Dataset Refinement for Improving the Generalization Ability of the EEG Decoding Model

Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent research has focused on decoding human intentions from EEG si...

Full description

Saved in:
Bibliographic Details
Published in:The ... International Winter Conference on Brain-Computer Interface pp. 1 - 4
Main Authors: Kim, Sung-Jin, Lee, Dae-Hyeok, Han, Hyeon-Taek
Format: Conference Proceeding
Language:English
Published: IEEE 24.02.2025
Subjects:
Brain modeling
Brain-computer interfaces
dataset refinement
Decoding
Deep learning
electroencephalogram
Electroencephalography
motor imagery
Motors
Neuroimaging
Noise
Noise measurement
Training
ISSN:2572-7672
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent research has focused on decoding human intentions from EEG signals utilizing deep learning methods. However, since EEG signals are highly susceptible to noise during acquisition, there is a high possibility of the existence of noisy data in the dataset. Although pioneer studies have generally assumed that the dataset is well-curated, this assumption is not always met in the EEG dataset. In this paper, we addressed this issue by designing a dataset refinement algorithm that can eliminate noisy data based on metrics evaluating data influence during the training process. We applied the proposed algorithm to two motor imagery EEG public datasets and three different models to perform dataset refinement. The results indicated that retraining the model with the refined dataset consistently led to better generalization performance compared to using the original dataset. Hence, we demonstrated that removing noisy data from the training dataset alone can effectively improve the generalization performance of deep learning models in the EEG domain.
AbstractList Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience, making it an effective tool for understanding human intentions. Therefore, recent research has focused on decoding human intentions from EEG signals utilizing deep learning methods. However, since EEG signals are highly susceptible to noise during acquisition, there is a high possibility of the existence of noisy data in the dataset. Although pioneer studies have generally assumed that the dataset is well-curated, this assumption is not always met in the EEG dataset. In this paper, we addressed this issue by designing a dataset refinement algorithm that can eliminate noisy data based on metrics evaluating data influence during the training process. We applied the proposed algorithm to two motor imagery EEG public datasets and three different models to perform dataset refinement. The results indicated that retraining the model with the refined dataset consistently led to better generalization performance compared to using the original dataset. Hence, we demonstrated that removing noisy data from the training dataset alone can effectively improve the generalization performance of deep learning models in the EEG domain.
Author Lee, Dae-Hyeok
Kim, Sung-Jin
Han, Hyeon-Taek
Author_xml – sequence: 1
  givenname: Sung-Jin
  surname: Kim
  fullname: Kim, Sung-Jin
  email: s_j_kim@korea.ac.kr
  organization: Korea University,Dept. of Artificial Intelligence,Seoul,Republic of Korea
– sequence: 2
  givenname: Dae-Hyeok
  surname: Lee
  fullname: Lee, Dae-Hyeok
  email: lee_dh@korea.ac.kr
  organization: Korea University,Dept. of Brain and Cognitive Engineering,Seoul,Republic of Korea
– sequence: 3
  givenname: Hyeon-Taek
  surname: Han
  fullname: Han, Hyeon-Taek
  email: ht_han@korea.ac.kr
  organization: Korea University,Dept. of Artificial Intelligence,Seoul,Republic of Korea
