Improving Cross-Subject Emotion Recognition Performance with an Encoder-Decoder Structure

Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performan...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Ročník 2024; s. 1 - 4
Hlavní autoři: Cui, Haowei, Shi, Hanwen, Lu, Bao-Liang, Zheng, Wei-Long
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.07.2024
Témata:
ISSN:2694-0604, 2694-0604
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performance due to the differences in the EEG distributions of different subjects, domain adaptation algorithms have been used to transfer the knowledge from source to target domains, and have achieved good performance in the task of cross-subject emotion recognition. However, most domain adaptation methods do not take into account the possible correspondence between the samples in the source and target domains. Therefore, we adopt an encoder-decoder architecture, the EEG converter, which utilizes the time alignment condition between the source and target domains during training. In the EEG converter structure, the encoder consists of a series of convolutional layers and max pooling layers, and the decoder consists of a series of upsampling layers and convolutional layers. We use the EEG converter to transfer the differential entropy features of EEG signals, from one subject to another, on datasets SEED, SEED-IV, and SEEDV. The results show that the transfer effect of the EEG converter significantly improves the performance of emotion recognition and outperforms existing domain adaptation algorithms.
AbstractList Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performance due to the differences in the EEG distributions of different subjects, domain adaptation algorithms have been used to transfer the knowledge from source to target domains, and have achieved good performance in the task of cross-subject emotion recognition. However, most domain adaptation methods do not take into account the possible correspondence between the samples in the source and target domains. Therefore, we adopt an encoder-decoder architecture, the EEG converter, which utilizes the time alignment condition between the source and target domains during training. In the EEG converter structure, the encoder consists of a series of convolutional layers and max pooling layers, and the decoder consists of a series of upsampling layers and convolutional layers. We use the EEG converter to transfer the differential entropy features of EEG signals, from one subject to another, on datasets SEED, SEED-IV, and SEEDV. The results show that the transfer effect of the EEG converter significantly improves the performance of emotion recognition and outperforms existing domain adaptation algorithms.
Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performance due to the differences in the EEG distributions of different subjects, domain adaptation algorithms have been used to transfer the knowledge from source to target domains, and have achieved good performance in the task of cross-subject emotion recognition. However, most domain adaptation methods do not take into account the possible correspondence between the samples in the source and target domains. Therefore, we adopt an encoder-decoder architecture, the EEG converter, which utilizes the time alignment condition between the source and target domains during training. In the EEG converter structure, the encoder consists of a series of convolutional layers and max pooling layers, and the decoder consists of a series of upsampling layers and convolutional layers. We use the EEG converter to transfer the differential entropy features of EEG signals, from one subject to another, on datasets SEED, SEED-IV, and SEEDV. The results show that the transfer effect of the EEG converter significantly improves the performance of emotion recognition and outperforms existing domain adaptation algorithms.Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performance due to the differences in the EEG distributions of different subjects, domain adaptation algorithms have been used to transfer the knowledge from source to target domains, and have achieved good performance in the task of cross-subject emotion recognition. However, most domain adaptation methods do not take into account the possible correspondence between the samples in the source and target domains. Therefore, we adopt an encoder-decoder architecture, the EEG converter, which utilizes the time alignment condition between the source and target domains during training. In the EEG converter structure, the encoder consists of a series of convolutional layers and max pooling layers, and the decoder consists of a series of upsampling layers and convolutional layers. We use the EEG converter to transfer the differential entropy features of EEG signals, from one subject to another, on datasets SEED, SEED-IV, and SEEDV. The results show that the transfer effect of the EEG converter significantly improves the performance of emotion recognition and outperforms existing domain adaptation algorithms.
Author Cui, Haowei
Zheng, Wei-Long
Shi, Hanwen
Lu, Bao-Liang
Author_xml – sequence: 1
  givenname: Haowei
  surname: Cui
  fullname: Cui, Haowei
  email: qwertyui@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,School of Life Sciences and Biotechnology,Shanghai,China
– sequence: 2
  givenname: Hanwen
  surname: Shi
  fullname: Shi, Hanwen
  email: shihanwen@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 3
  givenname: Bao-Liang
  surname: Lu
  fullname: Lu, Bao-Liang
  email: bllu@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
– sequence: 4
  givenname: Wei-Long
  surname: Zheng
  fullname: Zheng, Wei-Long
  email: weilong@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40039562$$D View this record in MEDLINE/PubMed
BookMark eNpNkMtOwzAQRQ0qglL6BwiyZJMyjp04XkIJUKkIRGHBKoqdSTFq7OIkIP6eqg_E6l5pjq4055j0rLNIyDmFEaUgL7OH63HMKKSjCCI-oiDSCBjbI0MpZMpiYIJyKfdJP0okDyEB3vvXj8iwaYyCmMU8lhE7JEccgMk4ifrkbVIvvfsydh6MvWuacNapD9RtkNWuNc4Gz6jd3Jp1f0JfOV8XVmPwbdr3oLBBZrUr0Yc3uM5g1vpOt53HE3JQFYsGh9sckNfb7GV8H04f7ybjq2loKBdtyCuZCEV5QstY8bhiWpYJL6oU0gQZV1xUyBVKWqYi4qmAKoFCM61oxEoFFRuQi83u6o_PDps2r02jcbEoLLquyRkVHKRcmVuhZ1u0UzWW-dKbuvA_-U7HCjjdAAYR_8474ewXHtFyEw
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1109/EMBC53108.2024.10782033
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
EISBN 9798350371499
EISSN 2694-0604
EndPage 4
ExternalDocumentID 40039562
10782033
Genre orig-research
Journal Article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
– fundername: Shanghai Jiao Tong University
  funderid: 10.13039/501100004921
GroupedDBID 6IE
6IH
6IL
6IN
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-i147t-4f967b1461d5b45f3c9d64af8086e34b47fe4be91d8724870f60ac3cb123db0f3
IEDL.DBID RIE
ISSN 2694-0604
IngestDate Sun Nov 09 11:48:30 EST 2025
Mon May 12 02:38:35 EDT 2025
Wed Aug 27 02:32:15 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i147t-4f967b1461d5b45f3c9d64af8086e34b47fe4be91d8724870f60ac3cb123db0f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 40039562
PQID 3174099024
PQPubID 23479
PageCount 4
ParticipantIDs ieee_primary_10782033
proquest_miscellaneous_3174099024
pubmed_primary_40039562
PublicationCentury 2000
PublicationDate 2024-Jul
PublicationDateYYYYMMDD 2024-07-01
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-Jul
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
PublicationTitleAbbrev EMBC
PublicationTitleAlternate Annu Int Conf IEEE Eng Med Biol Soc
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib053545923
ssib042469959
ssib061542107
Score 2.2608778
Snippet Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of...
