensitivity analysis. A subsequent parametric study was carried out and the trends of the results were confirmed with the results of the experimental study. The results indicate that the proposed GP/SA model is effectively capable of evaluating the flow number of asphalt mixtures. The derived model is remarkably straightforward and provides an analysis tool accessible to practising engineers.", notes = "a School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran b College of Civil Engineering, Tafresh University, Tafresh, Iran c Transportation Research Institute (TRI), Tehran, Iran", } @Article{Alavi20101239, author = "A. H. Alavi and A. H. Gandomi and A. A. R. Heshmati", title = "Discussion on {"}Soft computing approach for real-time estimation of missing wave heights{"} by S.N. Londhe [Ocean Engineering 35 (2008) 1080-1089]", journal = "Ocean Engineering", year = "2010", volume = "37", number = "13", pages = "1239--1240", month = sep, ISSN = "0029-8018", DOI = "doi:10.1016/j.oceaneng.2010.06.003", URL = "http://www.sciencedirect.com/science/article/B6V4F-50DXD90-1/2/b2489a1aebf49e771abca1b27d3b24b4", keywords = "genetic algorithms, genetic programming, Linear genetic programming, Tree structure, Wave forecasts", abstract = "The paper studied by Londhe (2008) \cite{Londhe20081080} uses genetic programming (GP) for estimation of missing wave heights. The paper includes some problems about the fundamental aspects and use of the GP approach. In this discussion, some controversial points of the paper are given.", } @Article{Alavi2011, author = "Amir Hossein Alavi and Pejman Aminian and Amir Hossein Gandomi and Milad {Arab Esmaeili}", title = "Genetic-based modeling of uplift capacity of suction caissons", journal = "Expert Systems with Applications", volume = "38", number = "10", pages = "12608--12618", year = "2011", month = "15 " # sep, ISSN = "0957-4174", URL = "http://www.sciencedirect.com/science/article/pii/S0957417411005653", URL = "http://www.sciencedirect.com/science/article/B6V03-52P1KNK-4/2/f33267200d0fc51ad7a086befe3a361c", DOI = "doi:10.1016/j.eswa.2011.04.049", keywords = "genetic algorithms, genetic programming, Gene expression programming, Suction caissons, Uplift capacity, Formulation", size = "11 pages", abstract = "In this study, classical tree-based genetic programming (TGP) and its recent variants, namely linear genetic programming (LGP) and gene expression programming (GEP) are used to develop new prediction equations for the uplift capacity of suction caissons. The uplift capacity is formulated in terms of several inflecting variables. An experimental database obtained from the literature is employed to develop the models. Further, a conventional statistical analysis is performed to benchmark the proposed models. Sensitivity and parametric analyses are conducted to verify the results. TGP, LGP and GEP are found to be effective methods for evaluating the horizontal, vertical, and inclined uplift capacity of suction caissons. The TGP, LGP and GEP models reach a prediction performance better than or comparable with the models found in the literature.", } @Article{Alavi:2011:JEQE, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Minoo Modaresnezhad and Mehdi Mousavi", title = "New Ground-Motion Prediction Equations Using Multi Expression Programing", journal = "Journal of Earthquake Engineering", year = "2011", volume = "15", number = "4", pages = "511--536", keywords = "genetic algorithms, genetic programming, Multi-Expression Programming, Time-Domain Ground-Motion Parameters, Attenuation Relationship, Nonlinear Modelling", ISSN = "1363-2469", URL = "http://www.tandfonline.com/doi/abs/10.1080/13632469.2010.526752#.UlMR6NKc_G0", DOI = "doi:10.1080/13632469.2010.526752", size = "26 pages", abstract = "High-precision attenuation models were derived to estimate peak ground acceleration (PGA), velocity (PGV), and displacement (PGD) using a new variant of genetic programming, namely multi expression programming (MEP). The models were established based on an extensive database of ground-motion recordings released by Pacific Earthquake Engineering Research Center (PEER). For more validity verification, the models were employed to predict the ground-motion parameters of the Iranian plateau earthquakes. The results indicate that the MEP attenuation models are capable of effectively estimating the peak ground-motion parameters. The proposed models are able to reach a prediction performance comparable with the attenuation relationships found in the literature.", } @Article{Alavi2012541, author = "Amir Hossein Alavi and Amir Hossein Gandomi", title = "Energy-based numerical models for assessment of soil liquefaction", journal = "Geoscience Frontiers", volume = "3", number = "4", pages = "541--555", year = "2012", ISSN = "1674-9871", DOI = "doi:10.1016/j.gsf.2011.12.008", URL = "http://www.sciencedirect.com/science/article/pii/S167498711100137X", keywords = "genetic algorithms, genetic programming, Soil liquefaction, Capacity energy, Multi expression programming, Sand, Formulation", abstract = "This study presents promising variants of genetic programming (GP), namely linear genetic programming (LGP) and multi expression programming (MEP) to evaluate the liquefaction resistance of sandy soils. Generalised LGP and MEP-based relationships were developed between the strain energy density required to trigger liquefaction (capacity energy) and the factors affecting the liquefaction characteristics of sands. The correlations were established based on well established and widely dispersed experimental results obtained from the literature. To verify the applicability of the derived models, they were employed to estimate the capacity energy values of parts of the test results that were not included in the analysis. The external validation of the models was verified using statistical criteria recommended by researchers. Sensitivity and parametric analyses were performed for further verification of the correlations. The results indicate that the proposed correlations are effectively capable of capturing the liquefaction resistance of a number of sandy soils. The developed correlations provide a significantly better prediction performance than the models found in the literature. Furthermore, the best LGP and MEP models perform superior than the optimal traditional GP model. The verification phases confirm the efficiency of the derived correlations for their general application to the assessment of the strain energy at the onset of liquefaction.", } @InCollection{books/sp/chiong2012/AlaviGM12, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Ali Mollahasani", title = "A Genetic Programming-Based Approach for the Performance Characteristics Assessment of Stabilized Soil", booktitle = "Variants of Evolutionary Algorithms for Real-World Applications", publisher = "Springer", year = "2012", editor = "Raymond Chiong and Thomas Weise and Zbigniew Michalewicz", chapter = "9", pages = "343--376", keywords = "genetic algorithms, genetic programming, Chemical stabilisation, Simulated annealing, Nonlinear modelling", isbn13 = "978-3-642-23423-1", DOI = "doi:10.1007/978-3-642-23424-8_11", abstract = "This chapter presents a variant of genetic programming, namely linear genetic programming (LGP), and a hybrid search algorithm coupling LGP and simulated annealing (SA), called LGP/SA, to predict the performance characteristics of stabilised soil. LGP and LGP/SA relate the unconfined compressive strength (UCS), maximum dry density (MDD), and optimum moisture content (OMC) metrics of stabilised soil to the properties of the natural soil as well as the types and quantities of stabilizing additives. Different sets of LGP and LGP/SA-based prediction models have been separately developed. The contributions of the parameters affecting UCS, MDD, and OMC are evaluated through a sensitivity analysis. A subsequent parametric analysis is carried out and the trends of the results are compared with previous studies. A comprehensive set of data obtained from the literature has been used for developing the models. Experimental results confirm that the accuracy of the proposed models is satisfactory. In particular, the LGP-based models are found to be more accurate than the LGP/SA-based models.", affiliation = "School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran", bibdate = "2011-11-16", bibsource = "DBLP, http://dblp.uni-trier.de/db/books/collections/Chiong2012.html#AlaviGM12", } @InCollection{Alavi:2013:MWGTE, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Ali Mollahasani and Jafar {Bolouri Bazaz}", title = "Linear and Tree-Based Genetic Programming for Solving Geotechnical Engineering Problems", editor = "Xin-She Yang and Amir Hossein Gandomi and Siamak Talatahari and Amir Hossein Alavi", booktitle = "Metaheuristics in Water, Geotechnical and Transport Engineering", publisher = "Elsevier", address = "Oxford", year = "2013", pages = "289--310", chapter = "12", keywords = "genetic algorithms, genetic programming, Tree-based genetic programming, linear genetic programming, geotechnical engineering, prediction", isbn13 = "978-0-12-398296-4", DOI = "doi:10.1016/B978-0-12-398296-4.00012-X", URL = "http://www.sciencedirect.com/science/article/pii/B978012398296400012X", abstract = "This chapter presents new approaches for solving geotechnical engineering problems using classical tree-based genetic programming (TGP) and linear genetic programming (LGP). TGP and LGP are symbolic optimisation techniques that create computer programs to solve a problem using the principle of Darwinian natural selection. Generally, they are supervised, machine-learning techniques that search a program space instead of a data space. Despite remarkable prediction capabilities of the TGP and LGP approaches, the contents of reported applications indicate that the progress in their development is marginal and not moving forward. The present study introduces a state-of-the-art examination of TGP and LGP applications in solving complex geotechnical engineering problems that are beyond the computational capability of traditional methods. In order to justify the capabilities of these techniques, they are systematically employed to formulate a typical geotechnical engineering problem. For this aim, effective angle of shearing resistance (phi) of soils is formulated in terms of the physical properties of soil. The validation of the TGP and LGP models is verified using several statistical criteria. The numerical example shows the superb accuracy, efficiency, and great potential of TGP and LGP. The models obtained using TGP and LGP can be used efficiently as quick checks on solutions developed by more time consuming and in-depth deterministic analyses. The current research directions and issues that need further attention in the future are discussed. Keywords Tree-based genetic programming, linear genetic programming geotechnical engineering, prediction", notes = "Also known as \cite{Alavi2013289}", } @Article{Alavi:2014:NCA, author = "Amir Hossein Alavi and Amir Hossein Gandomi and Hadi {Chahkandi Nejad} and Ali Mollahasani and Azadeh Rashed", title = "Design equations for prediction of pressuremeter soil deformation moduli utilizing expression programming systems", journal = "Neural Computing and Applications", year = "2013", volume = "23", number = "6", pages = "1771--1786", month = nov, keywords = "genetic algorithms, genetic programming, gene expression programming, Soil deformation modulus, Expression programming techniques, Pressure meter test, Soil physical properties", publisher = "Springer-Verlag", ISSN = "0941-0643", URL = "http://link.springer.com/article/10.1007%2Fs00521-012-1144-6", DOI = "doi:10.1007/s00521-012-1144-6", language = "English", size = "16 pages", abstract = "Providing precise estimations of soil deformation modulus is very difficult due to its dependence on many factors. In this study, gene expression programming (GEP) and multi-expression programming (MEP) systems are presented to derive empirical equations for the prediction of the pressuremeter soil deformation modulus. The employed expression programming (EP) systems formulate the soil deformation modulus in terms of the soil physical properties. Selection of the best models is on the basis of developing and controlling several models with different combinations of the affecting parameters. The proposed EP-based models are established upon 114 pressure meter tests on different soil types conducted in this study. The generalisation capabilities of the models are verified using several statistical criteria. Contributions of the variables influencing the soil modulus are evaluated through a sensitivity analysis. The GEP and MEP approaches accurately characterise the soil deformation modulus resulting in a very good prediction performance. The result indicates that moisture content and soil dry unit weight can efficiently represent the initial state and consolidation history of soil for determining its modulus.", } @Article{Alavi:2014:GF, author = "Amir H. Alavi and Ehsan Sadrossadat", title = "New design equations for estimation of ultimate bearing capacity of shallow foundations resting on rock masses", journal = "Geoscience Frontiers", year = "2014", keywords = "genetic algorithms, genetic programming, Rock mass properties, Ultimate bearing capacity, Shallow foundation, Prediction, Evolutionary computation", ISSN = "1674-9871", DOI = "doi:10.1016/j.gsf.2014.12.005", URL = "http://www.sciencedirect.com/science/article/pii/S1674987114001625", abstract = "Rock masses are commonly used as the underlying layer of important structures such as bridges, dams and transportation constructions. The success of a foundation design for such structures mainly depends on the accuracy of estimating the bearing capacity of rock beneath them. Several traditional numerical approaches are proposed for the estimation of the bearing capacity of foundations resting on rock masses to avoid performing elaborate and expensive experimental studies. Despite this fact, there still exists a serious need to develop more robust predictive models. This paper proposes new nonlinear prediction models for the ultimate bearing capacity of shallow foundations resting on non-fractured rock masses using a novel evolutionary computational approach, called linear genetic programming. A comprehensive set of rock socket, centrifuge rock socket, plate load and large-scaled footing load test results is used to develop the models. In order to verify the validity of the models, the sensitivity analysis is conducted and discussed. The results indicate that the proposed models accurately characterise the bearing capacity of shallow foundations. The correlation coefficients between the experimental and predicted bearing capacity values are equal to 0.95 and 0.96 for the best LGP models. Moreover, the derived models reach a notably better prediction performance than the traditional equations.", } @Article{Alavi:2016:GSF, author = "Amir H. Alavi and Amir H. Gandomi and David J. Lary", title = "Progress of machine learning in geosciences: Preface", journal = "Geoscience Frontiers", year = "2016", volume = "7", number = "1", pages = "1--2", note = "Editorial", keywords = "genetic algorithms, genetic programming", ISSN = "1674-9871", URL = "http://www.sciencedirect.com/science/article/pii/S1674987115001243", DOI = "doi:10.1016/j.gsf.2015.10.006", size = "2 pages", notes = "Peer-review under responsibility of China University of Geosciences (Beijing)", } @Article{Alavi:2017:ACME, author = "Amir H. Alavi and Hassene Hasni and Imen Zaabar and Nizar Lajnef", title = "A new approach for modeling of flow number of asphalt mixtures", journal = "Archives of Civil and Mechanical Engineering", volume = "17", number = "2", pages = "326--335", year = "2017", ISSN = "1644-9665", DOI = "doi:10.1016/j.acme.2016.06.004", URL = "http://www.sciencedirect.com/science/article/pii/S1644966516300814", abstract = "Flow number of asphalt-aggregate mixtures is an explanatory parameter for the analysis of rutting potential of asphalt mixtures. In this study, a new model is proposed for the determination of flow number using a robust computational intelligence technique, called multi-gene genetic programming (MGGP). MGGP integrates genetic programming and classical regression to formulate the flow number of Marshall Specimens. A reliable experimental database is used to develop the proposed model. Different analyses are performed for the performance evaluation of the model. On the basis of a comparison study, the MGGP model performs superior to the models found in the literature.", keywords = "genetic algorithms, genetic programming, Asphalt mixture, Flow number, Marshall mix design", } @InProceedings{alba:1996:tGPrdflc, author = "Enrique Alba and Carlos Cotta and Jose M. Troya", title = "Type-Constrained Genetic Programming for Rule-Base Definition in Fuzzy Logic Controllers", booktitle = "Genetic Programming 1996: Proceedings of the First Annual Conference", editor = "John R. Koza and David E. Goldberg and David B. Fogel and Rick L. Riolo", year = "1996", month = "28--31 " # jul, keywords = "genetic algorithms, genetic programming", pages = "255--260", address = "Stanford University, CA, USA", publisher = "MIT Press", size = "6 pages", URL = "http://cognet.mit.edu/sites/default/files/books/9780262315876/pdfs/9780262315876_chap31.pdf", URL = "http://cognet.mit.edu/library/books/view?isbn=0262611279", notes = "GP-96", } @InProceedings{alba:1999:ERASPSPDGA, author = "Enrique Alba and Carlos Cotta and Jose M. Troya", title = "Entropic and Real-Time Analysis of the Search with Panmictic, Structured, and Parallel Distributed Genetic Algorithms", booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference", year = "1999", editor = "Wolfgang Banzhaf and Jason Daida and Agoston E. Eiben and Max H. Garzon and Vasant Honavar and Mark Jakiela and Robert E. Smith", volume = "1", pages = "773", address = "Orlando, Florida, USA", publisher_address = "San Francisco, CA 94104, USA", month = "13-17 " # jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms and classifier systems, poster papers", ISBN = "1-55860-611-4", URL = "http://gpbib.cs.ucl.ac.uk/gecco1999/Ga-808.pdf", notes = "GECCO-99 A joint meeting of the eighth international conference on genetic algorithms (ICGA-99) and the fourth annual genetic programming conference (GP-99)", } @InProceedings{alba:1999:T, author = "Enrique Alba and Jose M. Troya", title = "Tackling epistasis with panmictic and structured genetic algorithms", booktitle = "Late Breaking Papers at the 1999 Genetic and Evolutionary Computation Conference", year = "1999", editor = "Scott Brave and Annie S. Wu", pages = "1--7", address = "Orlando, Florida, USA", month = "13 " # jul, keywords = "Genetic Algorithms, NK", notes = "GECCO-99LB", } @Article{alba:1999:edflcSGP, author = "Enrique Alba and Carlos Cotta and Jose M. Troya", title = "Evolutionary Design of Fuzzy Logic Controllers Using Strongly-Typed GP", journal = "Mathware \& Soft Computing", year = "1999", volume = "6", number = "1", pages = "109--124", keywords = "genetic algorithms, genetic programming, Type System, Fuzzy Logic Controller, Cart-Centering Problem", URL = "http://docto-si.ugr.es/Mathware/v6n1/PS/7-alba.ps.gz", abstract = "An evolutionary approach to the design of fuzzy logic controllers is presented in this paper. We propose the use of the genetic programming paradigm to evolve fuzzy rule-bases (internally represented as type-constrained syntactic trees). This model has been applied to the cart-centering problem, although it can be readily extended to other problems. The obtained results show that a good parameterization of the algorithm, and an appropriate evaluation function, can lead to near-optimal solutions.", notes = "Mathware and softcomputing http://docto-si.ugr.es/Mathware/ENG/mathware.html", } @Book{Alba05, author = "Enrique Alba", title = "Parallel Metaheuristics: A New Class of Algorithms", publisher = "John Wiley \& Sons", month = aug, year = "2005", address = "NJ, USA", ISBN = "0-471-67806-6", keywords = "genetic algorithms, genetic programming, book, text, general computer engineering", URL = "https://www.amazon.com/Parallel-Metaheuristics-New-Class-Algorithms/dp/0471678066/ref=sr_1_1", abstract = "This single reference on parallel metaheuristic presents modern and ongoing research information on using, designing, and analysing efficient models of parallel algorithms. Table of Contents Author Information Introduction. PART I: INTRODUCTION TO METAHEURISTICS AND PARALLELISM. 1. An Introduction to Metaheuristic Techniques. 2. Measuring the Performance of Parallel Metaheuristics. 3. New Technologies in Parallelism. 4. Metaheuristics and Parallelism. PART II: PARALLEL METAHEURISTIC MODELS. 5. Parallel Genetic Algorithms. 6. Spatially Structured Genetic Programming. 7. Parallel Evolution Strategies. 8. Parallel Ant Colony Algorithms. 9. Parallel Estimation of Distribution Algorithms. 10. Parallel Scatter Search. 11. Parallel Variable Neighbourhood Search. 12. Parallel Simulated Annealing. 13. Parallel Tabu Search. 14. Parallel GRASP. 15. Parallel Hybrid Metaheuristics. 16. Parallel Multi Objective. 17. Parallel Heterogeneous Metaheuristics. PART III: THEORY AND APPLICATIONS. 18. Theory of Parallel Genetic Algorithms. 19. Parallel Metaheuristics. 20. Parallel Metaheuristics in Telecommunications. 