BookMark eNo1kM1KAzEUhaMoWGvfQCQvMDXJTSbJsra1DlQEseuSmbnRyDQpM0GoT19_VwfOd_gW55KcxRSRkBvOppwze3s3r0rFjJkKJtT0qwEOpTwhE6utAeBKcCvsKRkJpUWhSy0uyGQY3hljwI21TI7IZuGyGzDTZ_Qh4g5jpj71tNrt-_QR4ivNb0hXGLF3Xfh0OaRIZ3XoQj7Q5H_ocrmiC2xS-z1_TC12V-Tcu27AyV-OyeZ--TJ_KNZPq2o-WxeBa5OL1jpZgm5qBMWUqaWz4KBBVioQnHMra48KTQMtaMYah954b72SQknpWxiT619vQMTtvg871x-2_0_AEQ5MVCs
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BCI65088.2025.10931364
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Anatomy & Physiology
EISBN 9798331521929
EISSN 2572-7672
EndPage 4
ExternalDocumentID 10931364
Genre orig-research
GrantInformation_xml – fundername: Defense Acquisition Program Administration (DAPA)
  grantid: 912911601
  funderid: 10.13039/501100003626
– fundername: Agency For Defense Development (ADD)
  funderid: 10.13039/501100005073
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-i178t-d9a4637cbe35058b4a93a3ce0653211194bfe5e8c3d3700caef8ff9f542544fd3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001471781800015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Apr 02 05:44:44 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i178t-d9a4637cbe35058b4a93a3ce0653211194bfe5e8c3d3700caef8ff9f542544fd3
PageCount 4
ParticipantIDs ieee_primary_10931364
PublicationCentury 2000
PublicationDate 2025-Feb.-24
PublicationDateYYYYMMDD 2025-02-24
PublicationDate_xml – month: 02
  year: 2025
  text: 2025-Feb.-24
  day: 24
PublicationDecade 2020
PublicationTitle The ... International Winter Conference on Brain-Computer Interface
PublicationTitleAbbrev BCI
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189904
Score 1.9001777
Snippet Electroencephalography (EEG) is a generally used neuroimaging approach in brain-computer interfaces due to its non-invasive characteristics and convenience,...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Brain modeling
Brain-computer interfaces
dataset refinement
Decoding
Deep learning
electroencephalogram
Electroencephalography
motor imagery
Motors
Neuroimaging
Noise
Noise measurement
Training
Title Dataset Refinement for Improving the Generalization Ability of the EEG Decoding Model
URI https://ieeexplore.ieee.org/document/10931364
WOSCitedRecordID wos001471781800015&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/eLvHCXMwlV1LT8JAEN4I8eDJBxjf2YPxVqDd7e72iICPxBBixHAj293ZhESLwWLCv3d2KRgPHrw1fW0y03a-bzrfDCHXKk-17Qj0AAgecQEsUqlLIoevkuAizm2Yn_L6JIdDNZlko0qsHrQwABCKz6DlN8O_fDs3S58qa_vWRzETvEZqUsq1WGubUMGHE7-svFIB46nt295jwB_IApO0tbn41xiVEEXu9v-5_gFp_ujx6GgbaQ7JDhRHpNEtkDC_r-gNDWWcIT_eIOO-LjEylfQZHCJIf0eKwJRuswcUIR-tuk1XIkzaDSWyKzp34ehgcE_7yEv9atRPS3trkvHd4KX3EFWzE6JZLFUZ2UxzwaTJgSHGUTnXGdPMgG9Fi5wvznjuIAVlmGWy0zEanHIucyn3PcucZcekXswLOCE007FVCYDU2nGr0cwGMZ7C2A7IXRJ-SpreVNOPdXuM6cZKZ3_sPyd73iFBF84vSL1cLOGS7Jqvcva5uApO_QYf8aJO
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEN4omujJBxjf7sF4K9Ludrs9Ig8hIiEGDDey7c4mJFoMFhP-vbNLwXjw4K3pOzNt5_um880QciuTUOmaQA-A4B4XwDwZmsAz-CoJLvxEu_kpr72o35fjcTwoxOpOCwMArvgMqnbR_cvXs3RhU2X3tvWRzwTfJjsh54G_kmttUir4eOK3lRc6YNz5_qHRdQgEeWAQVteH_xqk4uJI--Cfd3BIKj-KPDrYxJojsgXZMSnXM6TM70t6R10hp8uQl8moqXKMTTl9AYMY0p6RIjSlm_wBRdBHi37ThQyT1l2R7JLOjNvaaj3SJjJTezVq56W9Vcio3Ro2Ol4xPcGb-pHMPR0rLliUJsAQ5ciEq5gploJtRousz495YiAEmTLNolotVWCkMbEJue1aZjQ7IaVslsEpobHytQwAIqUM1wrNnCLKkxjdAdlLwM9IxZpq8rFqkDFZW-n8j_U3ZK8zfO5Net3-0wXZt85xKnF-SUr5fAFXZDf9yqef82vn4G_A9qWV
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=The+...+International+Winter+Conference+on+Brain-Computer+Interface&rft.atitle=Dataset+Refinement+for+Improving+the+Generalization+Ability+of+the+EEG+Decoding+Model&rft.au=Kim%2C+Sung-Jin&rft.au=Lee%2C+Dae-Hyeok&rft.au=Han%2C+Hyeon-Taek&rft.date=2025-02-24&rft.pub=IEEE&rft.eissn=2572-7672&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FBCI65088.2025.10931364&rft.externalDocID=10931364