Abstract
Genetic programming (GP) has proved successful at evolving pattern classifiers and although the paradigm lends itself easily to continuous pattern attributes, incorporating categorical attributes is little studied. Here we construct two synthetic datasets specifically to investigate the use of categorical attributes in GP and consider two possible approaches: indicator variables and integer mapping. We conclude that for ordered attributes, integer mapping yields the lowest errors. For purely nominal attributes, indicator variables give the best misclassification errors.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alpaydin, E.: Combined 5 ×2 cv F-test for comparing supervised classification learning algorithms. Neural Computation 11, 1885–1892 (1999)
Dietterich, T.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10, 1895–1923 (1998)
Ekárt, A., Németh, S.Z.: Selection based on the Pareto nondomination criterion for controlling code growth in genetic programming. Genetic Programming & Evolvable Machines 2, 61–73 (2001)
Fonseca, C.M., Fleming, P.J.: Multi-objective optimization and multiple constraints handling with evolutionary algorithms. Part 1: A unified formulation. IEEE Trans. Systems, Man & Cybernetics 28, 26–37 (1998)
Guo, H., Jack, L.B., Nandi, A.K.: Feature generation using genetic programming with application to fault classification. IEEE Transactions on Systems, Man & Cybernetics - Part B 35, 89–99 (2005)
Ito, T., Iba, H., Sato, S.: Non-destructive depth-dependent crossover for genetic programming. In: 1st European Workshop on Genetic Programming, Paris, France, pp. 14–15 (1998)
Krawiec, K.: Genetic programming-based construction of features for machine learning and knowledge discovery tasks. Genetic Programming & Evolvable Machines 3, 329–343 (2002)
Kumar, R., Rockett, P.: Improved sampling of the Pareto-front in multi-objective genetic optimization by steady-state evolution: A Pareto converging genetic algorithm. Evolutionary Computation 10, 283–314 (2002)
Loveard, T., Ciesielski, V.: Representing classification problems in genetic programming. In: Congress on Evolutionary Computation, Seoul, Korea, pp. 1070–1077 (2001)
Loveard, T., Ciesielski, V.: Employing nominal attributes in classification using genetic programming. In: 4th Asia-Pacific Conference on Simulated Evolution and Learning (SEAL 2002), Singapore, pp. 487–491 (2002)
Smith, M.G., Bull, L.: Genetic programming with a genetic algorithm for feature construction and selection. Genetic Programming & Evolvable Machines 6, 265–281 (2005)
Tian, Y., Deng, N.: Support vector classification with nominal attributes. In: Hao, Y., Liu, J., Wang, Y.-P., Cheung, Y.-m., Yin, H., Jiao, L., Ma, J., Jiao, Y.-C. (eds.) CIS 2005. LNCS (LNAI), vol. 3801, pp. 586–591. Springer, Heidelberg (2005)
Zhang, Y., Rockett, P.I.: Evolving optimal feature extraction using multi-objective genetic programming: A methodology and preliminary study on edge detection. In: Genetic & Evolutionary Computation Conference (GECCO 2005), Washington, DC, pp. 795–802 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Badran, K., Rockett, P. (2008). Integrating Categorical Variables with Multiobjective Genetic Programming for Classifier Construction. In: O’Neill, M., et al. Genetic Programming. EuroGP 2008. Lecture Notes in Computer Science, vol 4971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78671-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-78671-9_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78670-2
Online ISBN: 978-3-540-78671-9
eBook Packages: Computer ScienceComputer Science (R0)