Decoding motor imagery tasks using ESI and hybrid feature CNN

Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Electrophysiological source imaging (ESI) technology is used to solve the i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of neural engineering Ročník 19; číslo 1
Hlavní autori: Fang, Tao, Song, Zuoting, Zhan, Gege, Zhang, Xueze, Mu, Wei, Wang, Pengchao, Zhang, Lihua, Kang, Xiaoyang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England 01.02.2022
Predmet:
ISSN:1741-2552, 1741-2552
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting. The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy. Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.
AbstractList Objective.Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem.Approach.Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting.Main results.The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy.Significance.Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.Objective.Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem.Approach.Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting.Main results.The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy.Significance.Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.
Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new framework is proposed to solve the MI-EEG binary classification problem. Electrophysiological source imaging (ESI) technology is used to solve the influence of volume conduction effect and improve spatial resolution. Continuous wavelet transform and best time of interest (TOI) are combined to extract the optimal discriminant spatial-frequency features. Finally, a convolutional neural network with seven convolution layers is used to classify the features. In addition, we also validated several new data augment methods to solve the problem of small data sets and reduce network over-fitting. The model achieved an average classification accuracy of 93.2% and 95.4% on the BCI Competition III IVa and high-gamma data sets, which is better than most of the published advanced algorithms. By selecting the best TOI for each subject, the classification accuracy rate increased by about 2%. The effects of four data augment methods on the classification results were also verified. Among them, the noise addition and overlap methods are better than the other two, and the classification accuracy is improved by at least 4%. On the contrary, the rotation and flip data augment methods reduced the classification accuracy. Decoding MI tasks can benefit from combing the ESI technology and the data augment technology, which is used to solve the problem of low spatial resolution and small samples of EEG signals, respectively. Based on the results, the model proposed has higher accuracy and application potential in the task of MI-EEG binary classification.
Author Zhan, Gege
Wang, Pengchao
Kang, Xiaoyang
Zhang, Lihua
Mu, Wei
Fang, Tao
Zhang, Xueze
Song, Zuoting
Author_xml – sequence: 1
  givenname: Tao
  orcidid: 0000-0002-8464-3585
  surname: Fang
  fullname: Fang, Tao
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 2
  givenname: Zuoting
  orcidid: 0000-0003-0433-6882
  surname: Song
  fullname: Song, Zuoting
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 3
  givenname: Gege
  orcidid: 0000-0003-3369-8751
  surname: Zhan
  fullname: Zhan, Gege
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 4
  givenname: Xueze
  orcidid: 0000-0001-8884-2277
  surname: Zhang
  fullname: Zhang, Xueze
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 5
  givenname: Wei
  orcidid: 0000-0002-5731-679X
  surname: Mu
  fullname: Mu, Wei
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 6
  givenname: Pengchao
  orcidid: 0000-0001-9304-6478
  surname: Wang
  fullname: Wang, Pengchao
  organization: Laboratory for Neural Interface and Brain Computer Interface, Engineering Research Center of AI & Robotics, Ministry of Education, Shanghai Engineering Research Center of AI & Robotics, MOE Frontiers Center for Brain Science, State Key Laboratory of Medical Neurobiology, Institute of AI & Robotics, Academy for Engineering & Technology, Fudan University, Shanghai, People's Republic of China
– sequence: 7
  givenname: Lihua
  orcidid: 0000-0003-0467-4347
  surname: Zhang
  fullname: Zhang, Lihua
  organization: Ji Hua Laboratory, Foshan, People's Republic of China
– sequence: 8
  givenname: Xiaoyang
  orcidid: 0000-0003-4372-9531
  surname: Kang
  fullname: Kang, Xiaoyang
  organization: Research Center for Intelligent Sensing, Zhejiang Laboratory, Hangzhou, People's Republic of China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35078158$$D View this record in MEDLINE/PubMed
BookMark eNpNjztPwzAURi1URB-wMyGPLKF-xLE9MKBQoFJVBrpHjn1TAnkUOxny70lFQUzf1XePru6Zo0nTNoDQNSV3lCi1pDKmEROCLY2NwZEzNPurJv_mKZqH8EEIp1KTCzTlgkhFhZqh-0ewrSubPa7brvW4rM0e_IA7Ez4D7sNxs3pbY9M4_D7kvnS4ANP1HnC63V6i88JUAa5OuUC7p9UufYk2r8_r9GETWZ6oLlJFISyxMifGyDyWXBNmOCccpHaxcAVLpOKxNtRywQRoIkwR2_FBlmiVswW6_Tl78O1XD6HL6jJYqCrTQNuHjCWM6eQoNaI3J7TPa3DZwY9Gfsh-jdk3mXxYFQ
CitedBy_id crossref_primary_10_1109_JBHI_2024_3450753
crossref_primary_10_1016_j_neucom_2025_130250
crossref_primary_10_3390_sym14122677
crossref_primary_10_1016_j_bbe_2023_10_004
crossref_primary_10_1109_ACCESS_2023_3339857
crossref_primary_10_1016_j_bspc_2025_107526
crossref_primary_10_1007_s00521_023_08944_9
crossref_primary_10_1109_TNSRE_2024_3461339
crossref_primary_10_1109_TNSRE_2024_3383452
crossref_primary_10_1088_1741_2552_ad4914
crossref_primary_10_1088_1361_6560_adcafa
crossref_primary_10_1016_j_neucom_2024_128577
crossref_primary_10_1080_10255842_2024_2401918
crossref_primary_10_1088_1741_2552_add8bb
crossref_primary_10_1109_TNSRE_2023_3249831
crossref_primary_10_3389_fnins_2023_1194190
ContentType Journal Article
Copyright 2022 IOP Publishing Ltd.
Copyright_xml – notice: 2022 IOP Publishing Ltd.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1088/1741-2552/ac4ed0
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Anatomy & Physiology
EISSN 1741-2552
ExternalDocumentID 35078158
Genre Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID ---
1JI
4.4
53G
5B3
5GY
5VS
5ZH
7.M
7.Q
AAGCD
AAJIO
AAJKP
AATNI
ABHWH
ABJNI
ABQJV
ABVAM
ACAFW
ACGFS
ACHIP
AEFHF
AENEX
AFYNE
AKPSB
ALMA_UNASSIGNED_HOLDINGS
AOAED
ASPBG
ATQHT
AVWKF
AZFZN
CEBXE
CGR
CJUJL
CRLBU
CS3
CUY
CVF
DU5
EBS
ECM
EDWGO
EIF
EMSAF
EPQRW
EQZZN
F5P
HAK
IHE
IJHAN
IOP
IZVLO
KOT
LAP
M45
N5L
N9A
NPM
P2P
PJBAE
RIN
RO9
ROL
RPA
SY9
W28
XPP
7X8
ADEQX
AEINN
ID FETCH-LOGICAL-c368t-8ff5c0c7b0aa7b473902a3303e79d45df2678349a1c3525e905af4c1582698b2
IEDL.DBID 7X8
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000754919400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1741-2552
IngestDate Fri Sep 05 08:26:20 EDT 2025
Thu Jan 02 22:54:35 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords data augment
convolutional neural network (CNN)
motor imagery (MI)
electroencephalogram (EEG)
electrophysiological source imaging (ESI)
Language English
License 2022 IOP Publishing Ltd.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c368t-8ff5c0c7b0aa7b473902a3303e79d45df2678349a1c3525e905af4c1582698b2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-5731-679X
0000-0001-9304-6478
0000-0003-3369-8751
0000-0003-0467-4347
0000-0002-8464-3585
0000-0003-0433-6882
0000-0003-4372-9531
0000-0001-8884-2277
PMID 35078158
PQID 2622963507
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2622963507
pubmed_primary_35078158
PublicationCentury 2000
PublicationDate 2022-02-01
PublicationDateYYYYMMDD 2022-02-01
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-02-01
  day: 01
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Journal of neural engineering
PublicationTitleAlternate J Neural Eng
PublicationYear 2022
SSID ssj0031790
Score 2.429398
Snippet Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a new...
Objective.Brain-computer interface (BCI) based on motor imaging electroencephalogram (MI-EEG) can be useful in a natural interaction system. In this paper, a...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
SubjectTerms Algorithms
Brain-Computer Interfaces
Electroencephalography
Imagination - physiology
Neural Networks, Computer
Wavelet Analysis
Title Decoding motor imagery tasks using ESI and hybrid feature CNN
URI https://www.ncbi.nlm.nih.gov/pubmed/35078158
https://www.proquest.com/docview/2622963507
Volume 19
WOSCitedRecordID wos000754919400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3LS8MwGA_qPHjxNR_zRQTxFtYmbdMcRMbc0INl4A67jTQPHbJ2rlPYf--XtpsnQfDSQ2hp-fpLvt_3RuiGehpQKxXRytMkMMwjMjaCKMqs7yvNfVMNm-BJEo9GYlA73Io6rXJ1JpYHtc6V85G3aUQpgAXoy_3sg7ipUS66Wo_Q2EQNBlTGoZqP1lEE5rpPVQWRPgHqTOswJWys9nqtLVVgtPc7wSwVTX_vv5-4j3Zriok7FSYO0IbJDlGzk4F5PV3iW1wmfZbe9Ca6ewDz06kvDL8sn-PJ1PW0WOKFLN4L7JLiX3Hv5QnLTOO3pavuwtaUvUBxN0mO0LDfG3YfST1RgSgWxQsSWxsqT_HUk5KnAWfCo5KBFjNc6CDUlkZu8IaQvnJtUo3wQmkD5YdghIg4pcdoK8szc4owtcYV0QYR43C_tUKlqZDAPVggLQ9NC12vZDQGwLoohMxM_lmMf6TUQieVoMezqrPG2K3G8LazPzx9jnaoK0UoM6gvUMPCdjWXaFt9LSbF_KpEAlyTwfM32IC7vQ
linkProvider ProQuest
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=Decoding+motor+imagery+tasks+using+ESI+and+hybrid+feature+CNN&rft.jtitle=Journal+of+neural+engineering&rft.au=Fang%2C+Tao&rft.au=Song%2C+Zuoting&rft.au=Zhan%2C+Gege&rft.au=Zhang%2C+Xueze&rft.date=2022-02-01&rft.issn=1741-2552&rft.eissn=1741-2552&rft.volume=19&rft.issue=1&rft_id=info:doi/10.1088%2F1741-2552%2Fac4ed0&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1741-2552&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1741-2552&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1741-2552&client=summon