Afficher la notice abrégée

Classification of EEG signals by evolutionary algorithm

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierQuality control and dynamic reliability [CQFD]
dc.contributor.authorVEZARD, Laurent
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierQuality control and dynamic reliability [CQFD]
dc.contributor.authorLEGRAND, Pierrick
hal.structure.identifierQuality control and dynamic reliability [CQFD]
dc.contributor.authorCHAVENT, Marie
hal.structure.identifierUniversité Bordeaux Segalen - Bordeaux 2
dc.contributor.authorFAITA-AINSEBA, Frederique
hal.structure.identifierUniversité Bordeaux Segalen - Bordeaux 2
dc.contributor.authorCLAUZEL, Julien
hal.structure.identifierInstituto Tecnológico de Tijuana = Tijuana Institute of Technology [Tijuana]
dc.contributor.authorTRUJILLO, Leonardo
dc.contributor.editorGuillet
dc.contributor.editorF. and Pinaud
dc.contributor.editorB. and Venturini
dc.contributor.editorG. and Zighed
dc.contributor.editorD.A
dc.date.accessioned2024-04-04T02:19:56Z
dc.date.available2024-04-04T02:19:56Z
dc.date.issued2014
dc.identifier.isbnISBN 978-3-319-02998-6
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/189447
dc.description.abstractEnThe 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.
dc.language.isoen
dc.publisherSpringer
dc.source.titleAdvances in Knowledge Discovery and Management Volume 4
dc.title.enClassification of EEG signals by evolutionary algorithm
dc.typeChapitre d'ouvrage
dc.identifier.doi10.1007/978-3-319-02999-3_8
dc.subject.halInformatique [cs]/Traitement du signal et de l'image
dc.subject.halSciences de l'ingénieur [physics]/Traitement du signal et de l'image
dc.subject.halMathématiques [math]/Statistiques [math.ST]
dc.subject.halStatistiques [stat]/Théorie [stat.TH]
dc.subject.halSciences du Vivant [q-bio]/Neurosciences [q-bio.NC]
bordeaux.page133-153
bordeaux.volume527
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.title.proceedingAdvances in Knowledge Discovery and Management Volume 4
hal.identifierhal-00939850
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-00939850v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Advances%20in%20Knowledge%20Discovery%20and%20Management%20Volume%204&rft.date=2014&rft.volume=527&rft.spage=133-153&rft.epage=133-153&rft.au=VEZARD,%20Laurent&LEGRAND,%20Pierrick&CHAVENT,%20Marie&FAITA-AINSEBA,%20Frederique&CLAUZEL,%20Julien&rft.isbn=ISBN%20978-3-319-02998-6&rft.genre=unknown


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée