Analysis of the performance of Genetic Programming on the Blood Glucose Level Prediction Challenge 2020

Created by W.Langdon from gp-bibliography.bib Revision:1.7954

@InProceedings{DBLP:conf/ecai/JoedickeKCWVCH20,

• author = "David Joedicke and Gabriel Kronberger and Jose Manuel Colmenar and Stephan M. Winkler and Jose Manuel Velasco and Sergio Contador and Jose Ignacio Hidalgo",
• editor = "Kerstin Bach and Razvan C. Bunescu and Cindy Marling and Nirmalie Wiratunga",
• title = "Analysis of the performance of Genetic Programming on the Blood Glucose Level Prediction Challenge 2020",
• booktitle = "Proceedings of the 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial Intelligence, KDH@ECAI 2020",
• series = "CEUR Workshop Proceedings",
• volume = "2675",
• pages = "141--145",
• publisher = "CEUR-WS.org",
• year = "2020",
• address = "Santiago de Compostela, Spain and Virtually",
• month = aug # " 29-30",
• keywords = "genetic algorithms, genetic programming, Grammatical Evolution, Random Forest, ARIMA, GP-OS, GE, MOGE",
• URL = "http://ceur-ws.org/Vol-2675/paper25.pdf",
• timestamp = "Wed, 23 Sep 2020 17:50:25 +0200",
• biburl = "https://dblp.org/rec/conf/ecai/JoedickeKCWVCH20.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• size = "5 pages",
• abstract = "we present results for the Blood Glucose Level Prediction Challenge for the Ohio2020 dataset. We have used four variants of genetic programming to build white-box models for predicting 30 minutes and 60 minutes ahead. The results are compared to classical methods including multi-variate linear regression,random forests, as well as two types of ARIMA models. Notably,we have included future values of bolus and basal into some of the models because we assume that these values can be controlled. Additionally, we have used a convolution filter to smooth the information in the bolus volume feature. We find that overall tree-based GP performs well and better than multivariate linear regression and random forest, while ARIMA models performed worst on the here analysed data.",
• notes = "Josef Ressel Center for Symbolic Regression, Upper Austria University of Applied Sciences",

}

Genetic Programming entries for David Joedicke Gabriel Kronberger J Manuel Colmenar Stephan M Winkler Jose Manuel Velasco Cabo Sergio Contador Jose Ignacio Hidalgo Perez

Citations