Using Autoencoders to Denoise Cross-Session Non-Stationarity in EEG-Based Motor-Imagery Brain-Computer Interfaces

A major problem in brain-computer interfaces (BCIs) relates to the non-stationarity of brain signals. Consequently, the performance of a classification algorithm trained for an individual subject on a certain day deteriorates during the following days. The traditional approach is to recalibrate the...

Full description

Saved in:
Bibliographic Details
Published in:2022 IEEE 16th International Scientific Conference on Informatics (Informatics) pp. 24 - 29
Main Authors: Almagor, Ophir, Avin, Ofer, Rosipal, Roman, Shriki, Oren
Format: Conference Proceeding
Language:English
Published: IEEE 23.11.2022
Subjects:
autoencoders
brain-computer interface
Brain-computer interfaces
Classification algorithms
Convolutional neural networks
Decoding
deep learning
electroencephalogram
Electroencephalography
Limiting
motor-imagery
non-stationarity
Recording
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract A major problem in brain-computer interfaces (BCIs) relates to the non-stationarity of brain signals. Consequently, the performance of a classification algorithm trained for an individual subject on a certain day deteriorates during the following days. The traditional approach is to recalibrate the algorithm every session, limiting the wide use of BCIs. Here, we use an autoencoder convolutional neural network to identify a low dimensional representation of the EEG signals from the first day (or days) and show that this allows for stable decoding performance on the following days without resorting to recalibration. Furthermore, we demonstrate that the residual signals, namely the difference between the original and reconstructed EEG, can be used to accurately discriminate among different recording sessions. In line with that, the reconstructed EEG cannot be used to discriminate among recording sessions. This implies that the reconstructed EEG reflects an invariant representation of the subject's intent, whereas the residual signals reflect a non-stationary component, which differs from one session to another. The findings are demonstrated through two different datasets.
AbstractList A major problem in brain-computer interfaces (BCIs) relates to the non-stationarity of brain signals. Consequently, the performance of a classification algorithm trained for an individual subject on a certain day deteriorates during the following days. The traditional approach is to recalibrate the algorithm every session, limiting the wide use of BCIs. Here, we use an autoencoder convolutional neural network to identify a low dimensional representation of the EEG signals from the first day (or days) and show that this allows for stable decoding performance on the following days without resorting to recalibration. Furthermore, we demonstrate that the residual signals, namely the difference between the original and reconstructed EEG, can be used to accurately discriminate among different recording sessions. In line with that, the reconstructed EEG cannot be used to discriminate among recording sessions. This implies that the reconstructed EEG reflects an invariant representation of the subject's intent, whereas the residual signals reflect a non-stationary component, which differs from one session to another. The findings are demonstrated through two different datasets.
Author Rosipal, Roman
Almagor, Ophir
Shriki, Oren
Avin, Ofer
Author_xml – sequence: 1
  givenname: Ophir
  surname: Almagor
  fullname: Almagor, Ophir
  email: ophiralm@post.bgu.ac.il
  organization: Ben-Gurion University of the Negev,Dept. of Cognitive and Brain Sciences,Beersheba,Israel
– sequence: 2
  givenname: Ofer
  surname: Avin
  fullname: Avin, Ofer
  email: avino@post.bgu.ac.il
  organization: Ben-Gurion University of the Negev,Dept. of Cognitive and Brain Sciences,Beersheba,Israel
– sequence: 3
