Skip to Main content Skip to Navigation
Book sections

Classification of EEG signals by evolutionary algorithm

Laurent Vezard 1, 2 Pierrick Legrand 1, 2 Marie Chavent 2 Frederique Faita-Ainseba 3 Julien Clauzel 3 Leonardo Trujillo 4
1 IMB - Institut de Mathématiques de Bordeaux
2 CQFD - Quality control and dynamic reliability
IMB - Institut de Mathématiques de Bordeaux, Inria Bordeaux - Sud-Ouest
3 Université Bordeaux Segalen - Bordeaux 2
4 Instituto Tecnológico de Tijuana
Abstract : The goal of this work is to predict the state of alertness of an individual by analyzing the brain activity through electroencephalographic data (EEG) captured with 58 electrodes. Alertness is characterized here 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 show that the proposed strategy derives accurate predictive models of alertness.
Document type :
Book sections
Complete list of metadatas
https://hal.inria.fr/hal-00939850
Contributor : Pierrick Legrand <>
Submitted on : Thursday, January 30, 2014 - 10:54:45 PM
Last modification on : Wednesday, December 9, 2020 - 3:06:04 PM

Identifiers

Collections

CNRS | INRIA | IMB | INSMI

Citation

Laurent Vezard, Pierrick Legrand, Marie Chavent, Frederique Faita-Ainseba, Julien Clauzel, et al.. Classification of EEG signals by evolutionary algorithm. Guillet, F. and Pinaud, B. and Venturini, G. and Zighed, D.A. Advances in Knowledge Discovery and Management Volume 4, 527, Springer, pp.133-153, 2014, Studies in Computational Intelligence, ISBN 978-3-319-02998-6. ⟨10.1007/978-3-319-02999-3_8⟩. ⟨hal-00939850⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

621

 

Contact                    Legal Notice                    Personal Data