Calibration-Free Transfer Learning for EEG-Based Cross-Subject Motor Imagery Classification

Motor imagery based brain-computer interfaces (MI-BCIs) have been widely used in intelligent medical applications such as post-stroke rehabilitation and mobile assistant robots. However, the high inter-subject variability and the non-stationarity of EEG characteristics limit the cross-subject applic...

Full description

Saved in:
Bibliographic Details
Published in:IEEE International Conference on Automation Science and Engineering (CASE) pp. 1 - 6
Main Authors: Wang, Yihan, Wang, Jiaxing, Wang, Weiqun, Su, Jianqiang, Hou, Zeng-Guang
Format: Conference Proceeding
Language:English
Published: IEEE 26.08.2023
Subjects:
Brain modeling
Brain-computer interfaces
Calibration-free
Computer aided software engineering
cross-subject
EEG
Electroencephalography
Medical services
motor imagery
Training
Transfer learning
ISSN:2161-8089
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Motor imagery based brain-computer interfaces (MI-BCIs) have been widely used in intelligent medical applications such as post-stroke rehabilitation and mobile assistant robots. However, the high inter-subject variability and the non-stationarity of EEG characteristics limit the cross-subject applications of MI-BCIs. Long-term calibration can be used to improve EEG-based performance, but which will cause low efficiency and reduce practicality. To overcome the limitation, data from other subjects can be used for transfer learning to reduce calibration time. Therefore, a calibration-free transfer learning method for EEG-based cross-subject MI classification is proposed in this paper. On one hand, Euclidean alignment and Riemannian alignment are introduced to reduce domain differences. On the other hand, the similarity is calculated by Multiple Kernel-Maximum Mean Discrepancy (MK-MMD) to select appropriate source domain samples, which is followed by domain adversarial training of neural network (DANN) for the final model construction. In order to achieve calibration-free, the new subjects' resting-state data was used only. Extensive experiments were conducted on BCI competition IV dataset 2a. The results show that the proposed method can achieve 75.96% classification accuracy without using subjects' labeled data, which demonstrates the feasibility of the proposed method in calibration time reduction and classification accuracy improvement.
AbstractList Motor imagery based brain-computer interfaces (MI-BCIs) have been widely used in intelligent medical applications such as post-stroke rehabilitation and mobile assistant robots. However, the high inter-subject variability and the non-stationarity of EEG characteristics limit the cross-subject applications of MI-BCIs. Long-term calibration can be used to improve EEG-based performance, but which will cause low efficiency and reduce practicality. To overcome the limitation, data from other subjects can be used for transfer learning to reduce calibration time. Therefore, a calibration-free transfer learning method for EEG-based cross-subject MI classification is proposed in this paper. On one hand, Euclidean alignment and Riemannian alignment are introduced to reduce domain differences. On the other hand, the similarity is calculated by Multiple Kernel-Maximum Mean Discrepancy (MK-MMD) to select appropriate source domain samples, which is followed by domain adversarial training of neural network (DANN) for the final model construction. In order to achieve calibration-free, the new subjects' resting-state data was used only. Extensive experiments were conducted on BCI competition IV dataset 2a. The results show that the proposed method can achieve 75.96% classification accuracy without using subjects' labeled data, which demonstrates the feasibility of the proposed method in calibration time reduction and classification accuracy improvement.
Author Wang, Weiqun
Hou, Zeng-Guang
Wang, Yihan
Wang, Jiaxing
Su, Jianqiang
Author_xml – sequence: 1
  givenname: Yihan
  surname: Wang
  fullname: Wang, Yihan
  email: wangyihan2022@ia.ac.cn
  organization: School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049
– sequence: 2
  givenname: Jiaxing
  surname: Wang
  fullname: Wang, Jiaxing
  email: jiaxingwang@ia.ac.cn
  organization: School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049
– sequence: 3
  givenname: Weiqun
  surname: Wang
  fullname: Wang, Weiqun
  email: weiqunwang@ia.ac.cn
  organization: School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049
– sequence: 4
  givenname: Jianqiang
  surname: Su
  fullname: Su, Jianqiang
  email: sujianqiang2021@ia.ac.cn
  organization: School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049
– sequence: 5
  givenname: Zeng-Guang
  surname: Hou
  fullname: Hou, Zeng-Guang
  email: zengguang.hou@ia.ac.cn
  organization: School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049
BookMark eNo1kM1OAjEYAKvRREDewMR9gWL_tz3iZkESjAfw5IF82_1KSmDXtOuBt9egnuYwyRxmTG66vkNCHjmbcc7cUzXf1NoYW84EE3LGmTBMKXZFpq50VmomBTNOX5OR4IZTy6y7I-OcD4wZZjkfkY8KjrFJMMS-o4uEWGwTdDlgKtYIqYvdvgh9Kup6SZ8hY1tUqc-Zbr6aA_qheO2HH7s6wR7TuaiOkHMM0V969-Q2wDHj9I8T8r6ot9ULXb8tV9V8TaNgaqC6VOC1FMADtKbVAUrphdGNQsVabFAHLNEZ9KoFI7nxIYBBq7y3jXZCTsjDbzci4u4zxROk8-5_hvwGIwxXLg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CASE56687.2023.10260440
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350320695
EISSN 2161-8089
EndPage 6
ExternalDocumentID 10260440
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: U1913601,62203440
  funderid: 10.13039/501100001807
– fundername: Beijing Natural Science Foundation
  grantid: 4202074
  funderid: 10.13039/501100004826
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ACGFS
ADZIZ
AKRWK
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i204t-574ac532a1fad6d5fa73c265b4e40debe5fe7e96ec4da6316cffa6e84cc8b5923
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001545311800217&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:50:45 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-574ac532a1fad6d5fa73c265b4e40debe5fe7e96ec4da6316cffa6e84cc8b5923
PageCount 6
ParticipantIDs ieee_primary_10260440
PublicationCentury 2000
PublicationDate 2023-Aug.-26
PublicationDateYYYYMMDD 2023-08-26
PublicationDate_xml – month: 08
  year: 2023
  text: 2023-Aug.-26
  day: 26
PublicationDecade 2020
PublicationTitle IEEE International Conference on Automation Science and Engineering (CASE)
PublicationTitleAbbrev CASE
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0060811
Score 1.8784662
Snippet Motor imagery based brain-computer interfaces (MI-BCIs) have been widely used in intelligent medical applications such as post-stroke rehabilitation and mobile...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Brain modeling
Brain-computer interfaces
Calibration-free
Computer aided software engineering
cross-subject
EEG
Electroencephalography
Medical services
motor imagery
Training
Transfer learning
Title Calibration-Free Transfer Learning for EEG-Based Cross-Subject Motor Imagery Classification
URI https://ieeexplore.ieee.org/document/10260440
WOSCitedRecordID wos001545311800217&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPOjFV8U3OXhN3d3msTlq2aqgpeCDgoeSx0Q82EptBf-9k3Tr4-DB27JLsjDD5ptvdr4ZQk6c8M5AZKqx8Ilbr5jVYJHzSCQTSjubtDAP16rXKwcD3a_F6kkLAwCp-Axa8TL9y_djN4upMvzCcQfOkaEvKyXnYq3FsSsR2_K6gCvP9Gnn7LbCUKVUrTggvLVY-muISsKQ7vo_375Bmt9qPNr_wplNsgSjLbL2o5HgNnmMEis7dybrTgBowiBcTesGqk8Uo1NaVRfsHHHL005ER4bHRszD0JsxUm969RIbWnzQNCgzlhCl_ZrkvlvddS5ZPTaBPRcZnzKhuHGiXZg8GC-9CEa1XSGF5cAzj04TARRoCY57I9u5dCEYCSV3rrQCA74d0hiNR7BLaHwerLPOc8mD0dqWqgQ0gi0g0-D2SDPaafg674wxXJho_4_7B2Q1eiPmZAt5SBrTyQyOyIp7nz6_TY6TPz8BC2ejAw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5EBfXiq-LbPXhNTdJ9ZI9aUltsS8EqBQ9lHxPpwVZqK_jvnd2mPg4evIWE3cAM2W--yXwzhFxa7qwGz1R94RMzTkZGgUHOI5BMSGVN0MI8tmW3mw0GqleK1YMWBgBC8RlU_WX4l-8mdu5TZfiF4w6MIUNf44yl8UKutTx4BaJbUpZwJbG6ql_f5xisZLLqR4RXl4t_jVEJKNLY_uf7d0jlW49He19Is0tWYLxHtn60EtwnT15kZRbujBpTABpQCFfTsoXqM8X4lOb5bXSDyOVo3eNjhAeHz8TQzgTJN229-JYWHzSMyvRFRGG_Cnlo5P16MyoHJ0SjNGaziEumLa-lOim0E44XWtZsKrhhwGKHbuMFSFACLHNa1BJhi0ILyJi1meEY8h2Q1fFkDIeE-ueFscY6JlihlTKZzACNYFKIFdgjUvF2Gr4uemMMlyY6_uP-Bdlo9jvtYbvVvTshm94zPkObilOyOpvO4Yys2_fZ6G16Hnz7CbKRpko
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%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Conference+on+Automation+Science+and+Engineering+%28CASE%29&rft.atitle=Calibration-Free+Transfer+Learning+for+EEG-Based+Cross-Subject+Motor+Imagery+Classification&rft.au=Wang%2C+Yihan&rft.au=Wang%2C+Jiaxing&rft.au=Wang%2C+Weiqun&rft.au=Su%2C+Jianqiang&rft.date=2023-08-26&rft.pub=IEEE&rft.eissn=2161-8089&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FCASE56687.2023.10260440&rft.externalDocID=10260440