EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/ACCESS.2021.3135805 http://hdl.handle.net/11449/234066 |
Resumo: | Electroencephalogram signals (EEG) have provided biometric identification systems with great capabilities. Several studies have shown that EEG introduces unique and universal features besides specific strength against spoofing attacks. Essentially, EEG is a graphic recording of the brain’s electrical activity calculated by sensors (electrodes) on the scalp at different spots, but their best locations are uncertain. In this paper, the EEG channel selection problem is formulated as a binary optimization problem, where a binary version of the Grey Wolf Optimizer (BGWO) is used to find an optimal solution for such an NP-hard optimization problem. Further, a Support Vector Machine classifier with a Radial Basis Function kernel (SVM-RBF) is then considered for EEG-based biometric person identification. For feature extraction purposes, we examine three different auto-regressive coefficients. A standard EEG motor imagery dataset is employed to evaluate the proposed method, including four criteria: (i) Accuracy, (ii) F-Score, (iii) Recall, and (v) Specificity. In the experimental results, the proposed method (named BGWO-SVM) obtained 94.13% accuracy using only 23 sensors with 5 auto-regressive coefficients. Besides, BGWO-SVM finds electrodes not too close to each other to capture relevant information all over the head. As concluding remarks, BGWO-SVM achieved the best results concerning the number of selected channels and competitive classification accuracies against other meta-heuristics algorithms. |
id |
UNSP_0f4c145932e07e8caf68a8ed0af931d5 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/234066 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
EEG Channel Selection for Person Identification Using Binary Grey Wolf OptimizerAuthenticationElectrodesElectroencephalographyIris recognitionSensorsSupport vector machinesVisualizationElectroencephalogram signals (EEG) have provided biometric identification systems with great capabilities. Several studies have shown that EEG introduces unique and universal features besides specific strength against spoofing attacks. Essentially, EEG is a graphic recording of the brain’s electrical activity calculated by sensors (electrodes) on the scalp at different spots, but their best locations are uncertain. In this paper, the EEG channel selection problem is formulated as a binary optimization problem, where a binary version of the Grey Wolf Optimizer (BGWO) is used to find an optimal solution for such an NP-hard optimization problem. Further, a Support Vector Machine classifier with a Radial Basis Function kernel (SVM-RBF) is then considered for EEG-based biometric person identification. For feature extraction purposes, we examine three different auto-regressive coefficients. A standard EEG motor imagery dataset is employed to evaluate the proposed method, including four criteria: (i) Accuracy, (ii) F-Score, (iii) Recall, and (v) Specificity. In the experimental results, the proposed method (named BGWO-SVM) obtained 94.13% accuracy using only 23 sensors with 5 auto-regressive coefficients. Besides, BGWO-SVM finds electrodes not too close to each other to capture relevant information all over the head. As concluding remarks, BGWO-SVM achieved the best results concerning the number of selected channels and competitive classification accuracies against other meta-heuristics algorithms.Universiti Kebangsaan Malaysia Center for Artificial Intelligence Faculty of Information Science and Technology, BangiUniversity of Kufa Information Technology Research and Development Center (ITRDC)University of Sharjah MLALP Research GroupAjman University Artificial Intelligence Research Center (AIRC) College of Engineering and Information TechnologyTorrens University Australia Fortitude Valley Centre for Artificial Intelligence Research and OptimisationYonsei University Yonsei Frontier LaboratoryAl-Huson University College Al-Balqa Applied University Al-Huson Department of Information TechnologyUniversity of Kufa ITRDCSão Paulo State University Department of ComputingSão Paulo State University Department of ComputingFaculty of Information Science and TechnologyInformation Technology Research and Development Center (ITRDC)MLALP Research GroupCollege of Engineering and Information TechnologyCentre for Artificial Intelligence Research and OptimisationYonsei Frontier LaboratoryAl-HusonITRDCUniversidade Estadual Paulista (UNESP)Alyasseri, Zaid Abdi AlkareemAlomari, Osama AhmadMakhadmeh, Sharif NaserMirjalili, SeyedaliAl-Betar, Mohammed AzmiAbdullah, SalwaniAli, Nabeel SalihPapa, Joao P. [UNESP]Rodrigues, Douglas [UNESP]Abasi, Ammar Kamal2022-05-01T13:11:34Z2022-05-01T13:11:34Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article10500-10513http://dx.doi.org/10.1109/ACCESS.2021.3135805IEEE Access, v. 10, p. 10500-10513.2169-3536http://hdl.handle.net/11449/23406610.1109/ACCESS.2021.31358052-s2.0-85123727420Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIEEE Accessinfo:eu-repo/semantics/openAccess2024-04-23T16:10:42Zoai:repositorio.unesp.br:11449/234066Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T14:02:51.524196Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