21. Bioinformatics and Parallel Metaheuristics. Index.", notes = "US 95.", size = "00584 pages", } @InProceedings{Albalushi:2023:SWC, author = "Muna Albalushi and Rasha {Al Jassim} and Karan Jetly and Raya {Al Khayari} and Hilal {Al Maqbali}", booktitle = "2023 IEEE Smart World Congress (SWC)", title = "Optimizing Diabetes Predictive Modeling with Automated Decision Trees", year = "2023", abstract = "This paper introduces Linear Genetic Programming for Optimising Decision Tree (LGP-OptTree), a novel form of Genetic Programming (GP) aimed at enhancing diabetes detection. LGP-OptTree is designed to optimise the attributes and hyperparameters of decision trees by using a unique genotype and phenotype structure. The proposed method is evaluated on the Pima dataset and compared with other techniques. By fine-tuning the attributes and hyperparameters of decision trees using LGP-OptTree, this study aims to improve the accuracy and efficacy of diabetes detection. A performance metric is used to determine the effectiveness of the proposed method with respect to other approaches. The contribution of this research lies in providing general healthcare professionals with a new approach for enhancing diabetes detection accuracy through decision trees.", keywords = "genetic algorithms, genetic programming, Measurement, Medical services, Predictive models, Prediction algorithms, Diabetes, Decision trees, Evolutionary Algorithm", DOI = "doi:10.1109/SWC57546.2023.10449077", month = aug, notes = "Also known as \cite{10449077}", } @InProceedings{Albarracin:2016:SIBGRAPI, author = "Juan Felipe {Hernandez Albarracin} and Jefersson Alex {dos Santos} and Ricardo {da S. Torres}", booktitle = "2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)", title = "Learning to Combine Spectral Indices with Genetic Programming", year = "2016", pages = "408--415", abstract = "This paper introduces a Genetic Programming-based method for band selection and combination, aiming to support remote sensing image classification tasks. Relying on ground-truth data, our method selects spectral bands and finds the arithmetic combination of those bands (i.e., spectral index) that best separates examples of different classes. Experimental results demonstrate that the proposed method is very effective in pixel-wise binary classification problems.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/SIBGRAPI.2016.063", month = oct, notes = "Also known as \cite{7813062}", } @Article{albarracin:2020:RS, author = "Juan F. H. Albarracin and Rafael S. Oliveira and Marina Hirota and Jefersson A. {dos Santos} and Ricardo da S. Torres", title = "A Soft Computing Approach for Selecting and Combining Spectral Bands", journal = "Remote Sensing", year = "2020", volume = "12", number = "14", keywords = "genetic algorithms, genetic programming", ISSN = "2072-4292", URL = "https://www.mdpi.com/2072-4292/12/14/2267", DOI = "doi:10.3390/rs12142267", abstract = "We introduce a soft computing approach for automatically selecting and combining indices from remote sensing multispectral images that can be used for classification tasks. The proposed approach is based on a Genetic-Programming (GP) framework, a technique successfully used in a wide variety of optimisation problems. Through GP, it is possible to learn indices that maximize the separability of samples from two different classes. Once the indices specialized for all the pairs of classes are obtained, they are used in pixelwise classification tasks. We used the GP-based solution to evaluate complex classification problems, such as those that are related to the discrimination of vegetation types within and between tropical biomes. Using time series defined in terms of the learnt spectral indices, we show that the GP framework leads to superior results than other indices that are used to discriminate and classify tropical biomes.", notes = "also known as \cite{rs12142267}", } @InProceedings{Albinati:2014:SMGP, author = "Julio Albinati and Gisele L. Pappa and Fernando E. B. Otero and Luiz Otavio V. B. Oliveira", title = "A Study of Semantic Geometric Crossover Operators in Regression Problems", booktitle = "Semantic Methods in Genetic Programming", year = "2014", editor = "Colin Johnson and Krzysztof Krawiec and Alberto Moraglio and Michael O'Neill", address = "Ljubljana, Slovenia", month = "13 " # sep, note = "Workshop at Parallel Problem Solving from Nature 2014 conference", keywords = "genetic algorithms, genetic programming", URL = "http://www.cs.put.poznan.pl/kkrawiec/smgp2014/uploads/Site/Albinati.pdf", size = "2 pages", notes = "SMGP 2014 http://www.cs.put.poznan.pl/kkrawiec/smgp/?n=Site.SMGP2014", } @InProceedings{Albinati:2015:EuroGP, author = "Julio Albinati and Gisele L. Pappa and Fernando E. B. Otero and Luiz Otavio V. B. Oliveira", title = "The Effect of Distinct Geometric Semantic Crossover Operators in Regression Problems", booktitle = "18th European Conference on Genetic Programming", year = "2015", editor = "Penousal Machado and Malcolm I. Heywood and James McDermott and Mauro Castelli and Pablo Garcia-Sanchez and Paolo Burelli and Sebastian Risi and Kevin Sim", series = "LNCS", volume = "9025", publisher = "Springer", pages = "3--15", address = "Copenhagen", month = "8-10 " # apr, organisation = "EvoStar", keywords = "genetic algorithms, genetic programming, Crossover, Crossover mask optimisation", isbn13 = "978-3-319-16500-4", DOI = "doi:10.1007/978-3-319-16501-1", abstract = "This paper investigates the impact of geometric semantic crossover operators in a wide range of symbolic regression problems. First, it analyses the impact of using Manhattan and Euclidean distance geometric semantic crossovers in the learning process. Then, it proposes two strategies to numerically optimise the crossover mask based on mathematical properties of these operators, instead of simply generating them randomly. An experimental analysis comparing geometric semantic crossovers using Euclidean and Manhattan distances and the proposed strategies is performed in a test bed of twenty datasets. The results show that the use of different distance functions in the semantic geometric crossover has little impact on the test error, and that our optimized crossover masks yield slightly better results. For SGP practitioners, we suggest the use of the semantic crossover based on the Euclidean distance, as it achieved similar results to those obtained by more complex operators.", notes = "Nominated for EuroGP 2015 Best Paper. Part of \cite{Machado:2015:GP} EuroGP'2015 held in conjunction with EvoCOP2015, EvoMusArt2015 and EvoApplications2015", } @Article{albrecht:2022:Polymers, author = "Hanny Albrecht and Wolfgang Roland and Christian Fiebig and Gerald Roman Berger-Weber", title = "Multi-Dimensional Regression Models for Predicting the Wall Thickness Distribution of Corrugated Pipes", journal = "Polymers", year = "2022", volume = "14", number = "17", pages = "Article No. 3455", keywords = "genetic algorithms, genetic programming", ISSN = "2073-4360", URL = "https://www.mdpi.com/2073-4360/14/17/3455", DOI = "doi:10.3390/polym14173455", abstract = "Corrugated pipes offer both higher stiffness and higher flexibility while simultaneously requiring less material than rigid pipes. Production rates of corrugated pipes have therefore increased significantly in recent years. Due to rising commodity prices, pipe manufacturers have been driven to produce corrugated pipes of high quality with reduced material input. To the best of our knowledge, corrugated pipe geometry and wall thickness distribution significantly influence pipe properties. Essential factors in optimising wall thickness distribution include adaptation of the mold block geometry and structure optimisation. To achieve these goals, a conventional approach would typically require numerous iterations over various pipe geometries, several mold block geometries, and then fabrication of pipes to be tested experimentally—an approach which is very time-consuming and costly. To address this issue, we developed multi-dimensional mathematical models that predict the wall thickness distribution in corrugated pipes as functions of the mold geometry by using symbolic regression based on genetic programming (GP). First, the blow molding problem was transformed into a dimensionless representation. Then, a screening study was performed to identify the most significant influencing parameters, which were subsequently varied within wide ranges as a basis for a comprehensive, numerically driven parametric design study. The data set obtained was used as input for data-driven modelling to derive novel regression models for predicting wall thickness distribution. Finally, model accuracy was confirmed by means of an error analysis that evaluated various statistical metrics. With our models, wall thickness distribution can now be predicted and subsequently used for structural analysis, thus enabling digital mold block design and optimising the wall thickness distribution.", notes = "also known as \cite{polym14173455}", } @InCollection{Albuquerque:2004:EMTP, author = "Ana Claudia M. L. Albuquerque and Jorge D. Melo and Adriao D. {Doria Neto}", title = "Evolutionary Computation and Parallel Processing Applied to the Design of Multilayer Perceptrons", year = "2004", booktitle = "Evolvable Machines: Theory \& Practice", pages = "181--203", volume = "161", series = "Studies in Fuzziness and Soft Computing", chapter = "8", editor = "Nadia Nedjah and Luiza {de Macedo Mourelle}", publisher = "Springer", address = "Berlin", keywords = "genetic algorithms", ISBN = "3-540-22905-1", URL = "http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-175-22-33980449-0,00.html", notes = "Springer says published in 2005 but available Nov 2004", } @InProceedings{albuquerque:2000:irfl, author = "Paul Albuquerque and Bastien Chopard and Christian Mazza and Marco Tomassini", title = "On the Impact of the Representation on Fitness Landscapes", booktitle = "Genetic Programming, Proceedings of EuroGP'2000", year = "2000", editor = "Riccardo Poli and Wolfgang Banzhaf and William B. Langdon and Julian F. Miller and Peter Nordin and Terence C. Fogarty", volume = "1802", series = "LNCS", pages = "1--15", address = "Edinburgh", publisher_address = "Berlin", month = "15-16 " # apr, organisation = "EvoNet", publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-67339-3", DOI = "doi:10.1007/978-3-540-46239-2_1", abstract = "In this paper we study the role of program representation on the properties of a type of Genetic Programming (GP) algorithm. In a specific case, which we believe to be generic of standard GP, we show that the way individuals are coded is an essential concept which impacts the fitness landscape. We give evidence that the ruggedness of the landscape affects the behavior of the algorithm and we find that, below a critical population, whose size is representation-dependent, premature convergence occurs.", notes = "EuroGP'2000, part of \cite{poli:2000:GP}", } @Article{alcaraz:2019:JMMP, author = "Joselito Yam II {Alcaraz} and Kunal Ahluwalia and Swee-Hock Yeo", title = "Predictive Models of {Double-Vibropolishing} in Bowl System Using Artificial Intelligence Methods", journal = "Journal of Manufacturing and Materials Processing", year = "2019", volume = "3", number = "1", keywords = "genetic algorithms, genetic programming, vibratory finishing, double vibro-polishing, artificial intelligence, regression, neural network, ANN", ISSN = "2504-4494", URL = "https://www.mdpi.com/2504-4494/3/1/27", DOI = "doi:10.3390/jmmp3010027", abstract = "Vibratory finishing is a versatile and efficient surface finishing process widely used to finish components of various functionalities. Research efforts were focused in fundamental understanding of the process through analytical solutions and simulations. On the other hand, predictive modelling of surface roughness using computational intelligence (CI) methods are emerging in recent years, though CI methods have not been extensively applied yet to a new vibratory finishing method called double-vibropolishing. In this study, multi-variable regression, artificial neural networks, and genetic programming models were designed and trained with experimental data obtained from subjecting rectangular Ti-6Al-4V test coupons to double vibropolishing in a bowl system configuration. Model selection was done by comparing the mean-absolute percentage error and r-squared values from both training and testing datasets. Exponential regression was determined as the best model for the bowl double-vibropolishing system studied with a Test MAPE score of 6.1percent and a R-squared score of 0.99. A family of curves was generated using the exponential regression model as a potential tool in predicting surface roughness with time.", notes = "also known as \cite{jmmp3010027}", } @Article{alcazar:2024:IJMS, author = "Jackson J. Alcazar", title = "Thiophene Stability in Photodynamic Therapy: A Mathematical Model Approach", journal = "International Journal of Molecular Sciences", year = "2024", volume = "25", number = "5", pages = "Article No. 2528", month = "21 " # feb, note = "Special Issue Molecular Aspects of Photodynamic Therapy", keywords = "genetic algorithms, genetic programming, safe PDT, efficient PDT, thiophene-containing photosensitiser, singlet oxygen, conceptual DFT", ISSN = "1422-0067", URL = "https://www.mdpi.com/1422-0067/25/5/2528", DOI = "doi:10.3390/ijms25052528", code_url = "https://github.com/Jacksonalcazar/Thiophene-Reactivity-toward-Singlet-Oxygen", size = "18 pages", abstract = "Thiophene-containing photosensitizers are gaining recognition for their role in photodynamic therapy (PDT). However, the inherent reactivity of the thiophene moiety toward singlet oxygen threatens the stability and efficiency of these photosensitizers. This study presents a novel mathematical model capable of predicting the reactivity of thiophene toward singlet oxygen in PDT, using Conceptual Density Functional Theory (CDFT) and genetic programming. The research combines advanced computational methods, including various DFT techniques and symbolic regression, and is validated with experimental data. The findings underscore the capacity of the model to classify photosensitizers based on their photodynamic efficiency and safety, particularly noting that photosensitizers with a constant rate 1000 times lower than that of unmodified thiophene retain their photodynamic performance without substantial singlet oxygen quenching. Additionally, the research offers insights into the impact of electronic effects on thiophene reactivity. Finally, this study significantly advances thiophene-based photosensitizer design, paving the way for therapeutic agents that achieve a desirable balance between efficiency and safety in PDT.", notes = "also known as \cite{ijms25052528} Centro de Quimica Medica, Facultad de Medicina Clinica Alemana, Universidad del Desarrollo, Santiago 7780272, Chile", } @InProceedings{Alchirch:2022:EuroGP, author = "Pantia-Marina Alchirch and Dimitrios I. Diochnos and Katia Papakonstantinopoulou", title = "Evolving Monotone Conjunctions in Regimes Beyond Proved Convergence", booktitle = "EuroGP 2022: Proceedings of the 25th European Conference on Genetic Programming", year = "2022", editor = "Eric Medvet and Gisele Pappa and Bing Xue", series = "LNCS", volume = "13223", publisher = "Springer Verlag", address = "Madrid, Spain", pages = "228--244", month = "20-22 " # apr, organisation = "EvoStar, Species", keywords = "genetic algorithms, genetic programming: Poster, Evolvability, Monotone conjunctions, Distribution-specific learning, Bernoulli (p)**n distributions", isbn13 = "978-3-031-02055-1", DOI = "doi:10.1007/978-3-031-02056-8_15", abstract = "Recently it was shown, using the typical mutation mechanism that is used in evolutionary algorithms, that monotone conjunctions are provably evolvable under a specific set of Bernoulli (p)n distributions. A natural question is whether this mutation mechanism allows convergence under other distributions as well. Our experiments indicate that the answer to this question is affirmative and, at the very least, this mechanism converges under Bernoulli (p)n distributions outside of the known proved regime.", notes = "Athens University of Economics and Business (TESLAB), Athens, Greece http://www.evostar.org/2022/eurogp/ Part of \cite{Medvet:2022:GP} EuroGP'2022 held inconjunction with EvoApplications2022 EvoCOP2022 EvoMusArt2022", } @InProceedings{Aldeia:2018:CEC, author = "Guilherme Aldeia and Fabricio {de Franca}", title = "Lightweight Symbolic Regression with the Interaction-Transformation Representation", booktitle = "2018 IEEE Congress on Evolutionary Computation (CEC)", year = "2018", editor = "Marley Vellasco", address = "Rio de Janeiro, Brazil", month = "8-13 " # jul, publisher = "IEEE", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CEC.2018.8477951", abstract = "Symbolic Regression techniques stand out from other regression analysis tools because of the possibility of generating powerful but yet simple expressions. These simple expressions may be useful in many practical situations in which the practitioner wants to interpret the obtained results, fine tune the model, or understand the generating phenomena. Despite this possibility, the current state-of-the-art algorithms for Symbolic Regression usually require a high computational budget while having little guarantees regarding the simplicity of the returned expressions. Recently, a new Data Structure representation for mathematical expressions, called Interaction-Transformation (IT), was introduced together with a search-based algorithm named SymTree that surpassed a subset of the recent Symbolic Regression algorithms and even some state-of-the-art nonlinear regression algorithms, while returning simple expressions as a result. This paper introduces a lightweight tool based on this algorithm, named Lab Assistant. This tool runs on the client-side of any compatible Internet browser with JavaScript. Alongside this tool, two algorithms using the IT representation are introduced. Some experiments are performed in order to show the potential of the Lab Assistant to help practitioners, professors, researchers and students willing to experiment with Symbolic Regression. The results showed that this tool is competent to find the correct expression for many well known Physics and Engineering relations within a reasonable average time frame of a few seconds. This tool opens up lots of possibilities in Symbolic Regression research for low-cost devices to be used in applications where a high-end computer is not available.", notes = "WCCI2018", } @InProceedings{Aldeia:2020:CEC, author = "Guilherme Aldeia and Fabricio {de Franca}", title = "A Parametric Study of Interaction-Transformation Evolutionary Algorithm for Symbolic Regression", booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC 2020", year = "2020", editor = "Yaochu Jin", pages = "paper id24027", address = "internet", month = "19-24 " # jul, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-7281-6929-3", DOI = "doi:10.1109/CEC48606.2020.9185521", abstract = "The balance between approximation error and model complexity is an important trade-off for Symbolic Regression algorithms. This trade-off is achieved by means of specific operators for bloat control, modified operators, limits to the size of the generated expressions and multi-objective optimization. Recently, the representation Interaction-Transformation was introduced with the goal of limiting the search space to simpler expressions, thus avoiding bloating. This representation was used in the context of an Evolutionary Algorithm in order to find concise expressions resulting in small approximation errors competitive with the literature. Particular to this algorithm, two parameters control the complexity of the generated expression. This paper investigates the influence of those parameters w.r.t. the goodness-of-fit. Through some extensive experiments, we find that the maximum number of terms is more important to control goodness-of-fit but also that there is a limit to the extent that increasing its value renders any benefits. Second, the limit to the minimum and maximum value of the exponent has a smaller influence to the results and it can be set to a default value without impacting the final results.", notes = "https://wcci2020.org/ Federal University of ABC, Brazil", } @InProceedings{Aldeia:2021:GECCO, author = "Guilherme Seidyo Imai Aldeia and Fabricio {Olivetti de Franca}", title = "Measuring Feature Importance of Symbolic Regression Models Using Partial Effects", booktitle = "Proceedings of the 2021 Genetic and Evolutionary Computation Conference", year = "2021", editor = "Francisco Chicano and Alberto Tonda and Krzysztof Krawiec and Marde Helbig and Christopher W. Cleghorn and Dennis G. Wilson and Georgios Yannakakis and Luis Paquete and Gabriela Ochoa and Jaume Bacardit and Christian Gagne and Sanaz Mostaghim and Laetitia Jourdan and Oliver Schuetze and Petr Posik and Carlos Segura and Renato Tinos and Carlos Cotta and Malcolm Heywood and Mengjie Zhang and Leonardo Trujillo and Risto Miikkulainen and Bing Xue and Aneta Neumann and Richard Allmendinger and Fuyuki Ishikawa and Inmaculada Medina-Bulo and Frank Neumann and Andrew M. Sutton", pages = "750--758", address = "internet", series = "GECCO '21", month = jul # " 10-14", organisation = "SIGEVO", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, XAI, explainable AI, symbolic regression, interaction-transformation, Supervised learning, SHAP, Shapley value", isbn13 = "9781450383509", DOI = "doi:10.1145/3449639.3459302", size = "9 pages", abstract = "In explainable AI, one aspect of a prediction's explanation is to measure each predictor's importance to the decision process.The importance can measure how much variation a predictor promotes locally or how much the predictor contributes to the deviation from a reference point (Shapley value). If we have the ground truth analytical model, we can calculate the former using the Partial Effect, calculated as the predictor's partial derivative. Also, we can estimate the latter by calculating the average partial effect multiplied by the difference between the predictor and the reference value. Symbolic Regression is a gray-box model for regression problems that returns an analytical model approximating the input data. Although it is often associated with interpretability, few works explore this property. We will investigate the use of Partial Effect with the analytical models generated by the Interaction-Transformation Evolutionary Algorithm symbolic regressor (ITEA). We show that the regression models returned by ITEA coupled with Partial Effect provide the closest explanations to the ground truth and a close approximation to Shapley values. These results openup new opportunities to explain symbolic