SourceID proquest
pubmed
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 1
SubjectTerms Adaptation models
Algorithms
Brain modeling
Computational modeling
Convolution
Degradation
Electroencephalography
Electroencephalography - methods
Emotion recognition
Emotions - physiology
Engineering in medicine and biology
Entropy
Humans
Signal Processing, Computer-Assisted
Training
Title Improving Cross-Subject Emotion Recognition Performance with an Encoder-Decoder Structure
URI https://ieeexplore.ieee.org/document/10782033
https://www.ncbi.nlm.nih.gov/pubmed/40039562
https://www.proquest.com/docview/3174099024
Volume 2024
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcAEiALlURmJ1SWJL3G8UlKxtIp4SGWq7NiWuqSoD34_5zxalg4siRUplnW-5D7f3XdHyCP4qKZKQiZjKBiYRDEpbMgMh0IIFWsRqarZhJhO09lM5g1ZveLCWGur5DM79MMqlm-Wxda7yvAL99XdOO-QjhCiJmu1ygMRHvT-FEqJOWIDRC9NThcu6SmbPI9Q5QKf0RXBsJ2t6atyGGJWpmZ8-s9FnpHenrRH8505OidHtrwgXzunAR15e8jwR-E9LzSr2_fQtzaBCMf5nkRAvX-WqpJmpSe9r9iLre70vao3u13ZHvkcZx-jV9Z0U2CLEMSGgZOJ0L6Nt4k1xI4X0iSgXIqHGstBg3AWtJWhSUWEx5jAJYEqeKHRthkdOH5JuuWytNeEBpGW-ETJJHUQi0KFPDTW4AYg2Eid7ZOel8v8uy6YMW9F0icPrYjnqMU-NKFKu9yu54hiwIfoIuiTq1r2u7fB84cRpt0cmPWWnPj9rHNo70gX5WDvyXHxs1msVwNUlVmK12k-GVQK8wv0Kr0C
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5gIMEJEAPGM0hcM9rGbZorY9MQ2zTBkMapSptU2qVDe_D7cdJ248KBU6NKiSLHrb_Y_mxCHsBGNVXkMxlCxkBHiklhfKY5ZEKoMBWBcs0mxGgUT6dyXJHVHRfGGOOSz0zbDl0sX8-ztXWV4Rduq7txvkv2QoDAL-latfpAgFe9X6VSQo7oAPFLldWFm3rsDp86qHSezekKoF2vV3VW-RtkOmPTO_rnNo9Jc0vbo-ONQTohO6Y4JZ8btwHtWIvI8FdhfS-0WzbwoW91ChGOx1saAbUeWqoK2i0s7X3Bno170ndXcXa9ME3y0etOOn1W9VNgMx_EikEuI5HaRt46TCHMeSZ1BCqP8VpjOKQgcgOpkb6ORYAXGS-PPJXxLEXrplMv52ekUcwLc0GoF6QS3ygZxTmEIlM-97XReAAIN-LctEjTyiX5KktmJLVIWuS-FnGCemyDE6ow8_UyQRwDNkgXQIucl7LfzAbLIEagdvnHqnfkoD8ZDpLBy-j1ihzasy0zaq9JA2Vibsh-9r2aLRe3TmF-AAtvvlU
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=2024+46th+Annual+International+Conference+of+the+IEEE+Engineering+in+Medicine+and+Biology+Society+%28EMBC%29&rft.atitle=Improving+Cross-Subject+Emotion+Recognition+Performance+with+an+Encoder-Decoder+Structure&rft.au=Cui%2C+Haowei&rft.au=Shi%2C+Hanwen&rft.au=Lu%2C+Bao-Liang&rft.au=Zheng%2C+Wei-Long&rft.date=2024-07-01&rft.pub=IEEE&rft.eissn=2694-0604&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FEMBC53108.2024.10782033&rft.externalDocID=10782033
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2694-0604&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2694-0604&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2694-0604&client=summon