EEG-Transformer: Self-attention from Transformer Architecture for Decoding EEG of Imagined Speech

Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder structure following seq2seq without using RNN, but had better...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The ... International Winter Conference on Brain-Computer Interface s. 1 - 4
Hlavní autoři: Lee, Young-Eun, Lee, Seo-Hyun
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 21.02.2022
Témata:
ISSN:2572-7672
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder structure following seq2seq without using RNN, but had better performance than RNN. Herein, we investigate the decoding technique for electroencephalography (EEG) composed of self-attention module from transformer architecture during imagined speech and overt speech. We performed classification of nine subjects using convolutional neural network based on EEGNet that captures temporal-spectral-spatial features from EEG of imagined speech and overt speech. Furthermore, we applied the self-attention module to decoding EEG to improve the performance and lower the number of parameters. Our results demonstrate the possibility of decoding brain activities of imagined speech and overt speech using attention modules. Also, only single channel EEG or ear-EEG can be used to decode the imagined speech for practical BCIs.
AbstractList Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder structure following seq2seq without using RNN, but had better performance than RNN. Herein, we investigate the decoding technique for electroencephalography (EEG) composed of self-attention module from transformer architecture during imagined speech and overt speech. We performed classification of nine subjects using convolutional neural network based on EEGNet that captures temporal-spectral-spatial features from EEG of imagined speech and overt speech. Furthermore, we applied the self-attention module to decoding EEG to improve the performance and lower the number of parameters. Our results demonstrate the possibility of decoding brain activities of imagined speech and overt speech using attention modules. Also, only single channel EEG or ear-EEG can be used to decode the imagined speech for practical BCIs.
Author Lee, Young-Eun
Lee, Seo-Hyun
Author_xml – sequence: 1
  givenname: Young-Eun
  surname: Lee
  fullname: Lee, Young-Eun
  email: ye_lee@korea.ac.kr
  organization: Korea University,Dept. Brain and Cognitive Engineering,Seoul,Republic of Korea
– sequence: 2
  givenname: Seo-Hyun
  surname: Lee
  fullname: Lee, Seo-Hyun
  email: seohyunlee@korea.ac.kr
  organization: Korea University,Dept. Brain and Cognitive Engineering,Seoul,Republic of Korea
BookMark eNpNkM1Kw0AUhUdRsNY-gQjzAqn3zk8mcVdrrYGCi3ZfJpM77UgzKZO48O0N2IWrA4ePj8O5Zzexi8TYE8IcEcrn12WlpREwFyDEvDRSo1BXbFaaAvNcK5TSqGs2EdqIzORG3LFZ338BgMSiLEFNmF2t1tku2dj7LrWUXviWTj6zw0BxCF3kPnUt_wfwRXLHMJAbvhPxseNv5LomxAMfVbzzvGrtIURq-PZM5I4P7NbbU0-zS07Z7n21W35km891tVxssiBADpnHYtzUmNoUikBpXzuba4eovQZwJUpVW100StVotPMkhFcKGwdWj4ycssc_bSCi_TmF1qaf_eUT-QuQVFdq
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/BCI53720.2022.9735124
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
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/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Anatomy & Physiology
EISBN 9781665413374
1665413379
EISSN 2572-7672
EndPage 4
ExternalDocumentID 9735124
Genre orig-research
GrantInformation_xml – fundername: Interface
  funderid: 10.13039/100004712
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-i203t-f18189d7b784e045fbca65c115f500c9134ba58d44b175cfe22f441dc0a515f3
IEDL.DBID RIE
ISICitedReferencesCount 34
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000814683300048&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 02:47:41 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f18189d7b784e045fbca65c115f500c9134ba58d44b175cfe22f441dc0a515f3
PageCount 4
ParticipantIDs ieee_primary_9735124
PublicationCentury 2000
PublicationDate 2022-Feb.-21
PublicationDateYYYYMMDD 2022-02-21
PublicationDate_xml – month: 02
  year: 2022
  text: 2022-Feb.-21
  day: 21
PublicationDecade 2020
PublicationTitle The ... International Winter Conference on Brain-Computer Interface
PublicationTitleAbbrev BCI
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189904
Score 2.1133645
Snippet Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms attention module
brain-computer interface
Communication systems
Deep learning
Electroencephalography
Hardware
imagined speech
Speech recognition
Statistical analysis
transformer
Transformers
Title EEG-Transformer: Self-attention from Transformer Architecture for Decoding EEG of Imagined Speech
URI https://ieeexplore.ieee.org/document/9735124
WOSCitedRecordID wos000814683300048&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/eLvHCXMwlV3LTgIxFG2QuHDlA4zvdGFcWSgzHdpxhwjKhpDAgh3ptLeRRAaCYOLfe1tGxMSNu0mnM03apvfcx-kh5DYW0MxSaxk3DcVELDlTLtYsNs4kUmcG3wWxCdnvq_E4HZTI_ZYLAwCh-Axq_jHk8u3crH2orJ7KGO2T2CN7UsoNV2sbT8G9iQerKEg6DZ7WH9u9xGuwoBMYRbXi218iKsGGdA__N_oRqf6Q8ehga2aOSQnyE1Jp5egtzz7pHQ01nCE4XiG603lmo28sCssHOoQ3x_wdmqGqkXo2Cd3pQFs7iQSKbfQJ_VE_EMVf0bmjvZnXMQJLhwsA81olo25n1H5hhYgCm0Y8XjGHJlylVmZSCUD85jKjm4lBIOgSzo1PvGc6UVaIDJGEcRBFDiGSNVwj1HHxKSnn8xzOCAWEtklTSB8DETrRacatkhqk0NI6Yc9JxU_aZLG5JmNSzNfF382X5MCvS2CHN65IebVcwzXZNx-r6fvyJqztF0WXpbk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTgIxFG0QTXTlA4xvuzCuLMyjpTPuEEGISEiYBTvSaW8jiQwEwcS_ty0jYuLG3aTTmSZt03vu4_QgdBNSqKWxUsSTfkRoyD0S6VCQUGrJuEileefEJnivFw2Hcb-A7tZcGABwxWdQsY8ul6-mcmlDZdWYh8Y-0S20zSgN_BVbax1RMbvTHK00p-n4Xlx9aHSYVWExbmAQVPKvf8moOCvS2v_f-Aeo_EPHw_21oTlEBciOUKmeGX958olvsavidOHxEhLN5hNJvtEozO_xAN40sbdourpGbPkkeKMDrm-kErBpw4_GI7UDYfMrPNW4M7FKRqDwYAYgX8soaTWTRpvkMgpkHHjhgmhjxKNY8ZRHFAyC06kUNSYNFNTM86RNvaeCRYrS1GAJqSEItAFJSnrCgB0dHqNiNs3gBGEw4JbVKLdRECqYiFNPRVwAp4IrTdUpKtlJG81WF2WM8vk6-7v5Gu22k5fuqNvpPZ-jPbtGjivuX6DiYr6ES7QjPxbj9_mVW-cvEzCpAA
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=EEG-Transformer%3A+Self-attention+from+Transformer+Architecture+for+Decoding+EEG+of+Imagined+Speech&rft.au=Lee%2C+Young-Eun&rft.au=Lee%2C+Seo-Hyun&rft.date=2022-02-21&rft.pub=IEEE&rft.eissn=2572-7672&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FBCI53720.2022.9735124&rft.externalDocID=9735124