title |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
spellingShingle |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer Alyasseri, Zaid Abdi Alkareem Authentication Electrodes Electroencephalography Iris recognition Sensors Support vector machines Visualization |
title_short |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
title_full |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
title_fullStr |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
title_full_unstemmed |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
title_sort |
EEG Channel Selection for Person Identification Using Binary Grey Wolf Optimizer |
author |
Alyasseri, Zaid Abdi Alkareem |
author_facet |
Alyasseri, Zaid Abdi Alkareem Alomari, Osama Ahmad Makhadmeh, Sharif Naser Mirjalili, Seyedali Al-Betar, Mohammed Azmi Abdullah, Salwani Ali, Nabeel Salih Papa, Joao P. [UNESP] Rodrigues, Douglas [UNESP] Abasi, Ammar Kamal |
author_role |
author |
author2 |
Alomari, Osama Ahmad Makhadmeh, Sharif Naser Mirjalili, Seyedali Al-Betar, Mohammed Azmi Abdullah, Salwani Ali, Nabeel Salih Papa, Joao P. [UNESP] Rodrigues, Douglas [UNESP] Abasi, Ammar Kamal |
author2_role |
author author author author author author author author author |
dc.contributor.none.fl_str_mv |
Faculty of Information Science and Technology Information Technology Research and Development Center (ITRDC) MLALP Research Group College of Engineering and Information Technology Centre for Artificial Intelligence Research and Optimisation Yonsei Frontier Laboratory Al-Huson ITRDC Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Alyasseri, Zaid Abdi Alkareem Alomari, Osama Ahmad Makhadmeh, Sharif Naser Mirjalili, Seyedali Al-Betar, Mohammed Azmi Abdullah, Salwani Ali, Nabeel Salih Papa, Joao P. [UNESP] Rodrigues, Douglas [UNESP] Abasi, Ammar Kamal |
dc.subject.por.fl_str_mv |
Authentication Electrodes Electroencephalography Iris recognition Sensors Support vector machines Visualization |
topic |
Authentication Electrodes Electroencephalography Iris recognition Sensors Support vector machines Visualization |
description |
Electroencephalogram signals (EEG) have provided biometric identification systems with great capabilities. Several studies have shown that EEG introduces unique and universal features besides specific strength against spoofing attacks. Essentially, EEG is a graphic recording of the brain’s electrical activity calculated by sensors (electrodes) on the scalp at different spots, but their best locations are uncertain. In this paper, the EEG channel selection problem is formulated as a binary optimization problem, where a binary version of the Grey Wolf Optimizer (BGWO) is used to find an optimal solution for such an NP-hard optimization problem. Further, a Support Vector Machine classifier with a Radial Basis Function kernel (SVM-RBF) is then considered for EEG-based biometric person identification. For feature extraction purposes, we examine three different auto-regressive coefficients. A standard EEG motor imagery dataset is employed to evaluate the proposed method, including four criteria: (i) Accuracy, (ii) F-Score, (iii) Recall, and (v) Specificity. In the experimental results, the proposed method (named BGWO-SVM) obtained 94.13% accuracy using only 23 sensors with 5 auto-regressive coefficients. Besides, BGWO-SVM finds electrodes not too close to each other to capture relevant information all over the head. As concluding remarks, BGWO-SVM achieved the best results concerning the number of selected channels and competitive classification accuracies against other meta-heuristics algorithms. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-05-01T13:11:34Z 2022-05-01T13:11:34Z 2022-01-01 |
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/10.1109/ACCESS.2021.3135805 IEEE Access, v. 10, p. 10500-10513. 2169-3536 http://hdl.handle.net/11449/234066 10.1109/ACCESS.2021.3135805 2-s2.0-85123727420 |
url |
http://dx.doi.org/10.1109/ACCESS.2021.3135805 http://hdl.handle.net/11449/234066 |
identifier_str_mv |
IEEE Access, v. 10, p. 10500-10513. 2169-3536 10.1109/ACCESS.2021.3135805 2-s2.0-85123727420 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
IEEE Access |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
10500-10513 |
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_ |
1808128308990181376 |