Classification of EEG signals by an evolutionary algorithm

Published in Book Chapters

  1. Laurent Vezard, Pierrick Legrand, Marie Chavent, Frederique Faita-Ainseba, Julien Clauzel and others. Classification of EEG signals by an evolutionary algorithm. In COMPSTAT 2012. 2012. BibTeX

    @inproceedings{vezard2012classification,
    	title = "Classification of EEG signals by an evolutionary algorithm",
    	author = "Vezard, Laurent and Legrand, Pierrick and Chavent, Marie and Faita-Ainseba, Frederique and Clauzel, Julien and others",
    	booktitle = "COMPSTAT 2012",
    	year = 2012
    }
    

Abstract

The goal is to predict the alertness of an individual by analyzing the brain activity through electroencephalographic data (EEG) captured with 58 electrodes. Alertness is characterized as a binary variable that can be in a normal or relaxed state. We collected data from 44 subjects before and after a relaxation practice, giving a total of 88 records. After a pre-processing step and data validation, we analyzed each record and discriminate the alertness states using our proposed slope criterion. Afterwards, several common methods for supervised classification (k nearest neighbors, decision trees -CART-, random forests, PLS and discriminant sparse PLS) were applied as predictors for the state of alertness of each subject. The proposed slope criterion was further refined using a genetic algorithm to select the most important EEG electrodes in terms of classification accuracy. Results shown that the proposed strategy derives accurate predictive models of alertness.

Published in
Advances in Knowledge Discovery and Management
Pages 137-158
Volume 4
http://hal.inria.fr/hal-00759439/
Copyright
2013
Feedback