Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms

Detalhes bibliográficos
Autor(a) principal: Pereira, Luís A. M.
Data de Publicação: 2017
Outros Autores: Papa, João P. [UNESP], Coelho, André L. V., Lima, Clodoaldo A. M., Pereira, Danillo R. [UNESP], de Albuquerque, Victor Hugo C.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/s00521-017-3124-3
http://hdl.handle.net/11449/179040
Resumo: Epilepsy is a class of chronic neurological disorders characterized by transient and unexpected electrical disturbances of the brain. The automated analysis of the electroencephalogram (EEG) signal can be instrumental for the proper diagnosis of this mental condition. This work presents a systematic assessment of the performance of different variants of the binary magnetic optimization algorithm (BMOA), two of which are introduced here, while serving as feature selectors for epileptic EEG signal identification. In this context, the optimum-path forest classifier was adopted as a classification model, whereas different wavelet families were considered for EEG feature extraction. In order to compare the performance of the improved BMOA variants against the traditional one, as well as other metaheuristic techniques, namely particle swarm optimization, binary bat algorithm, and genetic algorithm, we employed a well-known EEG benchmark dataset composed of five classes of EEG signals (two of which comprising normal patients with eyes open or closed, and the remaining comprising ill patients with different levels of epilepsy). Overall, the results evidenced the robustness of the proposed BMOA and its variants.
id UNSP_36086d0a9155a5637407bfd813ac535e
oai_identifier_str oai:repositorio.unesp.br:11449/179040
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Automatic identification of epileptic EEG signals through binary magnetic optimization algorithmsEEG signal classificationEpilepsyFeature selectionMagnetic optimization algorithmMetaheuristicsOptimum-path forestEpilepsy is a class of chronic neurological disorders characterized by transient and unexpected electrical disturbances of the brain. The automated analysis of the electroencephalogram (EEG) signal can be instrumental for the proper diagnosis of this mental condition. This work presents a systematic assessment of the performance of different variants of the binary magnetic optimization algorithm (BMOA), two of which are introduced here, while serving as feature selectors for epileptic EEG signal identification. In this context, the optimum-path forest classifier was adopted as a classification model, whereas different wavelet families were considered for EEG feature extraction. In order to compare the performance of the improved BMOA variants against the traditional one, as well as other metaheuristic techniques, namely particle swarm optimization, binary bat algorithm, and genetic algorithm, we employed a well-known EEG benchmark dataset composed of five classes of EEG signals (two of which comprising normal patients with eyes open or closed, and the remaining comprising ill patients with different levels of epilepsy). Overall, the results evidenced the robustness of the proposed BMOA and its variants.Instituto de Computação Universidade Estadual de CampinasDepartamento de Computação UNESP - Univ Estadual PaulistaPrograma de Pós-Graduação em Informática Aplicada Universidade de FortalezaEscola de Artes Ciências e Humanidades Universidade de São PauloDepartamento de Computação UNESP - Univ Estadual PaulistaUniversidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (Unesp)Universidade de FortalezaUniversidade de São Paulo (USP)Pereira, Luís A. M.Papa, João P. [UNESP]Coelho, André L. V.Lima, Clodoaldo A. M.Pereira, Danillo R. [UNESP]de Albuquerque, Victor Hugo C.2018-12-11T17:33:16Z2018-12-11T17:33:16Z2017-06-28info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1-13application/pdfhttp://dx.doi.org/10.1007/s00521-017-3124-3Neural Computing and Applications, p. 1-13.0941-0643http://hdl.handle.net/11449/17904010.1007/s00521-017-3124-32-s2.0-850251469782-s2.0-85025146978.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengNeural Computing and Applications0,700info:eu-repo/semantics/openAccess2024-04-23T16:10:45Zoai:repositorio.unesp.br:11449/179040Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:10:19.477997Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
title Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
spellingShingle Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
Pereira, Luís A. M.
EEG signal classification
Epilepsy
Feature selection
Magnetic optimization algorithm
Metaheuristics
Optimum-path forest
title_short Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
title_full Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
title_fullStr Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
title_full_unstemmed Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
title_sort Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms
author Pereira, Luís A. M.
author_facet Pereira, Luís A. M.
Papa, João P. [UNESP]
Coelho, André L. V.
Lima, Clodoaldo A. M.
Pereira, Danillo R. [UNESP]
de Albuquerque, Victor Hugo C.
author_role author
author2 Papa, João P. [UNESP]
Coelho, André L. V.
Lima, Clodoaldo A. M.
Pereira, Danillo R. [UNESP]
de Albuquerque, Victor Hugo C.
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual de Campinas (UNICAMP)
Universidade Estadual Paulista (Unesp)
Universidade de Fortaleza
Universidade de São Paulo (USP)
dc.contributor.author.fl_str_mv Pereira, Luís A. M.
Papa, João P. [UNESP]
Coelho, André L. V.
Lima, Clodoaldo A. M.
Pereira, Danillo R. [UNESP]
de Albuquerque, Victor Hugo C.
dc.subject.por.fl_str_mv EEG signal classification
Epilepsy
Feature selection
Magnetic optimization algorithm
Metaheuristics
Optimum-path forest
topic EEG signal classification
Epilepsy
Feature selection
Magnetic optimization algorithm
Metaheuristics
Optimum-path forest
description Epilepsy is a class of chronic neurological disorders characterized by transient and unexpected electrical disturbances of the brain. The automated analysis of the electroencephalogram (EEG) signal can be instrumental for the proper diagnosis of this mental condition. This work presents a systematic assessment of the performance of different variants of the binary magnetic optimization algorithm (BMOA), two of which are introduced here, while serving as feature selectors for epileptic EEG signal identification. In this context, the optimum-path forest classifier was adopted as a classification model, whereas different wavelet families were considered for EEG feature extraction. In order to compare the performance of the improved BMOA variants against the traditional one, as well as other metaheuristic techniques, namely particle swarm optimization, binary bat algorithm, and genetic algorithm, we employed a well-known EEG benchmark dataset composed of five classes of EEG signals (two of which comprising normal patients with eyes open or closed, and the remaining comprising ill patients with different levels of epilepsy). Overall, the results evidenced the robustness of the proposed BMOA and its variants.
publishDate 2017
dc.date.none.fl_str_mv 2017-06-28
2018-12-11T17:33:16Z
2018-12-11T17:33:16Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1007/s00521-017-3124-3
Neural Computing and Applications, p. 1-13.
0941-0643
http://hdl.handle.net/11449/179040
10.1007/s00521-017-3124-3
2-s2.0-85025146978
2-s2.0-85025146978.pdf
url http://dx.doi.org/10.1007/s00521-017-3124-3
http://hdl.handle.net/11449/179040
identifier_str_mv Neural Computing and Applications, p. 1-13.
0941-0643
10.1007/s00521-017-3124-3
2-s2.0-85025146978
2-s2.0-85025146978.pdf
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Neural Computing and Applications
0,700
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 1-13
application/pdf
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808128613448417280