regression modelscompared to the approximations provided by model agnostic approaches.", notes = "PE-ITEA AI-Feynman datasets See also \cite{Aldeia:2022:GPEM} UFABC, Santo Andre, SP, Brazil GECCO-2021 A Recombination of the 30th International Conference on Genetic Algorithms (ICGA) and the 26th Annual Genetic Programming Conference (GP)", } @InProceedings{aldeia:2022:SymReg, author = "Guilherme Seidyo Imai Aldeia and Fabricio {Olivetti de Franca}", title = "{Interaction-Transformation} Evolutionary Algorithm with coefficients optimization", booktitle = "Proceedings of the 2022 Genetic and Evolutionary Computation Conference Companion", year = "2022", editor = "Heike Trautmann and Carola Doerr and Alberto Moraglio and Thomas Bartz-Beielstein and Bogdan Filipic and Marcus Gallagher and Yew-Soon Ong and Abhishek Gupta and Anna V Kononova and Hao Wang and Michael Emmerich and Peter A. N. Bosman and Daniela Zaharie and Fabio Caraffini and Johann Dreo and Anne Auger and Konstantin Dietric and Paul Dufosse and Tobias Glasmachers and Nikolaus Hansen and Olaf Mersmann and Petr Posik and Tea Tusar and Dimo Brockhoff and Tome Eftimov and Pascal Kerschke and Boris Naujoks and Mike Preuss and Vanessa Volz and Bilel Derbel and Ke Li and Xiaodong Li and Saul Zapotecas and Qingfu Zhang and Mark Coletti and Catherine (Katie) Schuman and Eric ``Siggy'' Scott and Robert Patton and Paul Wiegand and Jeffrey K. Bassett and Chathika Gunaratne and Tinkle Chugh and Richard Allmendinger and Jussi Hakanen and Daniel Tauritz and John Woodward and Manuel Lopez-Ibanez and John McCall and Jaume Bacardit and Alexander Brownlee and Stefano Cagnoni and Giovanni Iacca and David Walker and Jamal Toutouh and UnaMay O'Reilly and Penousal Machado and Joao Correia and Sergio Nesmachnow and Josu Ceberio and Rafael Villanueva and Ignacio Hidalgo and Francisco {Fernandez de Vega} and Giuseppe Paolo and Alex Coninx and Antoine Cully and Adam Gaier and Stefan Wagner and Michael Affenzeller and Bobby R. Bruce and Vesna Nowack and Aymeric Blot and Emily Winter and William B. Langdon and Justyna Petke and Silvino {Fernandez Alzueta} and Pablo {Valledor Pellicer} and Thomas Stuetzle and David Paetzel and Alexander Wagner and Michael Heider and Nadarajen Veerapen and Katherine Malan and Arnaud Liefooghe and Sebastien Verel and Gabriela Ochoa and Mohammad Nabi Omidvar and Yuan Sun and Ernesto Tarantino and De Falco Ivanoe and Antonio {Della Cioppa} and Scafuri Umberto and John Rieffel and Jean-Baptiste Mouret and Stephane Doncieux and Stefanos Nikolaidis and Julian Togelius and Matthew C. Fontaine and Serban Georgescu and Francisco Chicano and Darrell Whitley and Oleksandr Kyriienko and Denny Dahl and Ofer Shir and Lee Spector and Alma Rahat and Richard Everson and Jonathan Fieldsend and Handing Wang and Yaochu Jin and Erik Hemberg and Marwa A. Elsayed and Michael Kommenda and William {La Cava} and Gabriel Kronberger and Steven Gustafson", pages = "2274--2281", address = "Boston, USA", series = "GECCO '22", month = "9-13 " # jul, organisation = "SIGEVO", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, Representation of mathematical functions, symbolic regression, coefficient optimization, benchmark, evolutionary algorithm", isbn13 = "978-1-4503-9268-6/22/07", DOI = "doi:10.1145/3520304.3533987", size = "8 pages", abstract = "Symbolic Regression is the task of finding a mathematical expression to describe the relationship between one or more independent variables with a dependent variable. The search space can be vast and include any algebraic function; thus, finding optimal values for coefficients may not be a trivial task. The Interaction-Transformation representation alleviates this problem enforcing that the coefficients of the expression is part of a linear transformation, allowing the application of least squares. But this solution also limits the search space of the expressions. This paper proposes four different strategies to optimize the coefficients of the nonlinear part of the Interaction-Transformation representation. We benchmark the proposed strategies by applying the Interaction-Transformation Evolutionary Algorithm (ITEA) to six well-known data sets to evaluate four optimization heuristics combining linear and non-linear methods. The results show that optimizing the non-linear and linear coefficients separately was the best strategy to find better-performing expressions with a higher run-time and expression size. The non-linear optimization method alone was the worst-performing method.", notes = "GECCO-2022 A Recombination of the 31st International Conference on Genetic Algorithms (ICGA) and the 27th Annual Genetic Programming Conference (GP)", } @Article{Aldeia:2022:GPEM, author = "Guilherme Seidyo Imai Aldeia and Fabricio {Olivetti de Franca}", title = "Interpretability in symbolic regression: a benchmark of explanatory methods using the {Feynman} data set", journal = "Genetic Programming and Evolvable Machines", year = "2022", volume = "23", number = "3", pages = "309--349", month = sep, note = "Special Issue: Highlights of Genetic Programming 2021 Events", keywords = "genetic algorithms, genetic programming, Symbolic regression, Explanatory methods, Feature importance attribution, Benchmark", ISSN = "1389-2576", DOI = "doi:10.1007/s10710-022-09435-x", code_url = "https://github.com/gAldeia/iirsBenchmark", abstract = "In some situations, the interpretability of the machine learning models plays a role as important as the model accuracy. Interpretability comes from the need to trust the prediction model, verify some of its properties, or even enforce them to improve fairness. Many model-agnostic explanatory methods exists to provide explanations for black-box models. In the regression task, the practitioner can use white-boxes or gray-boxes models to achieve more interpretable results, which is the case of symbolic regression. When using an explanatory method, and since interpretability lacks a rigorous definition, there is a need to evaluate and compare the quality and different explainers. This paper proposes a benchmark scheme to evaluate explanatory methods to explain regression models, mainly symbolic regression models. Experiments were performed using 100 physics equations with different interpretable and non-interpretable regression methods and popular explanation methods, evaluating the performance of the explainers performance with several explanation measures. In addition, we further analyzed four benchmarks from the GP community. The results have shown that Symbolic Regression models can be an interesting alternative to white-box and black-box models that is capable of returning accurate models with appropriate explanations. Regarding the explainers, we observed that Partial Effects and SHAP were the most robust explanation models, with Integrated Gradients being unstable only with tree-based models. This benchmark is publicly available for further experiments.", } @InCollection{alderson:1999:TTCNDUEM, author = "David Alderson", title = "Toward a Technique for Cooperative Network Design Using Evolutionary Methods", booktitle = "Genetic Algorithms and Genetic Programming at Stanford 1999", year = "1999", editor = "John R. Koza", pages = "1--10", address = "Stanford, California, 94305-3079 USA", month = "15 " # mar, publisher = "Stanford Bookstore", keywords = "genetic algorithms", notes = "part of \cite{koza:1999:GAGPs}", } @Article{ALDREES:2024:jwpe, author = "Ali Aldrees and Majid Khan and Abubakr Taha Bakheit Taha and Mujahid Ali", title = "Evaluation of water quality indexes with novel machine learning and {SHapley} Additive {ExPlanation} ({SHAP)} approaches", journal = "Journal of Water Process Engineering", volume = "58", pages = "104789", year = "2024", ISSN = "2214-7144", DOI = "doi:10.1016/j.jwpe.2024.104789", URL = "https://www.sciencedirect.com/science/article/pii/S2214714424000199", keywords = "genetic algorithms, genetic programming, Gene expression programming, Water quality indexes, ANN, Deep neural networks, Optimizable Gaussian process regressor, SHAP", abstract = "Water quality indexes (WQI) are pivotal in assessing aquatic systems. Conventional modeling approaches rely on extensive datasets with numerous unspecified inputs, leading to time-consuming WQI assessment procedures. Numerous studies have used machine learning (ML) methods for WQI analysis but often lack model interpretability. To address this issue, this study developed five interpretable predictive models, including two gene expression programming (GEP) models, two deep neural networks (DNN) models, and one optimizable Gaussian process regressor (OGPR) model for estimating electrical conductivity (EC) and total dissolved solids (TDS). For the model development, a total of 372 records on a monthly basis were collected in the Upper Indus River at two outlet stations. The efficacy and accuracy of the models were assessed using various statistical measures, such as correlation (R), mean square error (MAE), root mean square error (RMSE), and 5-fold cross-validation. The DNN2 model demonstrated outstanding performance compared to the other five models, exhibiting R-values closer to 1.0 for both EC and TDS. However, the genetic programming-based models, GEP1 and GEP2, exhibited comparatively lower accuracy in predicting the water quality indexes. The SHapely Additive exPlanation (SHAP) analysis revealed that bicarbonate, calcium, and sulphate jointly contribute approximately 78 percent to EC, while the combined presence of sodium, bicarbonate, calcium, and magnesium accounts for around 87 percent of TDS in water. Notably, the influence of pH and chloride was minimal on both water quality indexes. In conclusion, the study highlights the cost-effective and practical potential of predictive models for EC and TDS in assessing and monitoring river water quality", } @InProceedings{Aleb:2012:GECCOcomp, author = "Nassima Aleb and Samir Kechid", title = "A new framework for scalable genetic programming", booktitle = "GECCO 2012 Symbolic regression and modeling workshop", year = "2012", editor = "Steven Gustafson and Ekaterina Vladislavleva", isbn13 = "978-1-4503-1178-6", keywords = "genetic algorithms, genetic programming", pages = "487--492", month = "7-11 " # jul, organisation = "SIGEVO", address = "Philadelphia, Pennsylvania, USA", DOI = "doi:10.1145/2330784.2330859", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "This paper presents a novel framework for scalable multi-objective genetic programming. We introduce a new program modeling aiming at facilitating programs' creation, execution and improvement. The proposed modeling allows making symbolic executions in such a way to reduce drastically the time of programs' executions and to allow well-founded programs recombination.", notes = "Also known as \cite{2330859} Distributed at GECCO-2012. ACM Order Number 910122.", } @InProceedings{Aleb:2013:GECCOcomp, author = "Nassima Aleb and Samir Kechid", title = "An interpolation based crossover operator for genetic programming", booktitle = "GECCO '13 Companion: Proceeding of the fifteenth annual conference companion on Genetic and evolutionary computation conference companion", year = "2013", editor = "Christian Blum and Enrique Alba and Thomas Bartz-Beielstein and Daniele Loiacono and Francisco Luna and Joern Mehnen and Gabriela Ochoa and Mike Preuss and Emilia Tantar and Leonardo Vanneschi and Kent McClymont and Ed Keedwell and Emma Hart and Kevin Sim and Steven Gustafson and Ekaterina Vladislavleva and Anne Auger and Bernd Bischl and Dimo Brockhoff and Nikolaus Hansen and Olaf Mersmann and Petr Posik and Heike Trautmann and Muhammad Iqbal and Kamran Shafi and Ryan Urbanowicz and Stefan Wagner and Michael Affenzeller and David Walker and Richard Everson and Jonathan Fieldsend and Forrest Stonedahl and William Rand and Stephen L. Smith and Stefano Cagnoni and Robert M. Patton and Gisele L. Pappa and John Woodward and Jerry Swan and Krzysztof Krawiec and Alexandru-Adrian Tantar and Peter A. N. Bosman and Miguel Vega-Rodriguez and Jose M. Chaves-Gonzalez and David L. Gonzalez-Alvarez and Sergio Santander-Jimenez and Lee Spector and Maarten Keijzer and Kenneth Holladay and Tea Tusar and Boris Naujoks", isbn13 = "978-1-4503-1964-5", keywords = "genetic algorithms, genetic programming", pages = "1107--1112", month = "6-10 " # jul, organisation = "SIGEVO", address = "Amsterdam, The Netherlands", DOI = "doi:10.1145/2464576.2482689", publisher = "ACM", publisher_address = "New York, NY, USA", abstract = "This paper presents a new crossover operator for genetic programming. We exploit two concepts of formal methods: Weakest precondition and Craig interpolation, to perform semantically aware crossover. Weakest preconditions are used to locate faulty parts of a program and Craig interpolation is used to correct these ones.", notes = "Also known as \cite{2482689} Distributed at GECCO-2013.", } @Article{Aleksandrov:2013:JCSSI, author = "A. V. Aleksandrov and S. V. Kazakov and A. A. Sergushichev and F. N. Tsarev and A. A. Shalyto", title = "The use of evolutionary programming based on training examples for the generation of finite state machines for controlling objects with complex behavior", journal = "Journal of Computer and Systems Sciences International", year = "2013", volume = "52", number = "3", pages = "410--425", month = may, publisher = "SP MAIK Nauka/Interperiodica", language = "English", keywords = "genetic algorithms, genetic programming, FSM", ISSN = "1064-2307", DOI = "doi:10.1134/S1064230713020020", size = "16 pages", abstract = "It is proposed to use evolutionary programming to generate finite state machines (FSMs) for controlling objects with complex behaviour. The well-know approach in which the FSM performance is evaluated by simulation, which is typically time consuming, is replaced with comparison of the object's behaviour controlled by the FSM with the behaviour of this object controlled by a human. A feature of the proposed approach is that it makes it possible to deal with objects that have not only discrete but also continuous parameters. The use of this approach is illustrated by designing an FSM controlling a model aircraft executing a loop-the-loop manoeuvre.", notes = " Original Russian Text A.V. Aleksandrov, S.V. Kazakov, A.A. Sergushichev, F.N. Tsarev, A.A. Shalyto, 2013, published in Izvestiya Akademii Nauk. Teoriya i Sistemy Upravleniya, 2013, No. 3, pp. 85-100. Translated by A. Klimontovich", } @Article{Alekseeva:2018:Algorithms, author = "Natalia Alekseeva and Ivan Tanev and Katsunori Shimohara", title = "Evolving the Controller of Automated Steering of a Car in Slippery Road Conditions", journal = "Algorithms", year = "2018", volume = "11", number = "7", pages = "108", month = jul, note = "Special Issue Algorithms for PID Controller", keywords = "genetic algorithms, genetic programming, autonomous vehicles, automated steering, slippery road conditions, PID controllers", ISSN = "1999-4893", URL = "http://www.mdpi.com/1999-4893/11/7/108", URL = "http://www.mdpi.com/1999-4893/11/7/108/pdf", URL = "https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902252618556627", DOI = "doi:10.3390/a11070108", size = "17 pages", abstract = "The most important characteristics of autonomous vehicles are their safety and their ability to adapt to various traffic situations and road conditions. In our research, we focused on the development of controllers for automated steering of a realistically simulated car in slippery road conditions. We comparatively investigated three implementations of such controllers: a proportional-derivative (PD) controller built in accordance with the canonical servo-control model of steering, a PID controller as an extension of the servo-control, and a controller designed heuristically via the most versatile evolutionary computing paradigm: genetic programming (GP). The experimental results suggest that the controller evolved via GP offers the best quality of control of the car in all of the tested slippery (rainy, snowy, and icy) road conditions.", notes = "Department of Information Systems Design, Faculty of Engineering, Doshisha University 1-3, Tatara Miyakodani, Kyotanabe City, Kyoto 610-0394, Japan http://www.mdpi.com/journal/algorithms", } @InProceedings{Alekseeva:2019:AIM, author = "Natalia Alekseeva and Ivan Tanev and Katsunori Shimohara", booktitle = "2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)", title = "On the Emergence of Oscillations in the Evolved Autosteering of a Car on Slippery Roads", year = "2019", pages = "1371--1378", month = "8-12 " # jul, address = "Hong Kong", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-7281-2494-0", DOI = "doi:10.1109/AIM.2019.8868610", ISSN = "2159-6255", abstract = "One of the important features of autonomous vehicles is their versatility to various traffic situations and road conditions. We explore the feasibility of using genetic programming to develop an adequate auto-steering of a car in slippery road conditions. We also investigate an important emergent property of the best-evolved steering solutions - the steering oscillations - and discuss how these oscillations contribute to the better controllability of the sliding car. We present the limitations and the technical challenges of the real world implementation of steering oscillations.", notes = "Also known as \cite{8868610}", } @Article{DBLP:journals/algorithms/AlekseevaTS20, author = "Natalia Alekseeva and Ivan Tanev and Katsunori Shimohara", title = "{PD} Steering Controller Utilizing the Predicted Position on Track for Autonomous Vehicles Driven on Slippery Roads", journal = "Algorithms", year = "2020", volume = "13", number = "2", pages = "id 48", month = feb, keywords = "genetic algorithms, genetic programming, autonomous vehicles, automated steering, slippery road conditions, PD controllers, predictive model", timestamp = "Thu, 19 Mar 2020 10:23:44 +0100", biburl = "https://dblp.org/rec/journals/algorithms/AlekseevaTS20.bib", bibsource = "dblp computer science bibliography, https://dblp.org", URL = "https://www.mdpi.com/1999-4893/13/2/48/pdf", DOI = "doi:10.3390/a13020048", size = "17 pages", abstract = "Among the most important characteristics of autonomous vehicles are the safety and robustness in various traffic situations and road conditions. In this paper, we focus on the development and analysis of the extended version of the canonical proportional-derivative PD controllers that are known to provide a good quality of steering on non-slippery (dry) roads. However, on slippery roads, due to the poor yaw controllability of the vehicle (suffering from understeering and oversteering), the quality of control of such controllers deteriorates. The proposed predicted PD controller (PPD controller) overcomes the main drawback of PD controllers, namely, the reactiveness of their steering behavior. The latter implies that steering output is a direct result of the currently perceived lateral- and angular deviation of the vehicle from its intended, ideal trajectory, which is the center of the lane. This reactiveness, combined with the tardiness of the yaw control of the vehicle on slippery roads, results in a significant lag in the control loop that could not be compensated completely by the predictive (derivative) component of these controllers. In our approach, keeping the controller efforts at the same level as in PD controllers by avoiding (i) complex computations and (ii) adding additional variables, the PPD controller shows better quality of steering than that of the evolved (via genetic programming) models.", } @Article{Alemdag:2016:EG, author = "S. Alemdag and Z. Gurocak and A. Cevik and A. F. Cabalar and C. Gokceoglu", title = "Modeling deformation modulus of a stratified sedimentary rock mass using neural network, fuzzy inference and genetic programming", journal = "Engineering Geology", volume = "203", pages = "70--82", year = "2016", note = "Special Issue on Probabilistic and Soft Computing Methods for Engineering Geology", ISSN = "0013-7952", DOI = "doi:10.1016/j.enggeo.2015.12.002", URL = "http://www.sciencedirect.com/science/article/pii/S0013795215300971", abstract = "This paper investigates a series of experimental results and numerical simulations employed to estimate the deformation modulus of a stratified rock mass. The deformation modulus of rock mass has a significant importance for some applications in engineering geology and geotechnical projects including foundation, slope, and tunnel designs. Deformation modulus of a rock mass can be determined using large scale in-situ tests. This large scale sophisticated in-situ testing equipments are sometimes difficult to install, plus time consuming to be employed in the field. Therefore, this study aims to estimate indirectly the deformation modulus values via empirical methods such as the neural network, neuro fuzzy and genetic programming approaches. A series of analyses have been developed for correlating various relationships between the deformation modulus of rock mass, rock mass rating, rock quality designation, uniaxial compressive strength, and elasticity modulus of intact rock parameters. The performance capacities of proposed models are assessed and found as quite satisfactory. At the completion of a comparative study on the accuracy of models, in the results, it is seen that overall genetic programming models yielded more precise results than neural network and neuro fuzzy models.", keywords = "genetic algorithms, genetic programming, Deformation modulus, Rock mass, Neural network, Neuro fuzzy", notes = "Department of Geological Engineering, Gumushane University, Gumushane 29000, Turkey", } @InProceedings{aler:1998:5parity, author = "Ricardo Aler", title = "Immediate transference of global improvements to all individuals in a population in Genetic Programming compared to Automatically Defined Functions for the EVEN-5 PARITY problem", booktitle = "Proceedings of the First European Workshop on Genetic Programming", year = "1998", editor = "Wolfgang Banzhaf and Riccardo Poli and Marc Schoenauer and Terence C. Fogarty", volume = "1391", series = "LNCS", pages = "60--70", address = "Paris", publisher_address = "Berlin", month = "14-15 " # apr, publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-64360-5", DOI = "doi:10.1007/BFb0055928", abstract = "Koza has shown how automatically defined functions (ADFs) can reduce computational effort in the GP paradigm. In Koza's ADF, as well as in standard GP, an improvement in a part of a program (an ADF or a main body) can only be transferred via crossover. In this article, we consider whether it is a good idea to transfer immediately improvements found by a single individual to the whole population. A system that implements this idea has been proposed and tested for the EVEN-5-PARITY and EVEN-6-PARITY problems. Results are very encouraging: computational effort is reduced (compared to Koza's ADFs) and the system seems to be less prone to early stagnation. Finally, our work suggests further research where less extreme approaches to our idea could be tested.", notes = "EuroGP'98", affiliation = "Universidad Carlos III de Madrid Butarque 15 28911 Leganes Madrid Espana Butarque 15 28911 Leganes Madrid Espana", } @InProceedings{aler:1998:ehp, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "Evolved Heuristics for Planning", booktitle = "Evolutionary Programming VII: Proceedings of the Seventh Annual Conference on Evolutionary Programming", year = "1998", editor = "V. William Porto and N. Saravanan and D. Waagen and A. E. Eiben", volume = "1447", series = "LNCS", pages = "745--754", address = "Mission Valley Marriott, San Diego, California, USA", publisher_address = "Berlin", month = "25-27 " # mar, publisher = "Springer-Verlag", keywords = "genetic algorithms, genetic programming", ISBN = "3-540-64891-7", DOI = "doi:10.1007/BFb0040753", notes = "EP-98 http://www.springer.de/cgi-bin/search_book.pl?isbn=3-540-64891-7 EvoCK compared with PRODIGY. HAMLET. Blocksworld domain.", } @InProceedings{icml98-ricardo, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "Genetic Programming and Deductive-Inductive Learning: A Multistrategy Approach", booktitle = "Proceedings of the Fifteenth International Conference on Machine Learning, ICML'98", year = "1998", editor = "Jude Shavlik", pages = "10--18", address = "Madison, Wisconsin, USA", month = jul, publisher = "Morgan Kaufmann", keywords = "genetic algorithms, genetic programming, Learning in Planning, Multistrategy learning", ISBN = "1-55860-556-8", URL = "http://scalab.uc3m.es/~dborrajo/papers/icml98.ps.gz", size = "9 pages", abstract = "Genetic Programming (GP) is a machine learning technique that was not conceived to use domain knowledge for generating new candidate solutions. It has been shown that GP can benefit from domain knowledge obtained by other machine learning methods with more powerful heuristics. However, it is not obvious that a combination of GP and a knowledge intensive machine learning method can work better than the knowledge intensive method alone. In this paper we present a multistrategy approach where an already multistrategy approach ({\sc hamlet} combines analytical and inductive learning) and an evolutionary technique based on GP (EvoCK) are combined for the task of learning control rules for problem solving in planning. Results show that both methods complement each other, supplying to the other method what the other method lacks and obtaining better results than using each method alone.", notes = "ICML'98 http://www.cs.wisc.edu/icml98/ blocksworld many random problems generated in order to train system. No crossover, steady state population size = 2, tournament size = 2", } @PhdThesis{aler:thesis, author = "Ricardo Aler Mur", title = "Programacion Genetica de Heuristicas para Planificacion", school = "Facultad de Informatica de la Universidad Politecnica de Madrid", year = "1999", address = "Spain", month = jul, keywords = "genetic algorithms, genetic programming, Planning, Problem Solving, Rule Based System", URL = "http://oa.upm.es/1101/1/10199907.pdf", size = "167 pages", abstract = "The aim of this thesis is to use and extend the machine learning genetic programming (GP) paradigm to learn control knowledge for domain independent planning. GP will be used as a standalone technique and as part of a multi-strategy system. Planning is the problem of finding a sequence of steps to transform an initial state in a final state. Finding a correct plan is NP-hard. A solution proposed by Artificial Intelligence is to augment a domain independent planner with control knowledge, to improve its efficiency. Machine learning techniques are used for that purpose. However, although a lot has been achieved, the domain independent planning problem has not been solved completely, therefore there is still room for research. The reason for using GP to learn planning control knowledge is twofold. First, it is intended for exploring the control knowledge space in a less biased way than other techniques. Besides, learning search control knowledge with GP will consider the planning system, the domain theory, planning search and efficiency measures in a global manner, all at the same time. Second, GP flexibility will be used to add useful biases and characteristics to another learning method that lacks them (that is, a multi-strategy GP based system). In the present work, Prodigy will be used as the base planner and Hamlet will be used as the learning system to which useful characteristics will be added through GP. In other words, GP will be used to solve some of Hamlet limitations by adding new biases/characteristics to Hamlet. In addition to the main goal, this thesis will design and experiment with methods to add background knowledge to a GP system, without modifying its basic algorithm. The first method seeds the initial population with individuals obtained by another method (Hamlet). Actually, this is the multi-strategy system discussed in the later paragraph. The second method uses a new genetic operator (instance based crossover) that is able to use instances/examples to bias its search, like other machine learning techniques. To test the validity of the methods proposed, extensive empirical and statistical validation will be carried out.", notes = "In Spanish: Genetic Programming of Heuristics for Planning School of Computer Science at Polytechnic University of Madrid Author: Ricardo Aler Mur Supervisors: Daniel Borrajo Millan and Pedro Isasi Vinuela ", } @InProceedings{aler:2000:G, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "GP fitness functions to evolve heuristics for planning", booktitle = "Evolutionary Methods for AI Planning", year = "2000", editor = "Martin Middendorf", pages = "189--195", address = "Las Vegas, Nevada, USA", month = "8 " # jul, keywords = "genetic algorithms, genetic programming", URL = "http://scalab.uc3m.es/~dborrajo/papers/gecco00.ps.gz", abstract = "There are several ways of applying Genetic Programming (GP) to STRIPS-like planning in the literature. In this paper we emphasise the use of a new one, based on learning heuristics for planning. In particular, we focus on the design of fitness functions for this task. We explore two alternatives (black and white box fitness functions) and present some empirical results", size = "5 pages", notes = "GECCO-2000WKS Part of \cite{wu:2000:GECCOWKS}", } @InProceedings{oai:CiteSeerPSU:341634, title = "Knowledge Representation Issues in Control Knowledge Learning", author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", booktitle = "Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)", year = "2000", editor = "Pat Langley", pages = "1--8", address = "Stanford University, Standord, CA, USA", month = jun # " 29 - " # jul # " 2", publisher = "Morgan Kaufmann", keywords = "genetic algorithms, genetic programming, EBL, HAMLET, EVOCK", ISBN = "1-55860-707-2", bibsource = "DBLP, http://dblp.uni-trier.de", URL = "http://scalab.uc3m.es/~dborrajo/papers/icml00.ps.gz", URL = "http://dl.acm.org/citation.cfm?id=645529.657964", acmid = "657964", URL = "http://citeseer.ist.psu.edu/341634.html", citeseer-isreferencedby = "oai:CiteSeerPSU:42967", citeseer-references = "oai:CiteSeerPSU:104987; oai:CiteSeerPSU:15322; oai:CiteSeerPSU:554819", annote = "The Pennsylvania State University CiteSeer Archives", language = "en", oai = "oai:CiteSeerPSU:341634", rights = "unrestricted", size = "8 pages", abstract = "Knowledge representation is a key issue for any machine learning task. There have already been many comparative studies about knowledge representation with respect to machine learning in classification tasks. However, apart from some work done on reinforcement learning techniques in relation to state representation, very few studies have concentrated on the effect of knowledge representation for machine learning applied to problem solving, and more specifically, to planning. In this paper, we present an experimental comparative study of the effect of changing the input representation of planning domain knowledge on control knowledge learning. We show results in two classical domains using three different machine learning systems, that have previously shown their effectiveness on learning planning control knowledge: a pure EBL mechanism, a combination of EBL and induction (HAMLET), and a Genetic Programming based system (EVOCK).", notes = "Also known as \cite{Aler:2000:KRI:645529.657964} http://www.informatik.uni-trier.de/~ley/db/conf/icml/icml2000.html ICML 2000", } @InProceedings{aler:2001:glckg, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "Grammars for Learning Control Knowledge with GP", booktitle = "Proceedings of the 2001 Congress on Evolutionary Computation CEC2001", year = "2001", pages = "1220--1227", address = "COEX, World Trade Center, 159 Samseong-dong, Gangnam-gu, Seoul, Korea", publisher_address = "445 Hoes Lane, P.O. Box 1331, Piscataway, NJ 08855-1331, USA", month = "27-30 " # may, organisation = "IEEE Neural Network Council (NNC), Evolutionary Programming Society (EPS), Institution of Electrical Engineers (IEE)", publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, computational linguistics, grammars, learning (artificial intelligence), search problems, AI planning system, EVOCK, Evolution of Control Knowledge, GP based system, PRODIGY, ad-hoc mechanisms, blocksworld domain, control knowledge learning, control rule language, control rule syntax, control rules, grammar approach flexibility, grammar specific, grammars, language restrictions, search space, standard GP, standard select type", ISBN = "0-7803-6658-1", URL = "http://scalab.uc3m.es/~dborrajo/papers/cec01.ps.gz", DOI = "doi:10.1109/CEC.2001.934330", size = "8 pages", abstract = "In standard GP there are no constraints on the structure to evolve: any combination of functions and terminals is valid. However, sometimes GP is used to evolve structures that must respect some constraints. Instead of ad-hoc mechanisms, grammars can be used to guarantee that individuals comply with the language restrictions. In addition, grammars permit great flexibility to define the search space. EVOCK (Evolution of Control Knowledge) is a GP based system that learns control rules for PRODIGY, an AI planning system. EVOCK uses a grammar to constrain individuals to PRODIGY 4.0 control rule syntax. The authors describe the grammar specific details of EVOCK. Also, the grammar approach flexibility has been used to extend the control rule language used by EVOCK in earlier work. Using this flexibility, tests were performed to determine whether using combinations of several types of control rules for planning was better than using only the standard select type. Experiments have been carried out in the blocksworld domain that show that using the combination of types of control rules does not get better individuals, but it produces good individuals more frequently", notes = "CEC-2001 - A joint meeting of the IEEE, Evolutionary Programming Society, Galesia, and the IEE. IEEE Catalog Number = 01TH8546C, Library of Congress Number = . EVOCK, PRODIGY 4.0, blocksworld", } @Article{aler:2001:ECJ, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "Learning to Solve Planning Problems Efficiently by Means of Genetic Programming", journal = "Evolutionary Computation", year = "2001", volume = "9", number = "4", pages = "387--420", month = "Winter", keywords = "genetic algorithms, genetic programming, genetic planning, evolving heuristics, planning, search. EvoCK, STGP, blocks world, logistics, Prodigy4.0, STRIPS, PDL40.", ISSN = "1063-6560", URL = "http://www.mitpressjournals.org/doi/pdf/10.1162/10636560152642841", DOI = "doi:10.1162/10636560152642841", size = "34 pages", abstract = "Declarative problem solving, such as planning, poses interesting challenges for Genetic Programming (GP). There have been recent attempts to apply GP to planning that fit two approaches: (a) using GP to search in plan space or (b) to evolve a planner. In this article, we propose to evolve only the heuristics to make a particular planner more efficient. This approach is more feasible than (b) because it does not have to build a planner from scratch but can take advantage of already existing planning systems. It is also more efficient than (a) because once the heuristics have been evolved, they can be used to solve a whole class of different planning problems in a planning domain, instead of running GP for every new planning problem. Empirical results show that our approach (EVOCK) is able to evolve heuristics in two planning domains (the blocks world and the logistics domain) that improve PRODIGY4.0 performance. Additionally, we experiment with a new genetic operator Instance-Based Crossover that is able to use traces of the base planner as raw genetic material to be injected into the evolving population.", } @Article{aler:2002:AI, author = "Ricardo Aler and Daniel Borrajo and Pedro Isasi", title = "Using genetic programming to learn and improve control knowledge", journal = "Artificial Intelligence", year = "2002", volume = "141", number = "1-2", pages = "29--56", month = oct, keywords = "genetic algorithms, genetic programming, Speedup learning, Multi-strategy learning, Planning", URL = "http://scalab.uc3m.es/~dborrajo/papers/aij-evock.ps.gz", URL = "http://citeseer.ist.psu.edu/511810.html", DOI = "doi:10.1016/S0004-3702(02)00246-1", abstract = "The purpose of this article is to present a multi-strategy approach to learn heuristics for planning. This multi-strategy system, called HAMLET-EVOCK, combines a learning algorithm specialised in planning () and a genetic programming (GP) based system (: Evolution of Control Knowledge). Both systems are able to learn heuristics for planning on their own, but both of them have weaknesses. Based on previous experience and some experiments performed in this article, it is hypothesised that handicaps are due to its example-driven operators and not having a way to evaluate the usefulness of its control knowledge. It is also hypothesized that even if control knowledge is sometimes incorrect, it might be easily correctable. For this purpose, a GP-based stage is added, because of its complementary biases: GP genetic operators are not example-driven and it can use a fitness function to evaluate control knowledge. and are combined by seeding initial population with control knowledge. It is also useful for to start from a knowledge-rich population instead of a random one. By adding the GP stage to , the number of solved problems increases from 58% to 85% in the blocks world and from 50% to 87% in the logistics domain (0% to 38% and 0% to 42% for the hardest instances of problems considered).", notes = "Hamlet, EvoCK, PRODIGY 4.0", } @InProceedings{Aleshunas:2011:CAoUHiA, title = "Cost-benefit Analysis of Using Heuristics in {ACGP}", author = "John Aleshunas and Cezary Janikow", pages = "1177--1183", booktitle = "Proceedings of the 2011 IEEE Congress on Evolutionary Computation", year = "2011", editor = "Alice E. Smith", month = "5-8 " # jun, address = "New Orleans, USA", organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", ISBN = "0-7803-8515-2", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CEC.2011.5949749", abstract = "Constrained Genetic Programming (CGP) is a method of searching the Genetic Programming search space non-uniformly, giving preferences to certain subspaces according to some heuristics. Adaptable CGP (ACGP) is a method for discovery of the heuristics. CGP and ACGP have previously demonstrated their capabilities using first-order heuristics: parent-child probabilities. Recently, the same advantage has been shown for second-order heuristics: parent- children probabilities. A natural question to ask is whether we can benefit from extending ACGP with deeper-order heuristics. This paper attempts to answer this question by performing cost-benefit analysis while simulating the higher- order heuristics environment. We show that this method cannot be extended beyond the current second or possibly third-order heuristics without a new method to deal with the sheer number of such deeper-order heuristics.", notes = "CEC2011 sponsored by the IEEE Computational Intelligence Society, and previously sponsored by the EPS and the IET.", } @InProceedings{Alexander:2009:cec, author = "B. J. Alexander and M. J. Gratton", title = "Constructing an Optimisation Phase Using Grammatical Evolution", booktitle = "2009 IEEE Congress on Evolutionary Computation", year = "2009", editor = "Andy Tyrrell", pages = "1209--1216", address = "Trondheim, Norway", month = "18-21 " # may, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", isbn13 = "978-1-4244-2959-2", file = "P395.pdf", DOI = "doi:10.1109/CEC.2009.4983083", size = "8 pages", abstract = "Optimising compilers present their authors with an intractable design space. A substantial body of work has used heuristic search techniques to search this space for the purposes of adapting optimisers to their environment. To date, most of this work has focused on sequencing, tuning and guiding the actions of atomic hand-written optimisation phases. In this paper we explore the adaption of optimisers at a deeper level by demonstrating that it is feasible to automatically build a non-trivial optimisation phase, for a simple functional language, using Grammatical Evolution. We show that the individuals evolved compare well in performance to a handwritten optimisation phase on a range of benchmarks. We conclude with proposals of how this work and its applications can be extended.", keywords = "genetic algorithms, genetic programming, grammatical evolution, SBSE, evolutionary computation, functional languages, grammars, optimising compilers, search problems, atomic hand-written optimisation phases, heuristic search techniques, intractable design space", notes = "Adl, DMO, C-MPI, FPGA, Semantics of program preserved. libGE, GAlib, effective crossover, Python, SWIG Python/C++. Canonical code. Five second time limit. Haskell. Training examples changed to 'provide traction for the evolutionary process' p1213. 'Evolution of fittest individuals highly discontinuous' p1214. Some examples where GE is competitive with hand written compiler optimisation, others less so. Evolved code _not_ like human. Compiler output _is_ correct. proof-of-concept. CEC 2009 - A joint meeting of the IEEE, the EPS and the IET. IEEE Catalog Number: CFP09ICE-CDR. Also known as \cite{4983083}", } @InProceedings{alexander2014boosting, author = "Brad Alexander and Brad Zacher", title = "Boosting Search for Recursive Functions Using Partial Call-Trees", booktitle = "13th International Conference on Parallel Problem Solving from Nature", year = "2014", editor = "Thomas Bartz-Beielstein and Juergen Brank and Jim Smith", publisher = "Springer", isbn13 = "978-3-319-10761-5", pages = "384--393", series = "Lecture Notes in Computer Science", address = "Ljubljana, Slovenia", month = "13-17 " # sep, volume = "8672", keywords = "genetic algorithms, genetic programming, grammatical evolution, Recursion, Call-Tree, Adaptive Grammar", DOI = "doi:10.1007/978-3-319-10762-2_38", size = "10 pages", abstract = "Recursive functions are a compact and expressive way to solve challenging problems in terms of local processing. These properties have made recursive functions a popular target for genetic programming. Unfortunately, the evolution of substantial recursive programs has proved difficult. One cause of this problem is the difficulty in evolving both correct base and recursive cases using just information derived from running test cases. In this work we describe a framework that exploits additional information in the form of partial call-trees. Such trees - a by-product of deriving input-output cases by hand - guides the search process by allowing the separate evolution of the recursive case. We show that the speed of evolution of recursive functions is significantly enhanced by the use of partial call-trees and demonstrate application of the technique in the derivation of functions for a suite of numerical functions.", notes = "CTGGP, GE, GElib 0.26, tiny-c-compiler tcc, factorial, oddevens, log2, fib2, fib3, lucas, factorings, summands1 PPSN-XIII Cites \cite{Moraglio:2012:CEC} and \cite{yu:1998:rlaGP98} (in both cases google scholar Feb 2015 data wrong)", } @InCollection{Alexander:2014:shonan, author = "Bradley Alexander", title = "Discussion on Automatic Fault Localisation and Repair", booktitle = "Computational Intelligence for Software Engineering", publisher = "National Institute of Informatics", year = "2014", editor = "Hong Mei and Leandro Minku and Frank Neumann and Xin Yao", pages = "16--19", address = "Japan", month = oct # " 20-23", note = "NII Shonan Meeting Report: No. 2014-13", keywords = "genetic algorithms, genetic programming, genetic improvement, APR", ISSN = "2186-7437", URL = "http://shonan.nii.ac.jp/seminar/reports/wp-content/uploads/sites/56/2015/01/No.2014-13.pdf", size = "4 pages", notes = "Mention of GenProg \cite{DBLP:journals/tse/GouesNFW12} and \cite{Kim:2013:ICSE}, etc. Book also contains abstracts of talks, some on GP. National Institute of Informatics 2-1-2 Hitotsubashi, Chiyoda-Ku, Tokyo, Japan", } @InProceedings{Alexander:2016:PPSN, author = "Brad Alexander and Connie Pyromallis and George Lorenzetti and Brad Zacher", title = "Using Scaffolding with Partial Call-Trees to Improve Search", booktitle = "14th International Conference on Parallel Problem Solving from Nature", year = "2016", editor = "Julia Handl and Emma Hart and Peter R. Lewis and Manuel Lopez-Ibanez and Gabriela Ochoa and Ben Paechter", volume = "9921", series = "LNCS", pages = "324--334", address = "Edinburgh", month = "17-21 " # sep, publisher = "Springer", keywords = "genetic algorithms, genetic programming, Grammatical evolution, Recursion", isbn13 = "978-3-319-45823-6", DOI = "doi:10.1007/978-3-319-45823-6_3", size = "11 page", abstract = "Recursive functions are an attractive target for genetic programming because they can express complex computation compactly. However, the need to simultaneously discover correct recursive and base cases in these functions is a major obstacle in the evolutionary search process. To overcome these obstacles two recent remedies have been proposed. The first is Scaffolding which permits the recursive case of a function to be evaluated independently of the base case. The second is Call- Tree-Guided Genetic Programming (CTGGP) which uses a partial call tree, supplied by the user, to separately evolve the parameter expressions for recursive calls. Used in isolation, both of these approaches have been shown to offer significant advantages in terms of search performance. In this work we investigate the impact of different combinations of these approaches. We find that, on our benchmarks, CTGGP significantly outperforms Scaffolding and that a combination CTGGP and Scaffolding appears to produce further improvements in worst-case performance.", notes = "factorial, odd-evens, log2, Fibonacci and Fibonacci-3, the nth Lucas number, the nth Pell number. p331 'We ran our experiments on an AMD Opteron 6348 machine with 48 processors running at 2.8 GHz' PPSN2016", } @Misc{Alexander:2018:arxiv, author = "Brad Alexander", title = "A Preliminary Exploration of Floating Point Grammatical Evolution", howpublished = "arXiv", year = "2018", month = "9 " # jun, keywords = "genetic algorithms, genetic programming, grammatical evolution", volume = "abs/1806.03455", bibdate = "2018-08-13", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/corr/corr1806.html#abs-1806-03455", URL = "http://arxiv.org/abs/1806.03455", size = "17 pages", abstract = "Current GP frameworks are highly effective on a range of real and simulated benchmarks. However, due to the high dimensionality of the genotypes for GP, the task of visualising the fitness landscape for GP search can be difficult. This paper describes a new framework: Floating Point Grammatical Evolution (FP-GE) which uses a single floating point genotype to encode an individual program. This encoding permits easier visualisation of the fitness landscape arbitrary problems by providing a way to map fitness against a single dimension. The new framework also makes it trivially easy to apply continuous search algorithms, such as Differential Evolution, to the search problem. In this work, the FP-GE framework is tested against several regression problems, visualising the search landscape for these and comparing different search meta-heuristics.", notes = "Also known as \cite{journals/corr/abs-1806-03455}", } @InProceedings{conf/eann/AlexandirisK13, author = "Antonios K. Alexandiris and Michael Kampouridis", title = "Temperature Forecasting in the Concept of Weather Derivatives: a Comparison between Wavelet Networks and Genetic Programming", editor = "Lazaros S. Iliadis and Harris Papadopoulos and Chrisina Jayne", booktitle = "Proceedings of 14th International Conference on Engineering Applications of Neural Networks (EANN 2013), Part {I}", year = "2013", volume = "383", series = "Communications in Computer and Information Science", pages = "12--21", address = "Halkidiki, Greece", month = sep # " 13-16", publisher = "Springer", keywords = "genetic algorithms, genetic programming, weather derivatives, wavelet networks, temperature derivatives", isbn13 = "978-3-642-41012-3", bibdate = "2014-01-25", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/eann/eann2013-1.html#AlexandirisK13", URL = "http://dx.doi.org/10.1007/978-3-642-41013-0", URL = "http://dx.doi.org/10.1007/978-3-642-41013-0_2", DOI = "doi:10.1007/978-3-642-41013-0_2", abstract = "The purpose of this study is to develop a model that accurately describes the dynamics of the daily average temperature in the context of weather derivatives pricing. More precisely we compare two state of the art algorithms, namely wavelet networks and genetic programming against the classic linear approaches widely using in the contexts of temperature derivative pricing. The accuracy of the valuation process depends on the accuracy of the temperature forecasts. Our proposed models were evaluated and compared in-sample and out-of-sample in various locations. Our findings suggest that the proposed nonlinear methods significantly outperform the alternative linear models and can be used for accurate weather derivative pricing.", } @Article{Alexandridis:2017:IJF, author = "Antonis K. Alexandridis and Michael Kampouridis and Sam Cramer", title = "A comparison of wavelet networks and genetic programming in the context of temperature derivatives", journal = "International Journal of Forecasting", volume = "33", number = "1", pages = "21--47", year = "2017", ISSN = "0169-2070", DOI = "doi:10.1016/j.ijforecast.2016.07.002", URL = "http://www.sciencedirect.com/science/article/pii/S0169207016300711", abstract = "The purpose of this study is to develop a model that describes the dynamics of the daily average temperature accurately in the context of weather derivatives pricing. More precisely, we compare two state-of-the-art machine learning algorithms, namely wavelet networks and genetic programming, with the classic linear approaches that are used widely in the pricing of temperature derivatives in the financial weather market, as well as with various machine learning benchmark models such as neural networks, radial basis functions and support vector regression. The accuracy of the valuation process depends on the accuracy of the temperature forecasts. Our proposed models are evaluated and compared, both in-sample and out-of-sample, in various locations where weather derivatives are traded. Furthermore, we expand our analysis by examining the stability of the forecasting models relative to the forecasting horizon. Our findings suggest that the proposed nonlinear methods outperform the alternative linear models significantly, with wavelet networks ranking first, and that they can be used for accurate weather derivative pricing in the weather market.", keywords = "genetic algorithms, genetic programming, Weather derivatives, Wavelet networks, Temperature derivatives, Modelling, Forecasting", } @PhdThesis{Alfaro-Cid:thesis, author = "Maria Eva {Alfaro Cid}", title = "Optimisation of Time Domain Controllers for Supply Ships Using Genetic Algorithms and Genetic Programming", school = "The University of Glasgow", year = "2003", address = "Glasgow, UK", month = oct, keywords = "genetic algorithms, genetic programming", URL = "http://casnew.iti.es/papers/ThesisEva.pdf", URL = "http://ethos.bl.uk/OrderDetails.do?did=49&uin=uk.bl.ethos.398769", size = "348 pages", abstract = "The use of genetic methods for the optimisation of propulsion and heading controllers for marine vessels is presented in this thesis. The first part of this work is a study of the optimisation, using Genetic Algorithms, of controller designs based on a number of different time-domain control methodologies such as PID, Sliding Mode, H? and Pole Placement. These control methodologies are used to provide the structure for propulsion and navigation controllers for a ship. Given the variety in the number of parameters to optimise and the controller structures, the Genetic Algorithm is tested in different control optimisation problems with different search spaces. This study presents how the Genetic Algorithm solves this minimisation problem by evolving controller parameters solutions that satisfactorily perform control duties while keeping actuator usage to a minimum. A variety of genetic operators are introduced and a comparison study is conducted to find the Genetic Algorithm scheme best suited to the parameter controller optimisation problem. The performance of the four control methodologies is also compared. A variation of Genetic Algorithms, the Structured Genetic Algorithm, is also used for the optimisation of the H? controller. The H? controller optimisation presents the difficulty that the optimisation focus is not on parameters but on transfer functions. Structured Genetic Algorithm incorporates hierarchy in the representation of solutions making it very suitable for structural optimisation. The H? optimisation problem has been found to be very appropriate for comparing the performance of Genetic Algorithms versus Structured Genetic Algorithm. During the second part of this work, the use of Genetic Programming to optimise the controller structure is assessed. Genetic Programming is used to evolve control strategies that, given as inputs the current and desired state of the propulsion and heading dynamics, generate the commanded forces required to manoeuvre the ship. Two Genetic Programming algorithms are implemented. The only difference between them is how they generate the numerical constants needed for the solution of the problem. The first approach uses a random generation of constants while the second approach uses a combination of Genetic Programming with Genetic Algorithms. Finally, the controllers optimised using genetic methods are evaluated through computer simulations and real manoeuvrability tests in a laboratory water basin facility. The robustness of each controller is analysed through the simulation of environmental disturbances. Also, optimisations in presence of disturbances are carried out so that the different controllers obtained can be compared. The particular vessels used in this study are two scale models of a supply ship called CyberShip I and CyberShip II. The results obtained illustrate the benefits of using Genetic Algorithms and Genetic Programming to optimise propulsion and navigation controllers for surface ships.", notes = "uk.bl.ethos.398769", } @InProceedings{alfespshar05, title = "Clasificaci\'{o}n de Senales de Electroencefalograma Usando Programaci\'{o}n Gen\'{e}tica", author = "Eva Alfaro-Cid and Anna Esparcia-Alc\'{a}zar and Ken Sharman", booktitle = "Actas del IV Congreso Espanol sobre Metaheur\'{i}sticas, Algoritmos Evolutivos y Bioinspirados ({MAEB}'05)", month = sep, address = "Granada, Spain", year = "2005", keywords = "genetic algorithms, genetic programming", URL = "http://www.iti.upv.es/cas/nade/data/maeb05vfinal.pdf", size = "8 pages", abstract = "En este articulo presentamos una nueva manera de aplicar programacion genetica al problema de clasificacion de series temporales. Eneste caso las series de datos usadas son senalesde electroencefalograma. Se han implementado dos tipos de algoritmos de programaciongenetica: uno de ellos usa programacion distribuida mientras que el otro aplica una tecnica de muestreo aleatorio para evitar el problema de la sobreadaptacion. Los arboles resultantes obtienen porcentajes de aciertos en la clasificacion equivalentes a los que se obtienen usando metodos de clasifficacion tradicionales", notes = "in Spanish", } @InProceedings{eurogp:Alfaro-CidMM05, author = "Eva Alfaro-Cid and Euan William McGookin and David James Murray-Smith", editor = "Maarten Keijzer and Andrea Tettamanzi and Pierre Collet and Jano I. {van Hemert} and Marco Tomassini", title = "Evolution of a Strategy for Ship Guidance Using Two Implementations of Genetic Programming", booktitle = "Proceedings of the 8th European Conference on Genetic Programming", publisher = "Springer", series = "Lecture Notes in Computer Science", volume = "3447", year = "2005", address = "Lausanne, Switzerland", month = "30 " # mar # " - 1 " # apr, organisation = "EvoNet", keywords = "genetic algorithms, genetic programming: Poster", ISBN = "3-540-25436-6", pages = "250--260", DOI = "doi:10.1007/978-3-540-31989-4_22", DOI = "doi:10.1007/b107383", bibsource = "DBLP, http://dblp.uni-trier.de", abstract = "In this paper the implementation of Genetic Programming (GP) to optimise a controller structure for a supply ship is assessed. GP is used to evolve control strategies that, given the current and desired state of the propulsion and heading dynamics of a supply ship as inputs, generate the commanded forces required to manoeuvre the ship. The optimised controllers are evaluated through computer simulations and real manoeuvrability tests in a water basin laboratory. In order to deal with the issue of the generation of numerical constants, two kinds of GP algorithms are implemented. The first one chooses the constants necessary to create the controller structure by random generation . The second algorithm includes a Genetic Algorithms (GAs) technique for the optimisation of such constants. The results obtained illustrate the benefits of using GP to optimise propulsion and navigation controllers for ships.", notes = "Part of \cite{keijzer:2005:GP} EuroGP'2005 held in conjunction with EvoCOP2005 and EvoWorkshops2005", } @InProceedings{conf/esann/Alfaro-CidES06, title = "Using distributed genetic programming to evolve classifiers for a brain computer interface", author = "Eva Alfaro-Cid and Anna Esparcia-Alc{\'a}zar and Ken Sharman", year = "2006", booktitle = "ESANN'2006 proceedings - European Symposium on Artificial Neural Networks", editor = "Michel Verleysen", pages = "59--66", address = "Bruges, Belgium", month = "26-28 " # apr, bibdate = "2006-08-30", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/esann/esann2006.html#Alfaro-CidES06", keywords = "genetic algorithms, genetic programming", ISBN = "2-930307-06-4", URL = "http://www.dice.ucl.ac.be/Proceedings/esann/esannpdf/es2006-44.pdf", abstract = "The objective of this paper is to illustrate the application of genetic programming to evolve classifiers for multi-channel time series data. The paper shows how high performance distributed genetic programming (GP) has been implemented for evolving classifiers. The particular application discussed herein is the classification of human electroencephalographic (EEG) signals for a brain-computer interface (BCI). The resulting classifying structures provide classification rates comparable to those obtained using traditional, human-designed, classification", notes = "http://www.dice.ucl.ac.be/Proceedings/esann/", } @InProceedings{Alfaro-Cid:2006:CEC, author = "Eva Alfaro-Cid and Ken Sharman and Anna I. Esparcia-Alcazar", title = "Evolving a Learning Machine by Genetic Programming", booktitle = "Proceedings of the 2006 IEEE Congress on Evolutionary Computation", year = "2006", editor = "Gary G. Yen and Lipo Wang and Piero Bonissone and Simon M. Lucas", pages = "958--962", address = "Vancouver", month = "16-21 " # jul, publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, simulated annealing, function set, learning machine, learning node, optimization algorithm, simulated annealing", ISBN = "0-7803-9487-9", DOI = "doi:10.1109/CEC.2006.1688316", size = "5 pages", abstract = "We describe a novel technique for evolving a machine that can learn. The machine is evolved using a Genetic Programming (GP) algorithm that incorporates in its function set what we have called a learning node. Such a node is tuned by a second optimisation algorithm (in this case Simulated Annealing), mimicking a natural learning process and providing the GP tree with added flexibility and adaptability. The result of the evolution is a system with a fixed structure but with some variable parameters. The system can then learn new tasks in new environments without undergoing further evolution.", notes = "WCCI 2006 - A joint meeting of the IEEE, the EPS, and the IEE. IEEE Catalog Number: 06TH8846D IEEE Xplore gives pages as 254--258", } @InProceedings{alshaes2007a, title = "Predicci\'{o}n de quiebra empresarial usando programaci\'{o}n gen\'{e}tica", author = "Eva {Alfaro Cid} and Ken Sharman and Anna I. {Esparcia Alc\'{a}zar}", booktitle = "Actas del V Congreso Espa{\~n}ol sobre Metaheur\'{i}sticas, Algoritmos Evolutivos y Bioinspirados (MAEB'07)", editor = "Francisco Almeida Rodriguez and Maria Belen Melian Batista and Jose Andres Moreno Perez and Jose Marcos Moreno Vega", publisher = "La Laguna", month = "Febrero", year = "2007", pages = "703--710", address = "Tenerife, Spain", publisher_address = "Tenerife, Spain", keywords = "genetic algorithms, genetic programming", isbn13 = "978-84-690-3470-5", URL = "https://dialnet.unirioja.es/servlet/articulo?codigo=4142085", notes = "Prediccion de quiebra empresarial usando programacion genetica in Spanish http://www.redheur.org/files/MAEBs/MAEB07.pdf", } @InProceedings{alshaescu2007a, title = "Aprendizaje autom\'{a}tico con programaci\'{o}n gen\'{e}tica", author = "Eva {Alfaro Cid} and Ken Sharman and Anna I. {Esparcia Alc\'{a}zar} and Alberto {Cuesta Ca{\~n}ada}", booktitle = "Actas del V Congreso Espa{\~n}ol sobre Metaheur\'{i}sticas, Algoritmos Evolutivos y Bioinspirados (MAEB'07)", publisher = "La Laguna", month = "Febrero", year = "2007", pages = "819--826", address = "Tenerife, Spain", publisher_address = "Tenerife, Spain", keywords = "genetic algorithms, genetic programming", isbn13 = "978-84-690-3470-5", URL = "https://dialnet.unirioja.es/servlet/articulo?codigo=4148339", notes = "Aprendizaje automatico con programacion genetica in Spanish http://www.redheur.org/files/MAEBs/MAEB07.pdf", } @InProceedings{alfaro-cid:evows07, author = "Eva Alfaro-Cid and Ken Sharman and Anna I. Esparcia-Alc\`azar", title = "A genetic programming approach for bankruptcy prediction using a highly unbalanced database", booktitle = "Applications of Evolutionary Computing, EvoWorkshops2007: {EvoCOMNET}, {EvoFIN}, {EvoIASP}, {EvoInteraction}, {EvoMUSART}, {EvoSTOC}, {EvoTransLog}", year = "2007", month = "11-13 " # apr, editor = "Mario Giacobini and Anthony Brabazon and Stefano Cagnoni and Gianni A. {Di Caro} and Rolf Drechsler and Muddassar Farooq and Andreas Fink and Evelyne Lutton and Penousal Machado and Stefan Minner and Michael O'Neill and Juan Romero and Franz Rothlauf and Giovanni Squillero and Hideyuki Takagi and A. Sima Uyar and Shengxiang Yang", series = "LNCS", volume = "4448", publisher = "Springer Verlag", address = "Valencia, Spain", pages = "169--178", keywords = "genetic algorithms, genetic programming, SVM", isbn13 = "978-3-540-71804-8", DOI = "doi:10.1007/978-3-540-71805-5_19", abstract = "in this paper we present the application of a genetic programming algorithm to the problem of bankruptcy prediction. To carry out the research we have used a database of Spanish companies. The database has two important drawbacks: the number of bankrupt companies is very small when compared with the number of healthy ones (unbalanced data) and a considerable number of companies have missing data. For comparison purposes we have solved the same problem using a support vector machine. Genetic programming has achieved very satisfactory results, improving those obtained with the support vector machine.", notes = "EvoWorkshops2007", } @InProceedings{conf/evoW/Alfaro-CidMGES08, title = "A {SOM} and {GP} Tool for Reducing the Dimensionality of a Financial Distress Prediction Problem", author = "Eva Alfaro-Cid and Antonio Miguel Mora and Juan Juli{\'a}n Merelo Guerv{\'o}s and Anna Esparcia-Alc{\'a}zar and Ken Sharman", bibdate = "2008-04-15", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/evoW/evoW2008.html#Alfaro-CidMGES08", booktitle = "Proceedings of Evo{COMNET}, Evo{FIN}, Evo{HOT}, Evo{IASP}, Evo{MUSART}, Evo{NUM}, Evo{STOC}, and EvoTransLog, Applications of Evolutionary Computing, EvoWorkshops", publisher = "Springer", year = "2008", volume = "4974", editor = "Mario Giacobini and Anthony Brabazon and Stefano Cagnoni and Gianni {Di Caro} and Rolf Drechsler and Anik{\'o} Ek{\'a}rt and Anna Esparcia-Alc{\'a}zar and Muddassar Farooq and Andreas Fink and Jon McCormack and Michael O'Neill and Juan Romero and Franz Rothlauf and Giovanni Squillero and Sima Uyar and Shengxiang Yang", isbn13 = "978-3-540-78760-0", pages = "123--132", series = "Lecture Notes in Computer Science", DOI = "doi:10.1007/978-3-540-78761-7_13", address = "Naples", month = "26-28 " # mar, keywords = "genetic algorithms, genetic programming", } @InProceedings{Alfaro-Cid:2008:cec, author = "E. Alfaro-Cid and P. A. Castillo and A. Esparcia and K. Sharman and J. J. Merelo and A. Prieto and J. L. J. Laredo", title = "Comparing Multiobjective Evolutionary Ensembles for Minimizing Type I and II Errors for Bankruptcy Prediction", booktitle = "2008 IEEE World Congress on Computational Intelligence", year = "2008", editor = "Jun Wang", pages = "2902--2908", address = "Hong Kong", month = "1-6 " # jun, organization = "IEEE Computational Intelligence Society", publisher = "IEEE Press", isbn13 = "978-1-4244-1823-7", file = "EC0649.pdf", DOI = "doi:10.1109/CEC.2008.4631188", abstract = "In many real world applications type I (false positive) and type II (false negative) errors have to be dealt with separately, which is a complex problem since an attempt to minimise one of them usually makes the other grow. In fact, a type of error can be more important than the other, and a trade-off that minimises the most important error type must be reached. In the case of the bankruptcy prediction problem the error type II is of greater importance, being unable to identify that a company is at risk causes problems to creditors and slows down the taking of measures that may solve the problem. Despite the importance of type II errors, most bankruptcy prediction methods take into account only the global classification error. In this paper we propose and compare two methods to optimise both error types in classification: artificial neural networks and function trees ensembles created through multiobjective Optimization. Since the multiobjective Optimization process produces a set of equally optimal results (Pareto front) the classification of the test