VEZARD, Laurent; LEGRAND, Pierrick; CHAVENT, Marie; FAITA-AINSEBA, Frederique; CLAUZEL, Julien

Métadonnées

Afficher la notice complète

Licence d’utilisation du document

VEZARD, Laurent
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]

LEGRAND, Pierrick
Institut de Mathématiques de Bordeaux [IMB]
Advanced Learning Evolutionary Algorithms [ALEA]

CHAVENT, Marie
Quality control and dynamic reliability [CQFD]

Langue

Communication dans un congrès

Ce document a été publié dans

COMPSTAT 2012 - 20th International Conference on Computational Statistics, 2012-08-27, Limassol. 2012-08-27

Résumé en anglais

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.< Réduire

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251