Generalized Optimal EEG Channels Selection for Motor Imagery Brain-Computer Interface

Brain-computer interfaces (BCI) enable people to communicate with external instruments through brain activity recorded by electroencephalography (EEG). BCI based on motor imagery (MI) can distinguish activation of specific brain regions by decoding EEG signals and then applying them to different sit...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE sensors journal Jg. 23; H. 20; S. 25356 - 25366
Hauptverfasser:	Lee, Hsiang-Chen, Lee, Ching-Hung
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 15.10.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Brain modeling Channel selection Channels Classification Datasets deep learning EEG-Net Electric potential Electrodes Electroencephalography electroencephalography (EEG) Feature extraction generalized optimal EEG channels Genetic algorithms Human-computer interface Imagery lateralized readiness potential (LRP) motor imagery (MI) non-dominated sorting genetic algorithm (NSGA)-II algorithm optimization Sensors Sorting algorithms Task analysis
ISSN:	1530-437X, 1558-1748
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Brain-computer interfaces (BCI) enable people to communicate with external instruments through brain activity recorded by electroencephalography (EEG). BCI based on motor imagery (MI) can distinguish activation of specific brain regions by decoding EEG signals and then applying them to different situations. Because the activation regions of the brain are specific, using all EEG channels for classification is redundant and may lead to feature confusion and inconvenience for users when applying EEG. Current EEG channel selection methods focus primarily on a single subject and require the data from the subject to generate the chosen channel, which is inconvenient on the application side to determine suitable channels for new subjects. Therefore, this study introduces a novel method for generalized EEG channel selection. Two datasets are used: the BCI competition IV 2a dataset for generating generalized EEG channels and the OpenBMI dataset for validation by numerous subjects. First, the signals from each channel are fed into EEG-Net for classification and ranked by loss to generate optimal EEG channels. Then, the methods of ranking and non-dominated sorting genetic algorithm (NSGA)-II are used to find different combinations of optimal potential differences. Finally, the generalized EEG channels are generated and validated by EEG-Net again. The validation results show that 88.5% of the subjects can be well-classified in one session, including MI-illiteracy, defined by the dataset. The average accuracy is 77.7% and 79.26% in Sessions 1 and 2, using the average channel number around 5, instead of channels from the motor cortex region or all placed EEG channels.
AbstractList	Brain–computer interfaces (BCI) enable people to communicate with external instruments through brain activity recorded by electroencephalography (EEG). BCI based on motor imagery (MI) can distinguish activation of specific brain regions by decoding EEG signals and then applying them to different situations. Because the activation regions of the brain are specific, using all EEG channels for classification is redundant and may lead to feature confusion and inconvenience for users when applying EEG. Current EEG channel selection methods focus primarily on a single subject and require the data from the subject to generate the chosen channel, which is inconvenient on the application side to determine suitable channels for new subjects. Therefore, this study introduces a novel method for generalized EEG channel selection. Two datasets are used: the BCI competition IV 2a dataset for generating generalized EEG channels and the OpenBMI dataset for validation by numerous subjects. First, the signals from each channel are fed into EEG-Net for classification and ranked by loss to generate optimal EEG channels. Then, the methods of ranking and non-dominated sorting genetic algorithm (NSGA)-II are used to find different combinations of optimal potential differences. Finally, the generalized EEG channels are generated and validated by EEG-Net again. The validation results show that 88.5% of the subjects can be well-classified in one session, including MI-illiteracy, defined by the dataset. The average accuracy is 77.7% and 79.26% in Sessions 1 and 2, using the average channel number around 5, instead of channels from the motor cortex region or all placed EEG channels.