  givenname: Roman
  surname: Rosipal
  fullname: Rosipal, Roman
  email: roman.rosipal@savba.sk
  organization: Institute of Measurement Science,Slovak Academy of Sciences,Bratislava,Slovakia
– sequence: 4
  givenname: Oren
  surname: Shriki
  fullname: Shriki, Oren
  email: shrikio@bgu.ac.il
  organization: Ben-Gurion University of the Negev,Dept. of Cognitive and Brain Sciences and Dept. of Computer Science,Beersheba,Israel
BookMark eNo1kL1OwzAURo0EA5S-AYMnNhf_pIkztiGUSAWG0rm6jW8qS8S32O7Qt6cSsHxnONIZvjt2HSggY49KzpSS9VMXBoojZN-neVXrcqal1jMlpTWFLa_YtK5qa-bSKGmK4pZ9b5MPB744ZcLQk8OYeCb-jIF8Qt5ESklsMCVPgb9TEJt8iVOA6POZ-8DbdiWWkNDxN8oURTfCAeOZLyP4IBoaj6eMkXfhsgP0mO7ZzQBfCad_nLDtS_vZvIr1x6prFmvhlaqzQCkdWDPUtqysBqVdhaWFvauslcYURvdFue8BlZ1bo0pbXfxgnUalnITCTNjDb9cj4u4Y_QjxvPt_wvwADRFciA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/Informatics57926.2022.10083486
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350310344
EndPage 29
ExternalDocumentID 10083486
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i119t-e00da83f986782a12d7e68abd788033432c46bcae1858316877e6f8d2e11d0a43
IEDL.DBID RIE
IngestDate Thu Jan 18 11:14:31 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-e00da83f986782a12d7e68abd788033432c46bcae1858316877e6f8d2e11d0a43
PageCount 6
ParticipantIDs ieee_primary_10083486
PublicationCentury 2000
PublicationDate 2022-Nov.-23
PublicationDateYYYYMMDD 2022-11-23
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-Nov.-23
  day: 23
PublicationDecade 2020
PublicationTitle 2022 IEEE 16th International Scientific Conference on Informatics (Informatics)
PublicationTitleAbbrev INFORMATICS
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8140885
Snippet A major problem in brain-computer interfaces (BCIs) relates to the non-stationarity of brain signals. Consequently, the performance of a classification...
SourceID ieee
SourceType Publisher
StartPage 24
SubjectTerms autoencoders
brain-computer interface
Brain-computer interfaces
Classification algorithms
Convolutional neural networks
Decoding
deep learning
electroencephalogram
Electroencephalography
Limiting
motor-imagery
non-stationarity
Recording
Title Using Autoencoders to Denoise Cross-Session Non-Stationarity in EEG-Based Motor-Imagery Brain-Computer Interfaces
URI https://ieeexplore.ieee.org/document/10083486
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFA22iLhSseKbLMRd2jymk2Rpa6uClkIVuiuZSQKzcEbbqeDfOzczVVy4cBcSQuBmcbiPcw5CV0IniaUxJUzYhESeOmJ0lBIvuDRUc69tEHF9lJOJms_1tCGrBy6Mcy4Mn7kuLEMv3xbpGkplPRCiEZGKW6glpazJWjvoutHN7DUEHpA37kvNYQCB8-7m0i_7lIAe471_vruPOj88PDz9RpgDtOXyQ_Qeuvz4Zl0WIEIJg8i4LPCty4ts5fAQYI_MarkNPClyMqu77QZs6nCW49Hojgwq8LL4qagybvLwCjoWn3gAbhFkY_OAQ63Qw8RWB72MR8_De9IYJ5CMMV0SR6k1SnitKijihnErXaxMYqt8lwqgkqZRnKTGVWCtwLlKVudeWe4Ys9RE4gi18yJ3xwjH1gN3NZJC8SjtJ4ZZz2QcQRplmEpOUAfitXirtTEWm1Cd_rF_hnbhV4DNx8U5apfLtbtA2-lHma2Wl-FHvwBBWqSx
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8IwGG4UjXpSI8ZvezDeCusHW3sUBCECIQETbqRbu2QHN4Vh4r93bzc0Hjx4a9o0Td4enrwfz_MgdMdVGBrP9wjlJiQi9izRSkQk5izQnmKxMk7EdRiMx3I-V5OKrO64MNZaN3xmG7B0vXyTRWsolTVBiIYL6W-jnZYQjJZ0rT10XylnNisKDwgctwLFYASBscbm2i8DFYcfvcN_vnyE6j9MPDz5xphjtGXTE_Tu-vz4YZ1nIEMJo8g4z_CjTbNkZXEHgI9MS8ENPM5SMi377RqM6nCS4m73ibQL-DJ4lBU5Nxm8gpLFJ26DXwTZGD1gVy2MYWarjl563VmnTyrrBJJQqnJiPc9oyWMlCzBimjITWF_q0BQZr8eBTBoJP4y0LeBagndVUJzH0jBLqfG04KeolmapPUPYNzGwV0XAJRNRK9TUxDTwBSRSmsrwHNUhXou3Uh1jsQnVxR_7t2i_PxsNF8PB-PkSHcAPAbeP8StUy5dre412o488WS1v3O9-Af5Sp_g
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=2022+IEEE+16th+International+Scientific+Conference+on+Informatics+%28Informatics%29&rft.atitle=Using+Autoencoders+to+Denoise+Cross-Session+Non-Stationarity+in+EEG-Based+Motor-Imagery+Brain-Computer+Interfaces&rft.au=Almagor%2C+Ophir&rft.au=Avin%2C+Ofer&rft.au=Rosipal%2C+Roman&rft.au=Shriki%2C+Oren&rft.date=2022-11-23&rft.pub=IEEE&rft.spage=24&rft.epage=29&rft_id=info:doi/10.1109%2FInformatics57926.2022.10083486&rft.externalDocID=10083486