Residual-Enhanced VAE-GAN for EEG Data Augmentation in Motor Imagery Classification

Motor imagery is a widely studied paradigm in Brain-Computer Interfaces (BCIs) systems, where electroencephalography (EEG) signals are used to decode brain activity. However, subject-specific variability leads to significant differences in EEG distributions across individuals, making it challenging...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE International Conference on Consumer Electronics-China (Online) S. 603 - 604
Hauptverfasser: Tang, Haiyuan, Zhao, Wenshan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 16.07.2025
Schlagworte:
ISSN:2575-8284
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Motor imagery is a widely studied paradigm in Brain-Computer Interfaces (BCIs) systems, where electroencephalography (EEG) signals are used to decode brain activity. However, subject-specific variability leads to significant differences in EEG distributions across individuals, making it challenging for models trained on existing subject data to generalize well to unseen individuals. To improve the diversity of training data and enhance model generalization, this paper proposes an EEG data augmentation method, termed Residual-Enhanced Variational Autoencoder-Generative Adversarial Network (REVG). The framework combines a Variational Autoencoder for EEG reconstruction with a Wasserstein Generative Adversarial Network to generate realistic residual signals, enriching EEG data distribution. Experimental results on the BCI Competition IV 2b dataset demonstrate that REVG achieves an average classification accuracy of 76.83%, outperforming the baseline and other data augmentation methods.
AbstractList Motor imagery is a widely studied paradigm in Brain-Computer Interfaces (BCIs) systems, where electroencephalography (EEG) signals are used to decode brain activity. However, subject-specific variability leads to significant differences in EEG distributions across individuals, making it challenging for models trained on existing subject data to generalize well to unseen individuals. To improve the diversity of training data and enhance model generalization, this paper proposes an EEG data augmentation method, termed Residual-Enhanced Variational Autoencoder-Generative Adversarial Network (REVG). The framework combines a Variational Autoencoder for EEG reconstruction with a Wasserstein Generative Adversarial Network to generate realistic residual signals, enriching EEG data distribution. Experimental results on the BCI Competition IV 2b dataset demonstrate that REVG achieves an average classification accuracy of 76.83%, outperforming the baseline and other data augmentation methods.
Author Tang, Haiyuan
Zhao, Wenshan
Author_xml – sequence: 1
  givenname: Haiyuan
  surname: Tang
  fullname: Tang, Haiyuan
  email: 22120126@bjtu.edu.cn
  organization: Beijing Jiaotong University,School of Electronic and Information Engineering,Beijing,China,100044
– sequence: 2
  givenname: Wenshan
  surname: Zhao
  fullname: Zhao, Wenshan
  email: wshzhao@bjtu.edu.cn
  organization: Beijing Jiaotong University,School of Electronic and Information Engineering,Beijing,China,100044
BookMark eNo10L1OwzAUhmGDQKKU3gGDJzaXYzvxzxiFUCoVkCBirU4cuxi1DkpSod49FT_TNzzSN7yX5Cx1yRNyw2HOOdjbZVlWrMb4hUkpY_hcgMiPJMBwMCdkZrU1UvLc6IzLUzIRuc6ZESa7ILNh-AAAyS0AtxPy-uKH2O5xy6r0jsn5lr4VFVsUTzR0Pa2qBb3DEWmx3-x8GnGMXaIx0cduPPJyhxvfH2i5xWGIIbofvyLnAbeDn_3tlNT3VV0-sNXzYlkWKxatHFlQqBWXaNrMCYsNCuWCAB1QYuZbJzw6lLo1ThgQymOumwabNohccetATsn172303q8_-7jD_rD-zyC_AcFZVio
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCE-Taiwan66881.2025.11208108
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798331587413
EISSN 2575-8284
EndPage 604
ExternalDocumentID 11208108
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-f6a7613a8d4c29aba26cf207fa3a4edc2eaca37d8c28026ea57bbabdf25619c03
IEDL.DBID RIE
IngestDate Wed Nov 05 07:14:43 EST 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-f6a7613a8d4c29aba26cf207fa3a4edc2eaca37d8c28026ea57bbabdf25619c03
PageCount 2
ParticipantIDs ieee_primary_11208108
PublicationCentury 2000
PublicationDate 2025-July-16
PublicationDateYYYYMMDD 2025-07-16
PublicationDate_xml – month: 07
  year: 2025
  text: 2025-July-16
  day: 16
PublicationDecade 2020
PublicationTitle IEEE International Conference on Consumer Electronics-China (Online)
PublicationTitleAbbrev ICCE-Taiwan
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003190019
Score 1.915274
Snippet Motor imagery is a widely studied paradigm in Brain-Computer Interfaces (BCIs) systems, where electroencephalography (EEG) signals are used to decode brain...