Author	Lee, Ching-Hung Lee, Hsiang-Chen
Author_xml	– sequence: 1 givenname: Hsiang-Chen surname: Lee fullname: Lee, Hsiang-Chen organization: Institute of Electrical and Control Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan – sequence: 2 givenname: Ching-Hung orcidid: 0000-0003-3081-362X surname: Lee fullname: Lee, Ching-Hung email: chl@nycu.edu.tw organization: Institute of Electrical and Control Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
BookMark	eNp9kDFPwzAQhS1UJNrCD0BiiMSc4rOTOBkhCqWo0KFUYoss5wKpUjs47lB-PY7aATGwvDud7t3TfRMy0kYjIddAZwA0u3teF68zRhmfcQ6c8eSMjCGO0xBElI6GntMw4uL9gkz6fkspZCIWY7KZo0Yr2-Ybq2DVuWYn26Ao5kH-KbXGtg_W2KJyjdFBbWzwYpzXxU5-oD0ED1Y2OszNrts79GPttZYKL8l5Ldser051SjaPxVv-FC5X80V-vwwVyyIXClGlEjIKCVSUYlpFinGMKeUYcRVVLGKQcagTxpKa0QQzwSRHKVSVpKIGPiW3x7udNV977F25NXurfWTJUpHGVGRJ5rfguKWs6XuLddlZ_6c9lEDLgV450CsHeuWJnveIPx7VODlgcP7n9l_nzdHZIOKvJBYDMMp_AEQ0fW8
CODEN	ISJEAZ
CitedBy_id	crossref_primary_10_1016_j_eswa_2024_123239 crossref_primary_10_3390_s25010120 crossref_primary_10_1080_09540091_2024_2426812 crossref_primary_10_1109_ACCESS_2024_3473810
Cites_doi	10.1093/gigascience/gix034 10.3390/bioengineering9040141 10.1109/TBME.2011.2131142 10.1016/S1388-2457(02)00057-3 10.1007/s12559-015-9379-z 10.1016/j.neucom.2016.05.035 10.1038/s41598-020-62712-6 10.1109/IEMBS.2009.5333585 10.1109/TBME.2008.923152 10.3390/s120201211 10.1371/journal.pone.0000637 10.1038/s41598-022-15252-0 10.1016/0013-4694(68)90080-1 10.1109/JAS.2020.1003336 10.1109/MSP.2008.4408441 10.3389/fnins.2022.1045851 10.1088/1741-2552/ac115d 10.1093/acprof:oso/9780195388855.001.0001 10.1109/JPROC.2012.2184829 10.1088/1741-2552/aace8c 10.3389/fnins.2012.00055 10.3390/bioengineering9120726 10.1109/ACCESS.2020.3009665 10.1093/gigascience/giz002 10.1109/TNSRE.2006.875642 10.1109/TBME.2004.827827 10.3389/fnbot.2017.00060 10.1109/IoT-SIU.2018.8519891 10.1109/4235.996017 10.1016/B978-0-12-800945-1.00023-9 10.1109/IJCNN.2008.4634130 10.1016/j.bspc.2021.102621 10.1145/3397850 10.1016/j.bspc.2021.102983 10.1109/BMEI.2011.6098380 10.1109/TNSRE.2020.3048106 10.1007/s10462-019-09694-8 10.1109/MC.2012.107 10.3390/bioengineering9070323 10.1109/TNSRE.2020.3020975 10.1007/BF00412364 10.1088/1741-2552/ac0583
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2023.3313236
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	25366
ExternalDocumentID	10_1109_JSEN_2023_3313236 10251120
Genre	orig-research
GrantInformation_xml	– fundername: National Science and Technology Council; National Science and Technology Council of Taiwan grantid: NSTC- 11-2221-E-A49-168-MY3; 110-2221-E-A49-121-MY2; 110-2221-E-224-026; 110-2634-F-007-027 funderid: 10.13039/100020595
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c294t-77d8a190161d00e8d4c23e5003e43c4d2421931f6226f206e972a3ea7cd687f13
IEDL.DBID	RIE
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001098067300144&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Mon Jun 30 10:13:21 EDT 2025 Sat Nov 29 06:39:42 EST 2025 Tue Nov 18 21:07:00 EST 2025 Wed Aug 27 02:34:56 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	20
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c294t-77d8a190161d00e8d4c23e5003e43c4d2421931f6226f206e972a3ea7cd687f13
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-3081-362X
PQID	2878507969
PQPubID	75733
PageCount	11