patterns in both cases is based on the non-dominated solutions acting as an ensemble. The experiments prove that, although the best classification rates are obtained using the artificial neural network, the multiobjective genetic programming model is able to generate comparable results in the form of an analytical function.", keywords = "genetic algorithms, genetic programming", notes = "WCCI 2008 - A joint meeting of the IEEE, the INNS, the EPS and the IET.", } @Article{Alfaro-Cid:2008:ieeeITS, author = "Eva Alfaro-Cid and Euan W. McGookin and David J. Murray-Smith and Thor I. Fossen", title = "Genetic Programming for the Automatic Design of Controllers for a Surface Ship", journal = "IEEE Transactions on Intelligent Transportation Systems", year = "2008", month = jun, volume = "9", number = "2", pages = "311--321", keywords = "genetic algorithms, genetic programming, control system synthesis, navigation, propulsion, ships CyberShip II, automatic design, controller structure, navigation controllers, propulsion controllers, supply ship, surface ship", ISSN = "1524-9050", DOI = "doi:10.1109/TITS.2008.922932", URL = "http://results.ref.ac.uk/Submissions/Output/2145080", abstract = "In this paper, the implementation of genetic programming (GP) to design a controller structure is assessed. GP is used to evolve control strategies that, given the current and desired state of the propulsion and heading dynamics of a supply ship as inputs, generate the commanded forces required to maneuver the ship. The controllers created using GP are evaluated through computer simulations and real maneuverability tests in a laboratory water basin facility. The robustness of each controller is analyzed through the simulation of environmental disturbances. In addition, GP runs in the presence of disturbances are carried out so that the different controllers obtained can be compared. The particular vessel used in this paper is a scale model of a supply ship called CyberShip II. The results obtained illustrate the benefits of using GP for the automatic design of propulsion and navigation controllers for surface ships.", notes = "Also known as \cite{4517335}", uk_research_excellence_2014 = "This paper represents the outcome of a Marie Curie funded collaborative project with the Norwegian University of Science and Technology (NUST), and is one of the first studies to use Genetic Programming in the design of marine vehicle control systems. The research involved the optimisation of the structure and associated gains of a control system for guiding a surface vessel. The optimised controller was used on the test vehicle in tank trials and evaluated in the Marine Cybernetics Laboratory at NUST (Contact: Thor Fossen, ), to demonstrate the power of this optimisation method for controller design.", } @InProceedings{Alfaro-Cid:2008:HIS, author = "Eva Alfaro-Cid and Anna Esparcia-Alcazar and Ken Sharman and Francisco {Fernandez de Vega} and J. J. Merelo", title = "Prune and Plant: A New Bloat Control Method for Genetic Programming", booktitle = "Eighth International Conference on Hybrid Intelligent Systems, HIS '08", year = "2008", month = sep, pages = "31--35", keywords = "genetic algorithms, genetic programming, bloat control method, genetic operator, prune and plant, time consumption, tree size reduction, mathematical operators, trees (mathematics)", DOI = "doi:10.1109/HIS.2008.127", abstract = "This paper reports a comparison of several bloat control methods and also evaluates a new proposal for limiting the size of the individuals: a genetic operator called prune and plant. The aim of this work is to prove the adequacy of this new method. Since a preliminary study of the method has already shown promising results, we have performed a thorough study in a set of benchmark problems aiming at demonstrating the utility of the new approach. Prune and plant has obtained results that maintain the quality of the final solutions in terms of fitness while achieving a substantial reduction of the mean tree size in all four problem domains considered. In addition, in one of these problem domains prune and plant has demonstrated to be better in terms of fitness, size reduction and time consumption than any of the other bloat control techniques under comparison.", notes = "Also known as \cite{4626601}", } @InCollection{series/sci/Alfaro-CidCSE08, title = "Strong Typing, Variable Reduction and Bloat Control for Solving the Bankruptcy Prediction Problem Using Genetic Programming", author = "Eva Alfaro-Cid and Alberto Cuesta-Canada and Ken Sharman and Anna Esparcia-Alcazar", bibdate = "2008-08-26", bibsource = "DBLP, http://dblp.uni-trier.de/db/series/sci/sci100.html#Alfaro-CidCSE08", booktitle = "Natural Computing in Computational Finance", publisher = "Springer", year = "2008", volume = "100", editor = "Anthony Brabazon and Michael O'Neill", isbn13 = "978-3-540-77476-1", pages = "161--185", series = "Studies in Computational Intelligence", DOI = "doi:10.1007/978-3-540-77477-8_9", chapter = "9", keywords = "genetic algorithms, genetic programming, STGP, SVM", size = "29 pages", abstract = "In this chapter we present the application of a genetic programming (GP) algorithm to the problem of bankruptcy prediction. To carry out the research we have used a database that includes extensive information (not only economic) from the companies. In order to handle the different data types we have used Strongly Typed GP and variable reduction. Also, bloat control has been implemented to obtain comprehensible classification models. For comparison purposes we have solved the same problem using a support vector machine (SVM). GP has achieved very satisfactory results, improving those obtained with the SVM.", } @InProceedings{Alfaro-Cid:2009:evonum, title = "Modeling Pheromone Dispensers Using Genetic Programming", author = "Eva Alfaro-Cid and Anna I. Esparcia-Alc\'{a}zar and Pilar Moya and Beatriu Femenia-Ferrer and Ken Sharman and J. J. Merelo", booktitle = "Applications of Evolutionary Computing, EvoWorkshops 2009: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG", editor = "Mario Giacobini and Anthony Brabazon and Stefano Cagnoni and Gianni A. Di Caro and Anik{\'o} Ek{\'a}rt and Anna Esparcia-Alc{\'a}zar and Muddassar Farooq and Andreas Fink and Penousal Machado and Jon McCormack and Michael O'Neill and Ferrante Neri and Mike Preuss and Franz Rothlauf and Ernesto Tarantino and Shengxiang Yang", volume = "5484", series = "Lecture Notes in Computer Science", address = "Tubingen, Germany", year = "2009", pages = "635--644", month = apr # " 15-17", organisation = "EvoStar", publisher = "Springer", keywords = "genetic algorithms, genetic programming", isbn13 = "978-3-642-01128-3", bibsource = "DBLP, http://dblp.uni-trier.de", DOI = "doi:10.1007/978-3-642-01129-0_73", size = "10 pages", abstract = "Mating disruption is an agricultural technique that intends to substitute the use of insecticides for pest control. This technique consists of the diffusion of large amounts of sexual pheromone, so that the males are confused and mating is disrupted. Pheromones are released using devices called dispensers. The speed of release is, generally, a function of time and atmospheric conditions such as temperature and humidity. One of the objectives in the design of the dispensers is to minimise the effect of atmospheric conditions in the performance of the dispenser. With this objective, the Centro de Ecologia Quimica Agricola (CEQA) has designed an experimental dispenser that aims to compete with the dispensers already in the market. The hypothesis we want to validate (and which is based on experimental results) is that the performance of the CEQA dispenser is independent of the atmospheric conditions, as opposed to the most widely used commercial dispenser, Isomate CPlus. This was done using a genetic programming (GP) algorithm. GP evolved functions able to describe the performance of both dispensers and that support the initial hypothesis.", notes = "ECJ. EvoWorkshops2009 held in conjunction with EuroGP2009, EvoCOP2009, EvoBIO2009", } @InProceedings{DBLP:conf/gecco/Alfaro-CidEMMFSP09, author = "Eva Alfaro-Cid and Anna Esparcia-Alcazar and Pilar Moya and J. J. Merelo and Beatriu Femenia-Ferrer and Ken Sharman and Jaime Primo", title = "Multiobjective genetic programming approach for a smooth modeling of the release kinetics of a pheromone dispenser", booktitle = "GECCO-2009 Symbolic regression and modeling workshop (SRM)", year = "2009", editor = "Anna I. Esparcia and Ying-ping Chen and Gabriela Ochoa and Ender Ozcan and Marc Schoenauer and Anne Auger and Hans-Georg Beyer and Nikolaus Hansen and Steffen Finck and Raymond Ros and Darrell Whitley and Garnett Wilson and Simon Harding and W. B. Langdon and Man Leung Wong and Laurence D. Merkle and Frank W. Moore and Sevan G. Ficici and William Rand and Rick Riolo and Nawwaf Kharma and William R. Buckley and Julian Miller and Kenneth Stanley and Jaume Bacardit and Will Browne and Jan Drugowitsch and Nicola Beume and Mike Preuss and Stephen L. Smith and Stefano Cagnoni and Jim DeLeo and Alexandru Floares and Aaron Baughman and Steven Gustafson and Maarten Keijzer and Arthur Kordon and Clare Bates Congdon and Laurence D. Merkle and Frank W. Moore", pages = "2225--2230", address = "Montreal", publisher = "ACM", publisher_address = "New York, NY, USA", month = "8-12 " # jul, organisation = "SigEvo", keywords = "genetic algorithms, genetic programming", isbn13 = "978-1-60558-325-9", bibsource = "DBLP, http://dblp.uni-trier.de", DOI = "doi:10.1145/1570256.1570309", abstract = "The accurate modeling of the release kinetics of pheromone dispensers is a matter or great importance for ensuring that the dispenser field-life covers the flight period of the pest and for optimizing the layout of dispensers in the treated area. A new experimental dispenser has been recently designed by researchers at the Instituto Agroforestal del Mediterraneo - Centro de Ecologia Quimica Agricola (CEQA) of the Universidad Politecnica de Valencia (Spain). The most challenging problem for the modeling of the release kinetics of this dispensers is the difficulty in obtaining experimental measurements for building the model. The procedure for obtaining these data is very costly, both time and money wise, therefore the available data across the whole season are scarce. In prior work we demonstrated the utility of using Genetic Programming (GP) for this particular problem. However, the models evolved by the GP algorithm tend to have discontinuities in those time ranges where there are not available measurements. In this work we propose the use of a multiobjective Genetic Programming for modeling the performance of the CEQA dispenser. We take two approaches, involving two and nine objectives respectively. In the first one, one of the objectives of the GP algorithm deals with how well the model fits the experimental data, while the second objective measures how {"}smooth{"} the model behaviour is. In the second approach we have as many objectives as data points and the aim is to predict each point separately using the remaining ones. The results obtained endorse the utility of this approach for those modeling problems characterized by the lack of experimental data.", notes = "Distributed on CD-ROM at GECCO-2009. ACM Order Number 910092.", } @Article{Alfaro-Cid:2010:EC, author = "Eva Alfaro-Cid and J. J. Merelo and Francisco {Fernandez de Vega} and Anna I. Esparcia-Alcazar and Ken Sharman", title = "Bloat Control Operators and Diversity in Genetic Programming: A Comparative Study", journal = "Evolutionary Computation", year = "2010", volume = "18", number = "2", pages = "305--332", month = "Summer", keywords = "genetic algorithms, genetic programming", ISSN = "1063-6560", DOI = "doi:10.1162/evco.2010.18.2.18206", abstract = "This paper reports a comparison of several bloat control methods and also evaluates a recent proposal for limiting the size of the individuals: a genetic operator called prune and plant. The aim of this work is to test the adequacy of this method. Since a preliminary study of the method has already shown promising results, we have performed a thorough study in a set of benchmark problems aiming at demonstrating the utility of the new approach. Prune and plant has obtained results that maintain the quality of the final solutions in terms of fitness while achieving a substantial reduction of the mean tree size in all four problem domains considered. In addition, in one of these problem domains, prune and plant has demonstrated to be better in terms of fitness, size reduction, and time consumption than any of the other bloat control techniques under comparison. The experimental part of the study presents a comparison of performance in terms of phenotypic and genotypic diversity. This comparison study can provide the practitioner with some relevant clues as to which bloat control method is better suited to a particular problem and whether the advantage of a method does or does not derive from its influence on the genetic pool diversity.", } @Article{Alfaro-Cid:2014:EC, author = "Eva Alfaro-Cid and Ken Sharman and Anna I. Esparcia-Alcazar", title = "Genetic programming and serial processing for time series classification", journal = "Evolutionary Computation", year = "2014", volume = "22", number = "2", pages = "265--285", month = "Summer", keywords = "genetic algorithms, genetic programming, Classification, time series, serial data processing, real world applications", ISSN = "1063-6560", DOI = "doi:10.1162/EVCO_a_00110", size = "20 pages", abstract = "This work describes an approach devised by the authors for time series classification. In our approach genetic programming is used in combination with a serial processing of data, where the last output is the result of the classification. The use of genetic programming for classification, although still a field where more research in needed, is not new. However, the application of genetic programming to classification tasks is normally done by considering the input data as a feature vector. That is, to the best of our knowledge, there are not examples in the genetic programming literature of approaches where the time series data are processed serially and the last output is considered as the classification result. The serial processing approach presented here fills a gap in the existing literature. This approach was tested in three different problems. Two of them are real world problems whose data were gathered for on-line or conference competitions. As there are published results of these two problems this gives us the chance of comparing the performance of our approach against top performing methods. The serial processing of data in combination with genetic programming obtained competitive results in both competitions, showing its potential for solving time series classification problems. The main advantage of our serial processing approach is that it can easily handle very large data sets.", notes = "ECJ. EEG BCI competition II. Ford Classification Challenge", } @Article{alfonseca:2004:GPEM, author = "Manuel Alfonseca and Alfonso Ortega", title = "Book Review: {Grammatical Evolution}: {Evolutionary} Automatic Programming in an Arbitrary Language", journal = "Genetic Programming and Evolvable Machines", year = "2004", volume = "5", number = "4", pages = "393", month = dec, keywords = "genetic algorithms, genetic programming, grammatical evolution", ISSN = "1389-2576", URL = "https://rdcu.be/dR8co", DOI = "doi:10.1023/B:GENP.0000036057.27304.5b", size = "1 page", notes = "review of \cite{oneill:book}. Article ID: 5272973", } @Article{journals/biosystems/AlfonsecaG13, title = "Evolving an ecology of mathematical expressions with grammatical evolution", author = "Manuel Alfonseca and Francisco Jose Soler Gil", journal = "Biosystems", year = "2013", number = "2", volume = "111", keywords = "genetic algorithms, genetic programming, grammatical evolution", bibdate = "2014-12-09", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/biosystems/biosystems111.html#AlfonsecaG13", pages = "111--119", URL = "http://dx.doi.org/10.1016/j.biosystems.2012.12.004", } @Article{journals/complexity/AlfonsecaG15, author = "Manuel Alfonseca and Francisco Jose Soler Gil", title = "Evolving a predator-prey ecosystem of mathematical expressions with grammatical evolution", journal = "Complexity", year = "2015", number = "3", volume = "20", bibdate = "2015-03-04", bibsource = "DBLP, http://dblp.uni-trier.de/db/journals/complexity/complexity20.html#AlfonsecaG15", pages = "66--83", keywords = "genetic algorithms, genetic programming, grammatical evolution", URL = "http://dx.doi.org/10.1002/cplx.21507", } @InProceedings{Alghamdi:2019:GI7, author = "Mahfouth Alghamdi and Christoph Treude and Markus Wagner", title = "Toward Human-Like Summaries Generated from Heterogeneous Software Artefacts", booktitle = "7th edition of GI @ GECCO 2019", year = "2019", month = jul # " 13-17", editor = "Brad Alexander and Saemundur O. Haraldsson and Markus Wagner and John R. Woodward", publisher = "ACM", address = "Prague, Czech Republic", pages = "1701--1702", organisation = "SIGEVO", keywords = "genetic algorithms, genetic programming, genetic improvement, SBSE, Heterogeneous software artefacts, extractive summarisation, human-like summaries", isbn13 = "978-1-4503-6748", URL = "https://arxiv.org/abs/1905.02258", URL = "https://ctreude.files.wordpress.com/2019/05/gi19.pdf", DOI = "doi:10.1145/3319619.3326814", size = "2 pages", abstract = "Automatic text summarisation has drawn considerable interest in the field of software engineering. It can improve the efficiency of software developers, enhance the quality of products, and ensure timely delivery. In this paper, we present our initial work towards automatically generating human-like multi-document summaries from heterogeneous software artefacts. Our analysis of the text properties of 545 human-written summaries from 15 software engineering projects will ultimately guide heuristics searches in the automatic generation of human-like summaries.", } @InProceedings{Alghieth:2015:INISTA, author = "Manal Alghieth and Yingjie Yang and Francisco Chiclana", booktitle = "2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA)", title = "Development of {2D} curve-fitting genetic/gene-expression programming technique for efficient time-series financial forecasting", year = "2015", abstract = "Stock market prediction is of immense interest to trading companies and buyers due to high profit margins. Therefore, precise prediction of the measure of increase or decrease of stock prices also plays an important role in buying/selling activities. This research presents a specialised extension to the genetic algorithms (GA) known as the genetic programming (GP) and gene expression programming (GEP) to explore and investigate the outcome of the GEP criteria on the stock market price prediction. The research presented in this paper aims at the modelling and prediction of short-to-medium term stock value fluctuations in the market via genetically tuned stock market parameters. The technique uses hierarchically defined GP and GEP techniques to tune algebraic functions representing the fittest equation for stock market activities. The proposed methodology is evaluated against five well-known stock market companies with each having its own trading circumstances during the past 20+ years. The proposed GEP/GP methodologies were evaluated based on variable window/population sizes, selection methods, and Elitism, Rank and Roulette selection methods. The Elitism-based approach showed promising results with a low error-rate in the resultant pattern matching with an overall accuracy of 93.46percent for short-term 5-day and 92.105 for medium-term 56-day trading periods.", keywords = "genetic algorithms, genetic programming, gene expression programming", DOI = "doi:10.1109/INISTA.2015.7276734", month = sep, notes = "Fac. of Technol., De Montfort Univ., Leicester, UK Also known as \cite{7276734}", } @InProceedings{Alghieth:2016:CEC, author = "Manal Alghieth and Yingjie Yang and Francisco Chiclana", title = "Development of a Genetic Programming-based GA Methodology for the Prediction of Short-to-Medium-term Stock Markets", booktitle = "Proceedings of 2016 IEEE Congress on Evolutionary Computation (CEC 2016)", year = "2016", editor = "Yew-Soon Ong", pages = "2381--2388", address = "Vancouver", month = "24-29 " # jul, publisher = "IEEE Press", keywords = "genetic algorithms, genetic programming, gene expressing programming, Stock market, Time series financial forecasting", isbn13 = "978-1-5090-0623-6", URL = "https://www.dora.dmu.ac.uk/handle/2086/11896", DOI = "doi:10.1109/CEC.2016.7744083", size = "8 pages", abstract = "This research presents a specialised extension to the genetic algorithms (GA) known as the genetic programming (GP) and gene expression programming (GEP) to explore and investigate the outcome of the GEP criteria on the stock market price prediction. The aim of this research is to model and predict short-to-medium term stock value fluctuations in the market via genetically tuned stock market parameters. The technology proposes a fractional adaptive mutation rate Elitism (GEPFAMR) technique to initiate a balance between varied mutation rates and between varied-fitness chromosomes, thereby improving prediction accuracy and fitness improvement rate. The methodology is evaluated against different dataset and selection methods and showed promising results with a low error-rate in the resultant pattern matching with an overall accuracy of 95.96percent for short-term 5-day and 95.35percent for medium-term 56-day trading periods.", notes = "WCCI2016 Centre for Computational Intelligence, Faculty of Technology, De Montfort University, Leicester, UK", } @Article{ALHAMED:2022:energy, author = "Khaled H. M. Al-Hamed and Ibrahim Dincer", title = "Exergoeconomic analysis and optimization of a solar energy-based integrated system with oxy-combustion for combined power cycle and carbon capturing", journal = "Energy", volume = "250", pages = "123814", year = "2022", ISSN = "0360-5442", DOI = "doi:10.1016/j.energy.2022.123814", URL = "https://www.sciencedirect.com/science/article/pii/S0360544222007174", keywords = "genetic algorithms, genetic programming, Ammonia, Carbon capture, Energy, Exergoeconomic analysis, Gas turbine, Optimization", abstract = "This work presents a newly developed integrated system that produces multiple useful products, namely electricity, space cooling, freshwater, and ammonium bicarbonate. The two sources of energy for this integrated system are solar energy and natural gas. The natural gas is consumed in an oxy-combustion Brayton cycle to produce electricity, while the solar energy provides electric power to the carbon capturing unit to produce ammonium bicarbonate as a valuable chemical product to compensate for the operation costs of carbon capture. This integrated system is studied using the exergoeconomic analysis and the multi-objective optimization method of genetic programming and genetic algorithm to enhance the thermodynamic and economic aspects of this system. Applying such an analysis to this integrated system adds more understanding and knowledge on how effectively and efficiently this carbon capture system operates and whether or not it is financially viable to pursue this integrated system for further prototyping and concept demonstration. The results of this exergoeconomic analysis show that the production cost of ammonium bicarbonate per 1 kg in this integrated system is 0.0687 $ kg-1, and this is much lower than the market price. This means that producing ammonium bicarbonate as a way to capture carbon dioxide is feasible financially. Furthermore, the optimization results show that the overall exergy destruction rate and the overall unit cost of products are 86,000 kW and 5.19 times 10-3 $ kJ-1, respectively, when operated under optimum conditions", } @InProceedings{Alhejali:2010:UKCI, author = "Atif M. Alhejali and Simon M. Lucas", title = "Evolving diverse {Ms. Pac-Man} playing agents using genetic programming", booktitle = "UK Workshop on Computational Intelligence (UKCI 2010)", year = "2010", month = "8-10 " # sep, pages = "1--6", abstract = "This paper uses genetic programming (GP) to evolve a variety of reactive agents for a simulated version of the classic arcade game Ms. Pac-Man. A diverse set of behaviours were evolved using the same GP setup in three different versions of the game. The results show that GP is able to evolve controllers that are well-matched to the game used for evolution and, in some cases, also generalise well to previously unseen mazes. For comparison purposes, we also designed a controller manually using the same function set as GP. GP was able to significantly outperform this hand-designed controller. The best evolved controllers are competitive with the best reactive controllers reported for this problem.", keywords = "genetic algorithms, genetic programming, Ms PacMan game, reactive agents, computer games, learning (artificial intelligence), software agents", DOI = "doi:10.1109/UKCI.2010.5625586", notes = "Also known as \cite{5625586}", } @InProceedings{Alhejali:2011:CIG, author = "Atif M. Alhejali and Simon M. Lucas", title = "Using a Training Camp with Genetic Programming to Evolve {Ms Pac-Man} Agents", booktitle = "Proceedings of the 2011 IEEE Conference on Computational Intelligence and Games", year = "2011", pages = "118--125", address = "Seoul, South Korea", month = "31 " # aug # " - 3 " # sep, publisher = "IEEE", keywords = "genetic algorithms, genetic programming, Pac-Man, Evolving Controllers, Decomposition learning, Training camp", isbn13 = "978-1-4577-0010-1", URL = "http://cilab.sejong.ac.kr/cig2011/proceedings/CIG2011/papers/paper31.pdf", DOI = "doi:10.1109/CIG.2011.6031997", size = "8 pages", abstract = "This paper investigates using a training camp in conjunction with Genetic Programming in the evolution of Ms Pac-Man playing agents. We measure the amount of effort, time and resources required to run the training camp successfully. The approach is compared with standard GP. The results indicate that better and more stable performance can be achieved using the training camp method at the expense of greater manual effort in the design of the training scenarios. However, in addition to the better results, the training camp also provides more detailed insight into the strengths and weaknesses of each controller.", notes = "Also known as \cite{6031997}", } @InProceedings{Alhejali:2013:CIG, author = "Atif M. Alhejali and Simon M. Lucas", title = "Using genetic programming to evolve heuristics for a Monte Carlo Tree Search {Ms Pac-Man} agent", booktitle = "IEEE Conference on Computational Intelligence in Games (CIG 2013)", year = "2013", month = "11-13 " # aug, address = "Niagara Falls, Canada", keywords = "genetic algorithms, genetic programming, Monte Carlo methods, artificial intelligence, computer games, tree searching, Al, MCTS, Monte Carlo tree search Ms Pac-Man agent, evolved default policy, game artificial intelligence, random agent, random default policy, Equations, Games, Mathematical model, Monte Carlo methods, Sociology, Monte Carlo Tree Search, Pac-Man", ISSN = "2325-4270", isbn13 = "978-1-4673-5311-3", DOI = "doi:10.1109/CIG.2013.6633639", abstract = "Ms Pac-Man is one of the most challenging test beds in game artificial intelligence (AI). Genetic programming and Monte Carlo Tree Search (MCTS) have already been successful applied to several games including Pac-Man. In this paper, we use Monte Carlo Tree Search to create a Ms Pac-Man playing agent before using genetic programming to enhance its performance by evolving a new default policy to replace the random agent used in the simulations. The new agent with the evolved default policy was able to achieve an 18percent increase on its average score over the agent with random default policy.", notes = "Also known as \cite{6633639}", } @PhdThesis{Alhejali:thesis, author = "Atif Mansour Alhejali", title = "Genetic Programming and the Evolution of Games Playing Agents", school = "Computing and Electronic Systems, University of Essex", year = "2013", address = "UK", keywords = "genetic algorithms, genetic programming", URL = "http://www.essex.ac.uk/csee/news_and_seminars/newsEvent.aspx?e_id=5796", notes = "Supervisor Simon M. Lucas", } @Article{ali:2004:GPEM, author = "B. Ali and A. E. A. Almaini and T. Kalganova", title = "Evolutionary Algorithms and Theirs Use in the Design of Sequential Logic Circuits", journal = "Genetic Programming and Evolvable Machines", year = "2004", volume = "5", number = "1", month = mar, keywords = "genetic algorithms, evolvable hardware, sequential circuits, state assignment", ISSN = "1389-2576", DOI = "doi:10.1023/B:GENP.0000017009.11392.e2", abstract = "design synchronous sequential logic circuits with minimum number of logic gates is suggested. The proposed method consists of four main stages. The first stage is concerned with the use of genetic algorithms (GA) for the state assignment problem to compute optimal binary codes for each symbolic state and construct the state transition table of finite state machine (FSM). The second stage defines the subcircuits required to achieve the desired functionality. The third stage evaluates the subcircuits using extrinsic Evolvable Hardware (EHW). During the fourth stage, the final circuit is assembled. The obtained results compare favourably against those produced by manual methods and other methods based on heuristic techniques.", notes = "Article ID: 5264733", } @InCollection{Ali:2008:GPTP, author = "Mostafa Z. Ali and Robert G. Reynolds and Xiangdong Che", title = "Genetic Programming for Incentive-Based Design within a Cultural Algorithms Framework", booktitle = "Genetic Programming Theory and Practice {VI}", year = "2008", editor = "Rick L. Riolo and Terence Soule and Bill Worzel", series = "Genetic and Evolutionary Computation", chapter = "16", pages = "249--269", address = "Ann Arbor", month = "15-17 " # may, publisher = "Springer", DOI = "doi:10.1007/978-0-387-87623-8_16", size = "20 pages", isbn13 = "978-0-387-87622-1", notes = "part of \cite{Riolo:2008:GPTP} published in 2009", keywords = "genetic algorithms, genetic programming", } @Article{DBLP:journals/evi/AliM20, author = "Muhammad Quamber Ali and Hammad Majeed", title = "Difficult first strategy {GP:} an inexpensive sampling technique to improve the performance of genetic programming", journal = "Evol. Intell.", volume = "13", number = "4", pages = "537--549", year = "2020", keywords = "genetic algorithms, genetic programming", URL = "https://doi.org/10.1007/s12065-020-00355-2", DOI = "doi:10.1007/s12065-020-00355-2", timestamp = "Tue, 20 Oct 2020 01:00:00 +0200", biburl = "https://dblp.org/rec/journals/evi/AliM20.bib", bibsource = "dblp computer science bibliography, https://dblp.org", } @Article{DBLP:journals/nca/AliJAAM22, author = "Mir Masoud Ale Ali and Ali Jamali and A. Asgharnia and R. Ansari and Rammohan Mallipeddi", title = "Multi-objective Lyapunov-based controller design for nonlinear systems via genetic programming", journal = "Neural Computing and Applications", year = "2022", volume = "34", number = "2", pages = "1345--1357", month = jan, keywords = "genetic algorithms, genetic programming, Lyapunov function, Stability, Region of attraction, Pareto", ISSN = "0941-0643", URL = "https://rdcu.be/dl3Cd", URL = "https://doi.org/10.1007/s00521-021-06453-1", DOI = "doi:10.1007/s00521-021-06453-1", timestamp = "Tue, 08 Feb 2022 00:00:00 +0100", biburl = "https://dblp.org/rec/journals/nca/AliJAAM22.bib", bibsource = "dblp computer science bibliography, https://dblp.org", size = "13 pages", abstract = "In system control, stability is considered the most important factor as unstable system is impractical or dangerous to use. Lyapunov direct method, one of the most useful tools in the stability analysis of nonlinear systems, enables the design of a controller by determining the region of attraction (ROA). However, the two main challenges posed are (1) it is hard to determine the scalar function referred to as Lyapunov function, and (2) the optimality of the designed controller is generally questionable. In this paper, multi-objective genetic programming (MOGP)-based framework is proposed to obtain both optimal Lyapunov and control functions at the same time. In other words, MOGP framework is employed to minimize several time-domain performances as well as the ROA radius to find the optimal Lyapunov and control functions. The proposed framework is tested in several nonlinear benchmark systems, and the control performance is compared with state-of-the-art algorithms.", notes = "Duffing oscillator Faculty of Mechanical Engineering, University of Guilan, Rasht, Iran", } @Article{ALI:2018:AFM, author = "Mumtaz Ali and Ravinesh C. Deo and Nathan J. Downs and Tek Maraseni", title = "Cotton yield prediction with Markov Chain Monte Carlo-based simulation model integrated with genetic programing algorithm: A new hybrid copula-driven approach", journal = "Agricultural and Forest Meteorology", volume = "263", pages = "428--448", year = "2018", keywords = "genetic algorithms, genetic programming, Crop yield prediction, Cotton yield, Climate data, Markov Chain Monte Carlo based copula model", ISSN = "0168-1923", DOI = "doi:10.1016/j.agrformet.2018.09.002", URL = "http://www.sciencedirect.com/science/article/pii/S0168192318302971", abstract = "Reliable data-driven models designed to accurately estimate cotton yield, an important agricultural commodity, can be adopted by farmers, agricultural system modelling experts and agricultural policy-makers in strategic decision-making processes. In this paper a hybrid genetic programing model integrated with the Markov Chain Monte Carlo (MCMC) based Copula technique is developed to incorporate climate-based inputs as the predictors of cotton yield, for selected study regions: Faisalabad", } @InCollection{ALI:2020:HPM, author = "Mumtaz Ali and Ravinesh C. Deo", title = "Chapter 2 - Modeling wheat yield with data-intelligent algorithms: artificial neural network versus genetic programming and minimax probability machine regression", editor = "Pijush Samui and Dieu {Tien Bui} and Subrata Chakraborty and Ravinesh C. Deo", booktitle = "Handbook of Probabilistic Models", publisher = "Butterworth-Heinemann", pages = "37--87", year = "2020", isbn13 = "978-0-12-816514-0", DOI = "doi:10.1016/B978-0-12-816514-0.00002-3", URL = "http://www.sciencedirect.com/science/article/pii/B9780128165140000023", keywords = "genetic algorithms, genetic programming, Agricultural precision, Artificial neural network, Minimax probability machine regression, Wheat yield model", abstract = "In precision agriculture, data-intelligent algorithms applied for predicting wheat yield can generate crucial information about enhancing crop production and strategic decision-making. In this chapter, artificial neural network (ANN) model is trained with three neighboring station-based wheat yields to predict the yield for two nearby objective stations that share a common geographic boundary in the agricultural belt of Pakistan. A total of 2700 ANN models (with a combination of hidden neurons, training algorithm, and hidden transfer/output functions) are developed by trial-and-error method, attaining the lowest mean square error, in which the 90 best-ranked models for 3-layered neuronal network are used for wheat prediction. Models such as learning algorithms comprised of pure linear, tangent, and logarithmic sigmoid equations in hidden transfer/output functions, executed by Levenberg-Marquardt, scaled conjugate gradient, conjugate gradient with Powell-Beale restarts, Broyden-Fletcher-Goldfarb-Shanno quasi-Newton, Fletcher-Reeves update, one-step secant, conjugate gradient with Polak-Ribiere updates, gradient descent with adaptive learning, gradient descent with momentum, and gradient descent with momentum adaptive learning method are trained. For the predicted wheat yield at objective station 1 (i.e., Toba Taik Singh), the optimal architecture was 3-14-1 (input-hidden-output neurons) trained with the Levenberg-Marquardt algorithm and logarithmic sigmoid as activation and tangent sigmoid as output function, while at objective station 2 (i.e., Bakkar), the Levenberg-Marquardt algorithm provided the best architecture (3-20-1) with pure liner as activation and tangent sigmoid as output function. The results are benchmarked with those from minimax probability machine regression (MPMR) and genetic programming (GP) in accordance with statistical analysis of predicted yield based on correlations (r), Willmott's index (WI), Nash-Sutcliffe coefficient (EV), root mean-squared error (RMSE), and mean absolute error (MAE). For objective station 1, the ANN model attained the r value of approximately 0.983, with WIapprox0.984 and EVapprox0.962, while the MPMR model attained rapprox0.957, WIapprox0.544, and EVapprox0.527, with the results attained by GP model, rapprox0.982, WIapprox0.980, and EVapprox0.955. For optimal ANN model, a relatively low value of RMSE approx 192.02kg/ha and MAE approx 162.75kg/ha was registered compared with the MPMR (RMSE approx 614.46kg/ha; MAE approx 431.29kg/ha) and GP model (RMSE approx 209.25kg/ha; MAE approx 182.84kg/ha). For both objective stations, ANN was found to be superior, as confirmed by a larger Legates-McCabe's (LM) index used in conjunction with relative RMSE and MAE. Accordingly, it is averred that ANN is considered as a useful data-intelligent contrivance for predicting wheat yield by using nearest neighbor yield", } @Article{Ali:2015:JBI, author = "Safdar Ali and Abdul Majid", title = "{Can-Evo-Ens}: Classifier stacking based evolutionary ensemble system for prediction of human breast cancer using amino acid sequences", journal = "Journal of Biomedical Informatics", volume = "54", pages = "256--269", year = "2015", month = apr, keywords = "genetic algorithms, genetic programming, Breast cancer, Amino acids, Physicochemical properties, Stacking ensemble", ISSN = "1532-0464", URL = "http://www.sciencedirect.com/science/article/pii/S1532046415000064", DOI = "doi:10.1016/j.jbi.2015.01.004", abstract = "The diagnostic of human breast cancer is an intricate process and specific indicators may produce negative results. In order to avoid misleading results, accurate and reliable diagnostic system for breast cancer is indispensable. Recently, several interesting machine-learning (ML) approaches are proposed for prediction of breast cancer. To this end, we developed a novel classifier stacking based evolutionary ensemble system Can-Evo-Ens for predicting amino acid sequences associated with breast cancer. In this paper, first, we selected four diverse-type of ML algorithms of Naive Bayes, K-Nearest Neighbour, Support Vector Machines, and Random Forest as base-level classifiers. These classifiers are trained individually in different feature spaces using physicochemical properties of amino acids. In order to exploit the decision spaces, the preliminary predictions of base-level classifiers are stacked. Genetic programming (GP) is then employed to develop a meta-classifier that optimal combine the predictions of the base classifiers. The most suitable threshold value of the best-evolved predictor is computed using Particle Swarm Optimisation technique. Our experiments have demonstrated the robustness of Can-Evo-Ens system for independent validation dataset. The proposed system has achieved the highest value of Area Under Curve (AUC) of ROC Curve of 99.95percent for cancer prediction. The comparative results revealed that proposed approach is better than individual ML approaches and conventional ensemble approaches of AdaBoostM1, Bagging, GentleBoost, and Random Subspace. It is expected that the proposed novel system would have a major impact on the fields of Biomedical, Genomics, Proteomics, Bioinformatics, and Drug Development.", } @PhdThesis{Ali:thesis, author = "Safdar Ali", title = "Intelligent Decision Making Ensemble Classification System for Breast Cancer Prediction", school = "Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences", year = "2015", address = "Nilore, Islamabad, Pakistan", month = "27 " # jul, keywords = "genetic algorithms, genetic programming, Can-Evo-Ens", URL = "http://faculty.pieas.edu.pk/abdulmajid/", URL = "http://prr.hec.gov.pk/jspui/handle/123456789//7613", URL = "https://prr.hec.gov.pk/jspui/bitstream/123456789/7613/1/Safdar-Ali_Computer_and_Information_Sciences_2015_PIEAS_ISD%20PDF.pdf", size = "159 pages", abstract = "Breast cancer is a complex and heterogeneous disease which seriously impacts women’s health. The diagnostic of breast cancer is an intricate process. Therefore, an accurate and reliable prediction system for breast cancer is indispensable to avoid misleading results.In this regard, improved decision support systems are essential for breast cancer prediction. Consequently, this thesis focuses on the development of intelligent decision making systems using ensemble classification for the early prediction of breast cancer. Proteins of a breast tissue generally reflect the initial changes caused by successive genetic mutations, which may lead to cancer. In this research, such changes in protein sequences are exploited for the early diagnosis of breast cancer. It is found that substantial variation of Proline, Serine, Tyrosine, Cysteine, Arginine, and Asparagine amino acid molecules in cancerous proteins offer high discrimination for cancer diagnostic. Molecular descriptors derived from physicochemical properties of amino acids are used to transform primary protein sequences into feature spaces of amino acid composition (AAC), split amino acid composition (SAAC), pseudo amino acid composition-series (PseAAC-S), and pseudo amino acid composition-parallel (PseAAC-P). The research work in this thesis is divided in two phases. In the first phase, the basic framework is established to handle imbalanced dataset in order to enhance true prediction performance. In this phase, conventional individual learning algorithms are employed to develop different prediction systems. Firstly, in conjunction with oversampling based Mega-Trend-Diffusion (MTD) technique, individual prediction systems are developed. Secondly, homogeneous ensemble systems CanPro-IDSS and Can-CSCGnB are developed using MTD and cost-sensitive classifier (CSC) techniques, respectively. It is found that assimilation of MTD technique for the CanPro-IDSS system is superior than CSC based technique to handle imbalanced dataset of protein sequences. In this connection, a web based CanPro-IDSS cancer prediction system is also developed. Lastly, a novel heterogeneous ensemble system called IDMS-HBC is developed for breast cancer detection. The second phase of this research focuses on the exploitation of variation of amino acid molecules in cancerous protein sequences using physicochemical properties. In this phase, unlike traditional ensemble prediction approaches, the proposed IDM-PhyChm-Ens ensemble system is developed by combining the decision spaces of a specific classifier trained on different feature spaces. This intelligent ensemble system is constructed using diverse learning algorithms of Random Forest(RF), Support Vector Machines, K-Nearest Neighbor, and Naive Bayes (NB). It is observed that the combined spaces of SAAC+PseAAC-S and AAC+SAAC possess the best discrimination using ensemble-RF and ensemble-NB. Lastly, a novel classifier stacking based evolutionary ensemble system Can-Evo-Ens is also developed, whereby Genetic programming is used as the ensemble method. This study revealed that PseAAC-S feature space carries better discrimination power compared to AAC, SAAC, and PseAAC-P based feature extraction strategies. Intensive experiments are performed to evaluate the performance of the proposed intelligent decision making systems for cancer/non-cancer and breast/non-breast cancer datasets. The proposed approaches have demonstrated improvement over previous state-of-the-art approaches. The proposed systems maybe useful for academia, practitioners, and clinicians for the early diagnosis of breast cancer using protein sequences. Finally, it is expected that the findings of this research would have positive impact on diagnosis, prevention, treatment, and management of cancer", notes = "In English. PIEAS, Islamabad Supervisor: Abdul Majid Co-Supervisor: Asifullah Khan", } @Article{Ali:2010:ieeeTSE, author = "Shaukat Ali and Lionel C. Briand and Hadi Hemmati and Rajwinder K. Panesar-Walawege", title = "A Systematic Review of the Application and Empirical Investigation of Search-Based Test-Case Generation", journal = "IEEE Transactions on Software Engineering", year = "2010", volume = "36", number = "6", pages = "742--762", month = nov # "-" # dec, keywords = "genetic algorithms, genetic programming, SBSE", ISSN = "0098-5589", URL = "http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5210118&isnumber=4359463", DOI = "doi:10.1109/TSE.2009.52", size = "22 pages", abstract = "Metaheuristic search techniques have been extensively used to automate the process of generating test cases and thus providing solutions for a more cost-effective testing process. This approach to test automation, often coined as Search-based Software Testing (SBST), has been used for a wide variety of test case generation purposes. Since SBST techniques are heuristic by nature, they must be empirically investigated in terms of how costly and effective they are at reaching their test objectives and whether they scale up to realistic development artifacts. However, approaches to empirically study SBST techniques have shown wide variation in the literature. This paper presents the results of a systematic, comprehensive review that aims at characterising how empirical studies have been designed to investigate SBST cost-effectiveness and what empirical evidence is available in the literature regarding SBST cost-effectiveness and scalability. We also provide a framework that drives the data collection process of this systematic review and can be the starting point of guidelines on how SBST techniques can be empirically assessed. The intent is to aid future researchers doing empirical studies in SBST by providing an unbiased view of the body of empirical evidence and by guiding them in performing well designed empirical studies.", notes = "cites one GP paper: \cite{Wappler:2007:ASE}. TSESI-2008-09-0283", } @InProceedings{Ali:2011:ICCNIT, author = "Zulfiqar Ali and Waseem Shahzad", title = "Critical analysis of swarm intelligence based routing protocols in adhoc and sensor wireless networks", booktitle = "International Conference on Computer Networks and Information Technology (ICCNIT 2011)", year = "2011", month = "11-13 " # jul, pages = "287--292", address = "Abbottabad", size = "6 pages", abstract = "There are various bio inspired and evolutionary approaches including genetic programming (GP), Neural Network, Evolutionary programming (EP), Particle Swarm Optimisation (PSO) and Ant Colony Optimisation (ACO) used for the routing protocols in ad hoc and sensor wireless networks. There are constraints involved in these protocols due to the mobility and non infrastructure nature of an ad hoc and sensor networks. We study in this research work a probabilistic performance evaluation frameworks and Swarm Intelligence approaches (PSO, ACO) for routing protocols. The performance evaluation metrics employed for wireless and ad hoc routing algorithms is routing overhead, route optimality, and energy consumption. This survey gives critical analysis of PSO and ACO based algorithms with other approaches applied for the optimisation of an ad hoc and wireless sensor network routing protocols.", keywords = "genetic algorithms, ACO, EP, PSO, adhoc network, ant colony optimisation, bioinspired approach, critical analysis, energy consumption, evolutionary approach, evolutionary programming, mobility nature, neural network, particle swarm optimisation, probabilistic performance evaluation framework, route optimality, routing overhead, routing protocol, swarm intelligence, wireless sensor network, evolutionary computation, mobile ad hoc networks, mobility management (mobile radio), particle swarm optimisation, performance evaluation, routing protocols, wireless sensor networks", DOI = "doi:10.1109/ICCNIT.2011.6020945", ISSN = "2223-6317", notes = "not on GP Also known as \cite{6020945}", } @InProceedings{Ali:2012:SETIT, author = "Samaher Hussein Ali", booktitle = "6th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT 2012)", title = "Miner for {OACCR}: Case of medical data analysis in knowledge discovery", year = "2012", pages = "962--975", month = "21-24 " # mar, address = "Sousse, Tunisia", keywords = "genetic algorithms, genetic programming, data mining, medical administrative data processing, OACCR, TreeNet classifier, astroinformatics, bioinformatics, data mining algorithm, datasets, genetic programming data construction method, geoinformatics, hybrid techniques, knowledge discovery, medical data analysis, obtaining accurate and comprehensible classification rules, principle component analysis, scientific World Wide Web, Algorithm design and analysis, Classification algorithms, Clustering algorithms, Data mining, Databases, Training, Vegetation, Adboosting, FP-Growth, GPDCM, PCA, Random Forest", isbn13 = "978-1-4673-1657-6", DOI = "doi:10.1109/SETIT.2012.6482043", size = "14 pages", abstract = "Modern scientific data consist of huge datasets which gathered by a very large number of techniques and stored in much diversified and often incompatible data repositories as data of bioinformatics, geoinformatics, astroinformatics and Scientific World Wide Web. At the other hand, lack of reference data is very often responsible for poor performance of learning where one of the key problems in supervised learning is due to the insufficient size of the training dataset. Therefore, we try to suggest a new development a theoretically and practically valid tool for analysing small of sample data remains a critical and challenging issue for researches. This paper presents a methodology for Obtaining Accurate and Comprehensible Classification Rules (OACCR) of both small and huge datasets with the use of hybrid techniques represented by knowledge discovering. In this article the searching capability of a Genetic Programming Data Construction Method (GPDCM) has been exploited for automatically creating more visual samples from the original small dataset. Add to that, this paper attempts to developing Random Forest data mining algorithm to handle missing value problem. Then database which describes depending on their components were built by Principle Component Analysis (PCA), after that, association rule algorithm to the FP-Growth algorithm (FP-Tree) was used. At the last, TreeNet classifier determines the class under which each association rules belongs to was used. The proposed methodology provides fast, Accurate and comprehensible classification rules. Also, this methodology can be use to compression dataset in two dimensions (number of features, number of records).", notes = "Also known as \cite{6482043}", } @InProceedings{conf/icaart/Ali0NR21, author = "Muhammad Sarmad Ali and Meghana Kshirsagar and Enrique Naredo and Conor Ryan", title = "{AutoGE}: A Tool for Estimation of Grammatical Evolution Models", booktitle = "Proceedings of the 13th International Conference on Agents and Artificial Intelligence, ICAART 2021", year = "2021", editor = "Ana Paula Rocha and Luc Steels and H. Jaap {van den Herik}", volume = "2", pages = "1274--1281", address = "Online", month = feb # " 4-6", publisher = "SCITEPRESS", keywords = "genetic algorithms, genetic programming, grammatical evolution", isbn13 = "978-989-758-484-8", bibdate = "2021-03-02", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/icaart/icaart2021-2.html#Ali0NR21", DOI = "doi:10.5220/0010393012741281", } @InProceedings{conf/ijcci/Ali0NR21, author = "Muhammad Sarmad Ali and Meghana Kshirsagar and Enrique Naredo and Conor Ryan", title = "Towards Automatic Grammatical Evolution for Real-world Symbolic Regression", booktitle = "Proceedings of the 13th International Joint Conference on Computational Intelligence, IJCCI", year = "2021", editor = "Thomas Baeck and Christian Wagner and Jonathan M. Garibaldi and H. K. Lam and Marie Cottrell and Juan Julian Merelo and Kevin Warwick", pages = "68--78", address = "Online", month = oct # " 25-27", organization = "INSTICC", publisher = "SCITEPRESS", keywords = "genetic algorithms, genetic programming, grammatical evolution, grammar pruning, effective genome length", isbn13 = "978-989-758-534-0", bibdate = "2021-11-19", bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/ijcci/ijcci2021.html#Ali0NR21", DOI = "doi:10.5220/0010691500003063", size = "11 pages", abstract = "AutoGE (Automatic Grammatical Evolution) is a tool designed to aid users of GE for the automatic estimation of Grammatical Evolution (GE) parameters, a key one being the grammar. The tool comprises of a rich suite of algorithms to assist in fine tuning a BNF (Backus-Naur Form) grammar to make it adaptable across a wide range of problems. It primarily facilitates the identification of better grammar structures and the choice of function sets to enhance existing fitness scores at a lower computational overhead. we discuss and report experimental results for our Production Rule Pruning algorithm from AutoGE which employs a simple frequency-based approach for eliminating less useful productions. It captures the relationship between production rules and function sets involved in the problem domain to identify better grammar. The experimental study incorporates an extended function set and common grammar structures for grammar definition. Preliminary results based on ten popular real-world regression datasets demonstrate that the proposed algorithm not only identifies suitable grammar structures, but also prunes the grammar which results in shorter genome length for every problem, thus optimising memory usage. Despite using a fraction of budget in pruning, AutoGE was able to significantly enhance test scores for 3 problems.", notes = "Biocomputing and Developmental Systems Lab, University of Limerick, Ireland", } @InProceedings{ali:2022:GECCO, author = "Muhammad Sarmad Ali and Meghana Kshirsagar and Enrique Naredo and Conor Ryan", title = "Automated Grammar-based Feature Selection in Symbolic Regression", booktitle = "Proceedings of the 2022 Genetic and Evolutionary Computation Conference", year = "2022", editor = "Alma Rahat and Jonathan Fieldsend and Markus Wagner and Sara Tari and Nelishia Pillay and Irene Moser and Aldeida Aleti and Ales Zamuda and Ahmed Kheiri and Erik Hemberg and Christopher Cleghorn and Chao-li Sun and Georgios Yannakakis and Nicolas Bredeche and Gabriela Ochoa and Bilel Derbel and Gisele L. Pappa and Sebastian Risi and Laetitia Jourdan and Hiroyuki Sato and Petr Posik and Ofer Shir and Renato Tinos and John Woodward and Malcolm Heywood and Elizabeth Wanner and Leonardo Trujillo and Domagoj Jakobovic and Risto Miikkulainen and Bing Xue and Aneta Neumann and Richard Allmendinger and Inmaculada Medina-Bulo and Slim Bechikh and Andrew M. Sutton and Pietro Simone Oliveto", pages = "902--910", address = "Boston, USA", series = "GECCO '22", month = "9-13 " # jul, organisation = "SIGEVO", publisher = "Association for Computing Machinery", publisher_address = "New York, NY, USA", keywords = "genetic algorithms, genetic programming, feature selection, symbolic regression, production ranking, grammatical evolution, grammar pruning", isbn13 = "978-1-4503-9237-2", DOI = "doi:10.1145/3512290.3528852", abstract = "With the growing popularity of machine learning (ML), regression problems in many domains are becoming increasingly high-dimensional. Identifying relevant features from a high-dimensional dataset still remains a significant challenge for building highly accurate machine learning models.Evolutionary feature selection has been used for high-dimensional symbolic regression using Genetic Programming (GP). While grammar based GP, especially Grammatical Evolution (GE), has been extensively used for symbolic regression, no systematic grammar-based feature selection approach exists. This work presents a grammar-based feature selection method, Production Ranking based Feature Selection (PRFS), and reports on the results of its application in symbolic regression.The main contribution of our work is to demonstrate that the proposed method can not only consistently select the most relevant features, but also significantly improves the generalization performance of GE when compared with several state-of-the-art ML-based feature selection methods. Experimental results on benchmark symbolic regression problems show that the generalization performance of GE using PRFS was significantly better than that of a state-of-the-art Random Forest based feature selection in three out of four problems, while in fourth problem the performance was the same.", notes = "GECCO-2022 A Recombination of the 31st International Conference on Genetic Algorithms (ICGA) and the 27th Annual Genetic Programming Conference (GP)", } @InProceedings{Ali:2022:ICAIoT, author = "Mohammed Sadeq Ali Ali and Mesut Cevik", booktitle = "2022 International Conference on Artificial Intelligence of Things (ICAIoT)", title = "Optimization of the Number and Placement of Routers in Wireless Mesh Networks", year = "2022", abstract = "Wireless Mesh Networks (WMNs) are a new type of wireless network that has been growing in popularity. These networks consist of routers and clients. The routers are called mesh routers (MRs) and the clients are called mesh clients. WMNs have several advantages over traditional wireless networks, such as more reliable coverage and faster speeds. Many different types of algorithms can be used to determine the best placement for these routers, with some algorithms being better than others depending on the environment or situation. One algorithm is called a Genetic Algorithm (GA), which uses genetic programming to find an optimal solution for router placement. GA is used to find the best placement of the router so that it can provide the most coverage possible for a specific area GA or evolutionary algorithms are based on a biological theory known as Darwin's theory. In evolutionary algorithms, it is since the information of the problem becomes chromosomes, and then the problem is solved by special problem-solving techniques in the evolutionary algorithm. The suggested method was implemented using the C++ programming environment and the NS2 software suite. Using a benchmark of produced instances, the experimental outcomes have been analysed. Variable sets of produced instances ranging in size from small to big have been explored. Consequently, several properties of WMNs, including the topological placement of mesh clients, have been recorded.", keywords = "genetic algorithms, genetic programming, Wireless networks, Wireless mesh networks, Evolutionary computation, Software, Reliability, Problem-solving, Internet of Things, IOT, routers, wireless network, WMNs", DOI = "doi:10.1109/ICAIoT57170.2022.10121861", month = dec, notes = "Also known as \cite{10121861}", } @Article{ALI:2023:istruc, author = "Mujahid Ali and Sai {Hin Lai}", title = "Artificial intelligent techniques for prediction of rock strength and deformation properties - A review", journal = "Structures", volume = "55", pages = "1542--1555", year = "2023", ISSN = "2352-0124", DOI = "doi:10.1016/j.istruc.2023.06.131", URL = "https://www.sciencedirect.com/science/article/pii/S2352012423008901", keywords = "genetic algorithms, genetic programming, Deformation, Unconfined Compressive Strength (UCS), Intelligent techniques, ANN, Statistical analysis", abstract = "In rock design projects, a number of mechanical properties are frequently employed, particularly unconfined compressive strength (UCS) and deformation (E). The researchers attempt to conduct an indirect investigation since direct measurement of UCS and E is time-consuming, expensive, and requires more expertise and methodologies. Recent and past studies investigate the UCS and E from rock index tests mainly P-wave velocity (Vp), slake durability index, Density, Shore hardness, Schmidt hammer Rebound number (Rn), unit weight, porosity (e) point load strength (Is(50)), and block punch strength index test as its economical and easy to use. The evaluation of these properties is the essential input into modern design methods that routinely adopt some form of numerical modeling, such as machine learning (ML), Artificial Neural Networking (ANN), finite element modeling (FEM), and finite difference methods. Besides, several researchers evaluate the correlation between the input parameters using statistical analysis tools before using them for intelligent techniques. The current study compared the results of laboratory tests, statistical analysis, and intelligent techniques for UCS and E estimation including ANN and adaptive neuro-fuzzy inference system (ANFIS), Genetic Programming (GP), Genetic Expression Programming (GEP), and hybrid models. Following the execution of the relevant models, numerous performance indicators, such as root mean squared error, coefficient of determination (R2), variance account for, and overall ranking, are reviewed to choose the best model and compare the acquired results. Based on the current review, it is concluded that the same rock types from different countries show different mechanical properties due to weathering, size, texture, mineral composition, and temperature. For instance, in the UCS of strong rock (granite) in Spain, ranges from 24 MPa to 278 MPa, whereas in Malaysian rocks, it shows 39 MPa to 212 MPa. On the other side, the coefficient of determination (R2) correlation for the UCS also varies from country to country; while using different modern techniques, the R2 values improved. Finally, recommendations on material properties and modern techniques have been suggested", } @InProceedings{Alibekov:2016:CDC, author = "Eduard Alibekov and Jiri Kubalik and Robert Babuska", booktitle = "2016 IEEE 55th Conference on Decision and Control (CDC)", title = "Symbolic method for deriving policy in reinforcement learning", year = "2016", pages = "2789--2795", abstract = "This paper addresses the problem of deriving a policy from the value function in the context of reinforcement learning in continuous state and input spaces. We propose a novel method based on genetic programming to construct a symbolic function, which serves as a proxy to the value function and from which a continuous policy is derived. The symbolic proxy function is constructed such that it maximizes the number of correct choices of the control input for a set of selected states. Maximization methods can then be used to derive a control policy that performs better than the policy derived from the original approximate value function. The method was experimentally evaluated on two control problems with continuous spaces, pendulum swing-up and magnetic manipulation, and compared to a standard policy derivation method using the value function approximation. The results show that the proposed method and its variants outperform the standard method.", keywords = "genetic algorithms, genetic programming", DOI = "doi:10.1109/CDC.2016.7798684", month = dec, notes = "Also known as \cite{7798684}", } @PhdThesis{Alibekov:thesis, author = "Eduard Alibekov", title = "Symbolic Regression for Reinforcement Learning in Continuous Spaces", school = "F3 Faculty of Electrical Engineering, Department of Cybernetics, Czech Technical University in Prague", year = "2021", address = "Czech Republic", month = aug, keywords = "genetic algorithms, genetic programming, Single Node Genetic Programming, reinforcement learning, optimal control, function approximation,evolutionary optimization, symbolic regression, robotics, autonomous systems", URL = "https://cyber.felk.cvut.cz/news/eduard-alibekov-defended-his-ph-d-thesis/", URL = "http://hdl.handle.net/10467/98283", URL = "https://dspace.cvut.cz/handle/10467/98283", URL = "https://dspace.cvut.cz/bitstream/handle/10467/98283/F3-D-2021-Alibekov-Eduard-phd_ready.pdf", size = "134 pages", abstract = "Reinforcement Learning (RL) algorithms can optimally solve dynamic decision and control problems in engineering, economics, medicine, artificial intelligence, and other disciplines.However, state-of-the-art RL methods still have not solved the transition from a small set of discrete states to fully continuous spaces. They have to rely on numerical function approximators, such as radial basis functions or neural networks, to represent the value function or policy mappings. While these numerical approximators are well-developed, the choice of a suitable architecture is a difficult step that requires significant trial-and-error tuning. Moreover, numerical approximators frequently exhibit uncontrollable surface artifacts that damage the overall performance of the controlled system. Symbolic Regression (SR) is an evolutionary optimization technique that automatically, without human intervention, generates analytical expressions to fit numerical data. The method has gained attention in the scientific community not only for its ability to recover known physical laws, but also for suggesting yet unknown but physically plausible and interpretable relationships. Additionally, the analytical nature of the result approximators allows to unleash the full power of mathematical apparatus. This thesis aims to develop methods to integrate SR into RL in a fully continuous case. To accomplish this goal, the following original contributions to the field have been developed. (i) Introduction of policy derivation methods. Their main goal is to exploit the full potential of using continuous action spaces, contrary to the state-of-the-art discretised set of actions. (ii) Quasi-symbolic policy derivation (QSPD) algorithm, specifically designed to be used with a symbolic approximation of the value function. The goal of the proposed algorithm is to efficiently derive continuous policy out of symbolic approximator. The experimental evaluation indicated the superiority of QSPD over state-of-the-art methods. (iii) Design of a symbolic proxy-function concept. Such a function is successfully used to alleviate the