SourceID ieee
SourceType Publisher
StartPage 603
SubjectTerms Accuracy
Autoencoders
Brain modeling
Brain-computer interfaces
Data augmentation
Data models
Domain Generalization
Electroencephalography
Image reconstruction
Motor Imagery
Motors
Residual Modeling
Training data
Title Residual-Enhanced VAE-GAN for EEG Data Augmentation in Motor Imagery Classification
URI https://ieeexplore.ieee.org/document/11208108
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwGLSgQggWXkXlKQ-IzX04ie2MVUlLB6oKKtStchwbMtRFbQri3_PZTQsMDGxRIkWRbeXuPvu-Q-gmogZUh1YExEVAwihOScqoIAB2XJnQBJQrHzbBBwMxHsfD0qzuvTBaa3_4TNfdpd_Lz2Zq6UplDeAGgGDO2rvNOVuZtTYFFVhLjq_sotuyj2aj3-kkZCTzD2kZE8KpQRrV1y_5Fafi0aR78M_vOETVb18eHm4Q5whtaXuM9n-0FDxBT4964f1VJLGvfncfP7cT0msPMNBTnCQ9fCcLidvLl2lpO7I4t_hhBuIb96eupcUn9lGZ7hCRf15Fo24y6tyTMjiB5HFQEMMkB5SWIgsVjWUqKVOGNrmRgQx1pij8bGXAM6GoAAmmZcTTVKaZAfrTilUzOEUVO7O6hnAM_CrVrAk0xoRchgLog45cPkcsXNuaM1R1wzN5W7XGmKxH5vyP-xdoz02CK4622CWqFPOlvkI76r3IF_NrP6FfoXyfkg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwFHxCBbFc2IrY8QFxcxdnsXOsSrqINqogQr1VjmNDDk1Rm4L4e2wTChw4cIsSKYpsKzPz7HkDcO0RpVWHFFiLCwe7XpDgxCcMa7CjQrnKIVTYsAkaRWw8DkalWd16YaSU9vCZrJlLu5efzsTSlMrqmhtoBDPW3nUTnVXatVYlFb2aDGPZhJuyk2a9326HOObZG899nzGjB4lX-3rNr0AViyed3X9-yR5Uv515aLTCnH1Yk_kB7PxoKngID_dyYR1WOMyf7f4-emyFuNuKkCaoKAy76JYXHLWWT9PSeJSjLEfDmZbfqD81TS3ekQ3LNMeI7PMqxJ0wbvdwGZ2As8ApsPI51TjNWeoKEvCEE18o0qCKO9yVqSD6d8sdmjJBmBZhkns0SXiSKk2AmoFoOEdQyWe5PAYUaIaVSL-hiYxyKXeZJhDSMwkdATONa06gaoZn8vLZHGPyNTKnf9y_gq1ePBxMBv3o7gy2zYSYUmnTP4dKMV_KC9gQr0W2mF_ayf0AIqGi2w
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+Consumer+Electronics-China+%28Online%29&rft.atitle=Residual-Enhanced+VAE-GAN+for+EEG+Data+Augmentation+in+Motor+Imagery+Classification&rft.au=Tang%2C+Haiyuan&rft.au=Zhao%2C+Wenshan&rft.date=2025-07-16&rft.pub=IEEE&rft.eissn=2575-8284&rft.spage=603&rft.epage=604&rft_id=info:doi/10.1109%2FICCE-Taiwan66881.2025.11208108&rft.externalDocID=11208108