ParticipantIDs	crossref_primary_10_1109_JSEN_2023_3313236 proquest_journals_2878507969 crossref_citationtrail_10_1109_JSEN_2023_3313236 ieee_primary_10251120
PublicationCentury	2000
PublicationDate	2023-10-15
PublicationDateYYYYMMDD	2023-10-15
PublicationDate_xml	– month: 10 year: 2023 text: 2023-10-15 day: 15
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref37 tam (ref17) 2011 ref36 ref30 ref11 ref33 ref10 ref32 islam (ref31) 2017; 14 ref2 ref1 ref39 ref16 ref38 ref19 bridle (ref47) 1989 ref18 thakor (ref6) 2012 ref24 ref23 ref45 ref26 ref25 ref20 ref42 ref41 ref22 ref44 chollet (ref46) 2016 ref21 ref43 ref28 ref27 ref29 ref8 faye (ref14) 2022; 9 ref7 ref9 ref4 ref3 ref5 ref40
References_xml	– ident: ref44 doi: 10.1093/gigascience/gix034 – ident: ref12 doi: 10.3390/bioengineering9040141 – ident: ref5 doi: 10.1109/TBME.2011.2131142 – ident: ref2 doi: 10.1016/S1388-2457(02)00057-3 – ident: ref15 doi: 10.1007/s12559-015-9379-z – ident: ref16 doi: 10.1016/j.neucom.2016.05.035 – ident: ref25 doi: 10.1038/s41598-020-62712-6 – ident: ref19 doi: 10.1109/IEMBS.2009.5333585 – ident: ref9 doi: 10.1109/TBME.2008.923152 – ident: ref3 doi: 10.3390/s120201211 – ident: ref13 doi: 10.1371/journal.pone.0000637 – ident: ref24 doi: 10.1038/s41598-022-15252-0 – ident: ref41 doi: 10.1016/0013-4694(68)90080-1 – ident: ref34 doi: 10.1109/JAS.2020.1003336 – ident: ref45 doi: 10.1109/MSP.2008.4408441 – ident: ref23 doi: 10.3389/fnins.2022.1045851 – ident: ref28 doi: 10.1088/1741-2552/ac115d – ident: ref1 doi: 10.1093/acprof:oso/9780195388855.001.0001 – start-page: 211 year: 1989 ident: ref47 article-title: Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters publication-title: Proc 2nd Int Conf Neural Inf Process Syst – ident: ref8 doi: 10.1109/JPROC.2012.2184829 – ident: ref37 doi: 10.1088/1741-2552/aace8c – start-page: 6344 year: 2011 ident: ref17 article-title: Performance of common spatial pattern under a smaller set of EEG electrodes in brain-computer interface on chronic stroke patients: A multi-session dataset study publication-title: Proc Annu Int Conf IEEE Eng Med Biol Soc – ident: ref38 doi: 10.3389/fnins.2012.00055 – volume: 9 start-page: 726 year: 2022 ident: ref14 article-title: EEG channel selection techniques in motor imagery applications: A review and new perspectives publication-title: Bioengineering doi: 10.3390/bioengineering9120726 – volume: 14 year: 2017 ident: ref31 article-title: Unsupervised frequency-recognition method of SSVEPs using a filter bank implementation of binary subband CCA publication-title: J Neural Eng – ident: ref36 doi: 10.1109/ACCESS.2020.3009665 – ident: ref39 doi: 10.1093/gigascience/giz002 – ident: ref43 doi: 10.1109/TNSRE.2006.875642 – ident: ref10 doi: 10.1109/TBME.2004.827827 – ident: ref33 doi: 10.3389/fnbot.2017.00060 – year: 2016 ident: ref46 article-title: Xception: Deep learning with depthwise separable convolutions publication-title: arXiv 1610 02357 – ident: ref30 doi: 10.1109/IoT-SIU.2018.8519891 – ident: ref42 doi: 10.1109/4235.996017 – ident: ref7 doi: 10.1016/B978-0-12-800945-1.00023-9 – ident: ref18 doi: 10.1109/IJCNN.2008.4634130 – ident: ref27 doi: 10.1016/j.bspc.2021.102621 – ident: ref29 doi: 10.1145/3397850 – ident: ref32 doi: 10.1016/j.bspc.2021.102983 – ident: ref20 doi: 10.1109/BMEI.2011.6098380 – year: 2012 ident: ref6 article-title: Building brain machine interfaces-Neuroprosthetic control with electrocorticographic signals publication-title: IEEE Life Sci Newslett – ident: ref35 doi: 10.1109/TNSRE.2020.3048106 – ident: ref21 doi: 10.1007/s10462-019-09694-8 – ident: ref4 doi: 10.1109/MC.2012.107 – ident: ref11 doi: 10.3390/bioengineering9070323 – ident: ref22 doi: 10.1109/TNSRE.2020.3020975 – ident: ref40 doi: 10.1007/BF00412364 – ident: ref26 doi: 10.1088/1741-2552/ac0583
SSID	ssj0019757
Score	2.4100018
Snippet	Brain-computer interfaces (BCI) enable people to communicate with external instruments through brain activity recorded by electroencephalography (EEG). BCI... Brain–computer interfaces (BCI) enable people to communicate with external instruments through brain activity recorded by electroencephalography (EEG). BCI...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	25356
SubjectTerms	Brain modeling Channel selection Channels Classification Datasets deep learning EEG-Net Electric potential Electrodes Electroencephalography electroencephalography (EEG) Feature extraction generalized optimal EEG channels Genetic algorithms Human-computer interface Imagery lateralized readiness potential (LRP) motor imagery (MI) non-dominated sorting genetic algorithm (NSGA)-II algorithm optimization Sensors Sorting algorithms Task analysis
Title	Generalized Optimal EEG Channels Selection for Motor Imagery Brain-Computer Interface
URI	https://ieeexplore.ieee.org/document/10251120 https://www.proquest.com/docview/2878507969
Volume	23
WOSCitedRecordID	wos001098067300144&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-1748 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019757 issn: 1530-437X databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5UBPXgW6wv9uBJSN0km30cVVofaBVU6C2kmwkK2optBf31zmy3VRAFbznshpAvs_PNbub7GNtXOgFdqCwyADKSqmOjTmxUBLERsopJktyLuF7qVsu02_YmNKv7XhgA8D-fQZ0u_Vl-2XND2irDCCdCnGCFPq21GjVrTY4MrPaynhjBIpKpbocjzFjYw4vbRqtOPuH1lJQKvRzzVxLyrio_lmKfX5pL_3yyZbYYiCQ_GiG_wqagu8oWvskLrrK54HD-8L7G7oO-9OMHlPwa14lnnNxonHJqL-higuS33hEHYeLIY_lVD4txfv5MEhfv_JiMJKKxAwT324hV4WCd3TcbdydnUbBUiFxi5QC5dGkK4gAqLoUAU0qXpJBhaINMnSzpgNimcaWQlVWJUGB1UqRQaFcqoxG7DTbT7XVhk3GRiUpaVRQVVnRZZTqxTokPQFIaLLJcjYnxO85d0Bsn24un3NcdwuYES06w5AGWGjuYTHkZiW38NXidcPg2cARBje2MkcxDPPZzrAsNMl-r7NYv07bZPN2d0lKc7bCZwesQdtmsexs89l_3_Kf2CQzEzQE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9tAEB1VFIlyAMqHCKVlDz0hOV3b6_04UhQKJaSVACk3y1mPRSRIEAQk-uuZ2WwACYHUmw-7suXn2Xmz63kP4Ls2GZpKF4lFVInSA5cMUqsTTK1UTcqS5EHEtWt6Pdvvu7-xWT30wiBi-PkM23wZzvLrsb_jrTKKcCbEGVXoHwulMjlt13o6NHAmCHtSDMtE5aYfDzFT6X78Pu302uwU3s5ZqzAIMj-noeCr8moxDhnmYPk_n20FliKVFHtT7D_DBxytwuILgcFVWIge5xcPa3AeFaaH_7AWf2iluKLJnc4vwQ0GI0qR4jR44hBQgpisOBlTOS6Orljk4kH8ZCuJZOYBIcJGYlN5XIfzg87Z_mESTRUSnzk1ITZd24pZgE5rKdHWymc5FhTcqHKvaj4idnnaaOJlTSY1OpNVOVbG19oaQm8D5kbjEW6CkIVslNNV1VBNVzR2kJqcGQFmtaUyy7dAzt5x6aPiOBtfXJah8pCuZFhKhqWMsLRg92nK9VRu473B64zDi4FTCFqwPUOyjBF5W1JlaIn7Ou223pi2AwuHZyfdsnvUO_4Cn_hOnKTSYhvmJjd3-BXm_f1keHvzLXx2j-NR0Eg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Generalized+Optimal+EEG+Channels+Selection+for+Motor+Imagery+Brain-Computer+Interface&rft.jtitle=IEEE+sensors+journal&rft.au=Lee%2C+Hsiang-Chen&rft.au=Lee%2C+Ching-Hung&rft.date=2023-10-15&rft.pub=IEEE&rft.issn=1530-437X&rft.volume=23&rft.issue=20&rft.spage=25356&rft.epage=25366&rft_id=info:doi/10.1109%2FJSEN.2023.3313236&rft.externalDocID=10251120
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon