A coarse-to-fine adaptive spatial–temporal graph convolution network with residuals for motor imagery decoding from the same limb

•A novel coarse-to-fine classification approach is proposed to decode MI tasks of the same upper limb.•A adaptive spatial–temporal graph convolutional network with residuals approach is proposed to extract spatial–temporal features.•Various classification models are applied to different classificati...

Full description

Saved in:
Bibliographic Details
Published in:Biomedical signal processing and control Vol. 90; p. 105885
Main Authors: Zhu, Lei, Yuan, Jie, Huang, Aiai, Zhang, Jianhai
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.04.2024
Subjects:
ISSN:1746-8094, 1746-8108
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •A novel coarse-to-fine classification approach is proposed to decode MI tasks of the same upper limb.•A adaptive spatial–temporal graph convolutional network with residuals approach is proposed to extract spatial–temporal features.•Various classification models are applied to different classification stages, and each model is specifically designed according to the feature differences among categories.•The proposed approach obtains better results than classical approaches. In the field of Brain Computer Interface (BCI) technology, Motor Imagery (MI) plays an important role as a paradigm. One of the primary focuses of this research area lies in exploring the MI of various upper limbs. Decoding MI signals from distinct joints within the same limb poses more intricate challenges in comparison to decoding MI signals originating from different upper limbs. In order to explore more efficient decoding methods, we propose a novel coarse-to-fine classification approach to investigate categorical decoding across three tasks, namely ‘rest’, ‘hand’, and ‘elbow’. This approach consists of two classification stages performed from coarse to fine. In the coarse classification stage, in order to capture the features of both resting state and the moving state in the temporal domain, the EEGNet network with temporal domain convolution is used to extract temporal domain features and classify the original samples into categories of ‘rest’ and ‘move’ (‘hand’, ‘elbow’). In the fine classification stage, the samples of ‘move’ category are segmented by time to form a graph sequence. Then, an adaptive spatial–temporal graph convolutional network with residuals is utilized to extract both temporal and spatial domains’ features from the graph sequence. The proposed algorithm has been validated experimentally on the MI-2 dataset and compared with contemporary methods. Its classification performance is quantified by the average accuracy which achieves a value of 72.21%. Extensive experimental results indicate that the novel coarse-to-fine classification approach is superior to the single classification approach.
AbstractList •A novel coarse-to-fine classification approach is proposed to decode MI tasks of the same upper limb.•A adaptive spatial–temporal graph convolutional network with residuals approach is proposed to extract spatial–temporal features.•Various classification models are applied to different classification stages, and each model is specifically designed according to the feature differences among categories.•The proposed approach obtains better results than classical approaches. In the field of Brain Computer Interface (BCI) technology, Motor Imagery (MI) plays an important role as a paradigm. One of the primary focuses of this research area lies in exploring the MI of various upper limbs. Decoding MI signals from distinct joints within the same limb poses more intricate challenges in comparison to decoding MI signals originating from different upper limbs. In order to explore more efficient decoding methods, we propose a novel coarse-to-fine classification approach to investigate categorical decoding across three tasks, namely ‘rest’, ‘hand’, and ‘elbow’. This approach consists of two classification stages performed from coarse to fine. In the coarse classification stage, in order to capture the features of both resting state and the moving state in the temporal domain, the EEGNet network with temporal domain convolution is used to extract temporal domain features and classify the original samples into categories of ‘rest’ and ‘move’ (‘hand’, ‘elbow’). In the fine classification stage, the samples of ‘move’ category are segmented by time to form a graph sequence. Then, an adaptive spatial–temporal graph convolutional network with residuals is utilized to extract both temporal and spatial domains’ features from the graph sequence. The proposed algorithm has been validated experimentally on the MI-2 dataset and compared with contemporary methods. Its classification performance is quantified by the average accuracy which achieves a value of 72.21%. Extensive experimental results indicate that the novel coarse-to-fine classification approach is superior to the single classification approach.
ArticleNumber 105885
Author Yuan, Jie
Zhu, Lei
Huang, Aiai
Zhang, Jianhai
Author_xml – sequence: 1
  givenname: Lei
  surname: Zhu
  fullname: Zhu, Lei
  email: zhulei@hdu.edu.cn
  organization: School of Automation, Hangzhou Dianzi University, Hangzhou 310000, China
– sequence: 2
  givenname: Jie
  surname: Yuan
  fullname: Yuan, Jie
  organization: School of Automation, Hangzhou Dianzi University, Hangzhou 310000, China
– sequence: 3
  givenname: Aiai
  surname: Huang
  fullname: Huang, Aiai
  organization: School of Automation, Hangzhou Dianzi University, Hangzhou 310000, China
– sequence: 4
  givenname: Jianhai
  surname: Zhang
  fullname: Zhang, Jianhai
  organization: School of Computer Science, Hangzhou Dianzi University, Hangzhou 310000, China
BookMark eNp9kM1KAzEURoNUsK2-gKu8wNRkZpKZgptS_IOCG12HTHLTps4kQ5JWuhN8BN_QJ3FKdevm3suF8_FxJmjkvAOErimZUUL5zXbWxF7NcpIXw4PVNTtDY1qVPKspqUd_N5mXF2gS45aQsq5oOUafC6y8DBGy5DNjHWCpZZ_sHnDsZbKy_f74StD1PsgWr4PsNwPg9r7dJesddpDefXjD7zZtcIBo9U62ERsfcOfTMG0n1xAOWIPy2ro1NsF3OG2GfNkBbm3XXKJzM0Bw9bun6PX-7mX5mK2eH56Wi1WmckZTpnijoNJNngPXknOiaUkNKwswlEjCG1NoXjOQTBpWaWrmlaSEa1bqvGCaFVOUn3JV8DEGMKIPQ71wEJSIo0axFUeN4qhRnDQO0O0JgqHZ3kIQUVlwCrQNoJLQ3v6H_wBUqIIy
Cites_doi 10.1109/TNSRE.2019.2953121
10.1109/TNSRE.2016.2601240
10.1007/s11517-008-0345-8
10.1109/TBME.2013.2248153
10.1007/s40815-016-0259-9
10.5539/gjhs.v10n11p66
10.1109/TNSRE.2022.3154369
10.1371/journal.pone.0121896
10.1038/s41597-020-0535-2
10.1016/j.mayocp.2011.12.008
10.1109/TBME.2007.897815
10.1007/s12559-017-9533-x
10.1109/ICCE-Asia49877.2020.9276983
10.1609/aaai.v32i1.12328
10.1016/j.neucom.2017.09.030
10.1142/S1793351X16500045
10.1016/j.medengphy.2011.11.001
10.1109/TNSRE.2008.926694
10.1007/978-3-540-88906-9_42
10.1109/IMCCC.2015.156
10.1371/journal.pone.0182578
10.1371/journal.pone.0188293
10.1016/j.clinph.2007.04.019
10.1109/LSP.2021.3049683
10.1016/j.jneumeth.2003.10.009
10.1109/TNSRE.2017.2721116
10.1016/j.pmrj.2014.01.006
10.1088/1741-2552/aba7cd
10.1177/1550059414522229
10.1145/2816839.2816845
10.1371/journal.pone.0174161
10.1109/5.939829
10.1007/s10044-019-00860-w
10.1109/TAMD.2015.2431497
10.1109/TSMCC.2012.2226444
10.1088/1741-2552/aace8c
10.1002/hbm.23730
ContentType Journal Article
Copyright 2023 Elsevier Ltd
Copyright_xml – notice: 2023 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.bspc.2023.105885
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1746-8108
ExternalDocumentID 10_1016_j_bspc_2023_105885
S1746809423013186
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
UNMZH
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c251t-c6bce7db22e6da660d141f543ef10a06bf3d685ea5af57d1f97a106d54d235d53
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001152576000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1746-8094
IngestDate Sat Nov 29 07:02:12 EST 2025
Sat Feb 24 15:48:58 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Motor Imagery (MI)
Adaptive spatial–temporal graph convolutional network
Brain Computer Interface(BCI)
Coarse-to-fine classification approach
Different joints of the same limb
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c251t-c6bce7db22e6da660d141f543ef10a06bf3d685ea5af57d1f97a106d54d235d53
ParticipantIDs crossref_primary_10_1016_j_bspc_2023_105885
elsevier_sciencedirect_doi_10_1016_j_bspc_2023_105885
PublicationCentury 2000
PublicationDate April 2024
2024-04-00
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: April 2024
PublicationDecade 2020
PublicationTitle Biomedical signal processing and control
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Srivastava, Hinton, Krizhevsky (b0230) 2014; 15
Li, Zhang, He (b0125) 2018; 10
Frisoli, Loconsole, Leonardis (b0030) 2012; 42
Hao, Zhang, Ma (b0115) 2016; 10
Hou Y, Jia S, Lun X, et al. Deep feature mining via attention-based BiLSTM-GCN for human motor imagery recognition[J]. arXiv preprint arXiv:2005.00777, 2020.
Pfurtscheller, Neuper (b0025) 2001; 89
Delorme, Makeig (b0200) 2004; 134
Hsu, Lin, Chou (b0080) 2017; 19
Yong, Menon (b0090) 2015; 10
Chu, Zhao, Zou (b0110) 2020; 17
Supratak, Dong, Wu (b0135) 2017; 25
Yahya-Zoubir B, Bentlemsan M, Zemouri E T T, et al. Adaptive time window for EEG-based motor imagery classification[C]//Proceedings of the International Conference on Intelligent Information Processing, Security and Advanced Communication. 2015: 1-6.
Wang Y, Liu X, Zhang Y, et al. Driving fatigue detection based on EEG signal[C]//2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC). IEEE, 2015: 715-718.
Gómez-Herrero, De Clercq, Anwar (b0205) 2006; 2006
Zhu, Xu, Yu (b0215) 2021, 2021
K. Choi A. Cichocki Control of a wheelchair by motor imagery in real time[C]//Intelligent Data Engineering and Automated Learning–IDEAL 2008: 9th International Conference Daejeon, South Korea, November 2-5, 2008 Proceedings 9. Springer Berlin Heidelberg, 2008: 330-337.
S. Yan, Y. Xiong, D. Lin. Spatial temporal graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the AAAI conference on artificial intelligence. 2018, 32(1).
Sun, Zhang, Wu (b0185) 2021; 28
Vučković, Sepulveda (b0155) 2012; 34
Zhang, Yong, Menon (b0075) 2017; 12
Schirrmeister, Springenberg, Fiederer (b0145) 2017; 38
Shih, Krusienski, Wolpaw (b0005) 2012; 87
Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
Robinson, Vinod, Ang (b0050) 2013; 60
Ma, Qiu, He (b0095) 2020; 7
Hwang, Hong, Son (b0065) 2020; 23
Jia, Lin, Wang (b0210) 2021
Lawhern, Solon, Waytowich (b0190) 2018; 15
Jia, Lin, Wang (b0195) 2020
Zheng, Lu (b0120) 2015; 7
Muller-Putz, Pfurtscheller (b0015) 2007; 55
Kwak Y, Song W J, Kim S E. Graph neural network with multilevel feature fusion for EEG based brain-computer interface[C]//2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia). IEEE, 2020: 1-3.
Dunsky, Dickstein (b0045) 2018; 10
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//International conference on machine learning. pmlr, 2015: 448-456.
Polich (b0020) 2007; 118
Ang, Chua, Phua (b0040) 2015; 46
Lu, Li, Ren (b0150) 2016; 25
Teo, Chew (b0010) 2014; 6
Thodoroff, Pineau, Lim (b0140) 2016
Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
Tavakolan, Frehlick, Yong (b0070) 2017; 12
Zheng, Zhu, Qin (b0085) 2018; 275
Ofner, Schwarz, Pereira (b0105) 2017; 12
Ma, Qiu, He (b0165) 2022; 30
Ma, Qiu, Wei (b0160) 2019; 28
Herman, Prasad, McGinnity (b0060) 2008; 16
Van der Maaten, Hinton (b0240) 2008; 9
Vuckovic, Sepulveda (b0100) 2008; 46
Ma (10.1016/j.bspc.2023.105885_b0160) 2019; 28
Sun (10.1016/j.bspc.2023.105885_b0185) 2021; 28
10.1016/j.bspc.2023.105885_b0225
Muller-Putz (10.1016/j.bspc.2023.105885_b0015) 2007; 55
Yong (10.1016/j.bspc.2023.105885_b0090) 2015; 10
Pfurtscheller (10.1016/j.bspc.2023.105885_b0025) 2001; 89
Thodoroff (10.1016/j.bspc.2023.105885_b0140) 2016
Vučković (10.1016/j.bspc.2023.105885_b0155) 2012; 34
Lawhern (10.1016/j.bspc.2023.105885_b0190) 2018; 15
10.1016/j.bspc.2023.105885_b0220
Supratak (10.1016/j.bspc.2023.105885_b0135) 2017; 25
10.1016/j.bspc.2023.105885_b0180
Zhu (10.1016/j.bspc.2023.105885_b0215) 2021
Srivastava (10.1016/j.bspc.2023.105885_b0230) 2014; 15
Hao (10.1016/j.bspc.2023.105885_b0115) 2016; 10
Gómez-Herrero (10.1016/j.bspc.2023.105885_b0205) 2006; 2006
Lu (10.1016/j.bspc.2023.105885_b0150) 2016; 25
Herman (10.1016/j.bspc.2023.105885_b0060) 2008; 16
Dunsky (10.1016/j.bspc.2023.105885_b0045) 2018; 10
Zheng (10.1016/j.bspc.2023.105885_b0085) 2018; 275
Chu (10.1016/j.bspc.2023.105885_b0110) 2020; 17
Shih (10.1016/j.bspc.2023.105885_b0005) 2012; 87
Polich (10.1016/j.bspc.2023.105885_b0020) 2007; 118
Ang (10.1016/j.bspc.2023.105885_b0040) 2015; 46
Ma (10.1016/j.bspc.2023.105885_b0095) 2020; 7
Zhang (10.1016/j.bspc.2023.105885_b0075) 2017; 12
Delorme (10.1016/j.bspc.2023.105885_b0200) 2004; 134
10.1016/j.bspc.2023.105885_b0035
Zheng (10.1016/j.bspc.2023.105885_b0120) 2015; 7
Robinson (10.1016/j.bspc.2023.105885_b0050) 2013; 60
10.1016/j.bspc.2023.105885_b0235
Li (10.1016/j.bspc.2023.105885_b0125) 2018; 10
10.1016/j.bspc.2023.105885_b0130
Hsu (10.1016/j.bspc.2023.105885_b0080) 2017; 19
Ma (10.1016/j.bspc.2023.105885_b0165) 2022; 30
10.1016/j.bspc.2023.105885_b0175
Frisoli (10.1016/j.bspc.2023.105885_b0030) 2012; 42
10.1016/j.bspc.2023.105885_b0055
10.1016/j.bspc.2023.105885_b0170
Jia (10.1016/j.bspc.2023.105885_b0210) 2021
Jia (10.1016/j.bspc.2023.105885_b0195) 2020
Van der Maaten (10.1016/j.bspc.2023.105885_b0240) 2008; 9
Vuckovic (10.1016/j.bspc.2023.105885_b0100) 2008; 46
Ofner (10.1016/j.bspc.2023.105885_b0105) 2017; 12
Tavakolan (10.1016/j.bspc.2023.105885_b0070) 2017; 12
Schirrmeister (10.1016/j.bspc.2023.105885_b0145) 2017; 38
Teo (10.1016/j.bspc.2023.105885_b0010) 2014; 6
Hwang (10.1016/j.bspc.2023.105885_b0065) 2020; 23
References_xml – volume: 46
  start-page: 310
  year: 2015
  end-page: 320
  ident: b0040
  article-title: A randomized controlled trial of EEG-based motor imagery brain-computer interface robotic rehabilitation for stroke
  publication-title: Clin. EEG Neurosci.
– volume: 15
  year: 2018
  ident: b0190
  article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J. Neural Eng.
– reference: S. Yan, Y. Xiong, D. Lin. Spatial temporal graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the AAAI conference on artificial intelligence. 2018, 32(1).
– volume: 118
  start-page: 2128
  year: 2007
  end-page: 2148
  ident: b0020
  article-title: Updating P300: an integrative theory of P3a and P3b
  publication-title: Clin. Neurophysiol.
– reference: Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
– start-page: 1047
  year: 2021
  end-page: 1056
  ident: b0210
  article-title: HetEmotionNet: two-stream heterogeneous graph recurrent neural network for multi-modal emotion recognition[C]//Proceedings of
  publication-title: The 29th ACM International Conference on Multimedia
– volume: 23
  start-page: 1323
  year: 2020
  end-page: 1335
  ident: b0065
  article-title: Learning CNN features from DE features for EEG-based emotion recognition
  publication-title: Pattern Anal. Appl.
– volume: 12
  start-page: e0174161
  year: 2017
  ident: b0070
  article-title: Classifying three imaginary states of the same upper extremity using time-domain features
  publication-title: PLoS One
– volume: 30
  start-page: 496
  year: 2022
  end-page: 508
  ident: b0165
  article-title: Time-distributed attention network for EEG-based motor imagery decoding from the same limb
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– reference: Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//International conference on machine learning. pmlr, 2015: 448-456.
– start-page: 178
  year: 2016
  end-page: 190
  ident: b0140
  article-title: Learning robust features using deep learning for automatic seizure detection
  publication-title: Machine learning for healthcare conference PMLR
– volume: 28
  start-page: 297
  year: 2019
  end-page: 306
  ident: b0160
  article-title: Deep channel-correlation network for motor imagery decoding from the same limb
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 7
  start-page: 191
  year: 2020
  ident: b0095
  article-title: Multi-channel EEG recording during motor imagery of different joints from the same limb
  publication-title: Sci. Data
– volume: 7
  start-page: 162
  year: 2015
  end-page: 175
  ident: b0120
  article-title: Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks
  publication-title: IEEE Trans. Auton. Ment. Dev.
– reference: Kwak Y, Song W J, Kim S E. Graph neural network with multilevel feature fusion for EEG based brain-computer interface[C]//2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia). IEEE, 2020: 1-3.
– start-page: 1324
  year: 2020
  end-page: 1330
  ident: b0195
  article-title: GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for
  publication-title: Sleep Stage Classification[C]//IJCAI. 2021
– volume: 25
  start-page: 566
  year: 2016
  end-page: 576
  ident: b0150
  article-title: A deep learning scheme for motor imagery classification based on restricted Boltzmann machines
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 25
  start-page: 1998
  year: 2017
  end-page: 2008
  ident: b0135
  article-title: DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– reference: Hou Y, Jia S, Lun X, et al. Deep feature mining via attention-based BiLSTM-GCN for human motor imagery recognition[J]. arXiv preprint arXiv:2005.00777, 2020.
– volume: 10
  start-page: 66
  year: 2018
  ident: b0045
  article-title: Motor Imagery Training for Gait Rehabilitation of People with Post-Stroke Hemiparesis: Practical Applications and Protocols
  publication-title: Glob. J. Health Sci.
– volume: 17
  year: 2020
  ident: b0110
  article-title: Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression
  publication-title: J. Neural Eng.
– reference: Yahya-Zoubir B, Bentlemsan M, Zemouri E T T, et al. Adaptive time window for EEG-based motor imagery classification[C]//Proceedings of the International Conference on Intelligent Information Processing, Security and Advanced Communication. 2015: 1-6.
– volume: 16
  start-page: 317
  year: 2008
  end-page: 326
  ident: b0060
  article-title: Comparative analysis of spectral approaches to feature extraction for EEG-based motor imagery classification
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 28
  start-page: 219
  year: 2021
  end-page: 223
  ident: b0185
  article-title: Adaptive spatiotemporal graph convolutional networks for motor imagery classification
  publication-title: IEEE Signal Process Lett.
– volume: 2006
  start-page: 130
  year: 2006
  end-page: 133
  ident: b0205
  article-title: Automatic removal of ocular artifacts in the EEG without an EOG reference channel[C]//Proceedings of the 7th Nordic signal processing symposium-NORSIG
  publication-title: IEEE
– start-page: 2069
  year: 2021, 2021,
  end-page: 2080
  ident: b0215
  article-title: Graph contrastive learning with adaptive augmentation
  publication-title: Proceedings of the Web Conference
– volume: 87
  start-page: 268
  year: 2012
  end-page: 279
  ident: b0005
  article-title: Brain-computer interfaces in medicine
  publication-title: Mayo clinic proceedings Elsevier
– volume: 19
  start-page: 566
  year: 2017
  end-page: 579
  ident: b0080
  article-title: EEG classification of imaginary lower limb stepping movements based on fuzzy support vector machine with kernel-induced membership function
  publication-title: Int. J. Fuzzy Syst.
– volume: 275
  start-page: 869
  year: 2018
  end-page: 880
  ident: b0085
  article-title: Multiclass support matrix machine for single trial EEG classification
  publication-title: Neurocomputing
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: b0230
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– volume: 89
  start-page: 1123
  year: 2001
  end-page: 1134
  ident: b0025
  article-title: Motor imagery and direct brain-computer communication
  publication-title: Proc. IEEE
– volume: 60
  start-page: 2123
  year: 2013
  end-page: 2132
  ident: b0050
  article-title: EEG-based classification of fast and slow hand movements using wavelet-CSP algorithm
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 12
  start-page: e0182578
  year: 2017
  ident: b0105
  article-title: Upper limb movements can be decoded from the time-domain of low-frequency EEG
  publication-title: PLoS One
– volume: 42
  start-page: 1169
  year: 2012
  end-page: 1179
  ident: b0030
  article-title: A new gaze-BCI-driven control of an upper limb exoskeleton for rehabilitation in real-world tasks
  publication-title: IEEE Trans. Syst. Man Cybern. Part C (applications and Reviews)
– volume: 10
  start-page: 368
  year: 2018
  end-page: 380
  ident: b0125
  article-title: Hierarchical convolutional neural networks for EEG-based emotion recognition
  publication-title: Cogn. Comput.
– reference: Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
– volume: 134
  start-page: 9
  year: 2004
  end-page: 21
  ident: b0200
  article-title: EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis
  publication-title: J. Neurosci. Methods
– volume: 46
  start-page: 529
  year: 2008
  end-page: 539
  ident: b0100
  article-title: Delta band contribution in cue based single trial classification of real and imaginary wrist movements
  publication-title: Med. Biol. Eng. Compu.
– volume: 10
  start-page: e0121896
  year: 2015
  ident: b0090
  article-title: EEG classification of different imaginary movements within the same limb
  publication-title: PLoS One
– volume: 34
  start-page: 964
  year: 2012
  end-page: 971
  ident: b0155
  article-title: A two-stage four-class BCI based on imaginary movements of the left and the right wrist
  publication-title: Med. Eng. Phys.
– volume: 55
  start-page: 361
  year: 2007
  end-page: 364
  ident: b0015
  article-title: Control of an electrical prosthesis with an SSVEP-based BCI
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 38
  start-page: 5391
  year: 2017
  end-page: 5420
  ident: b0145
  article-title: Deep learning with convolutional neural networks for EEG decoding and visualization
  publication-title: Hum. Brain Mapp.
– volume: 9
  year: 2008
  ident: b0240
  article-title: Visualizing data using t-SNE
  publication-title: J. Mach. Learn. Res.
– reference: K. Choi A. Cichocki Control of a wheelchair by motor imagery in real time[C]//Intelligent Data Engineering and Automated Learning–IDEAL 2008: 9th International Conference Daejeon, South Korea, November 2-5, 2008 Proceedings 9. Springer Berlin Heidelberg, 2008: 330-337.
– reference: Wang Y, Liu X, Zhang Y, et al. Driving fatigue detection based on EEG signal[C]//2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC). IEEE, 2015: 715-718.
– volume: 12
  start-page: e0188293
  year: 2017
  ident: b0075
  article-title: Evaluating the versatility of EEG models generated from motor imagery tasks: An exploratory investigation on upper-limb elbow-centered motor imagery tasks
  publication-title: PLoS One
– volume: 6
  start-page: 723
  year: 2014
  end-page: 728
  ident: b0010
  article-title: Is motor-imagery brain-computer interface feasible in stroke rehabilitation?
  publication-title: PM&R
– volume: 10
  start-page: 417
  year: 2016
  end-page: 439
  ident: b0115
  article-title: Deep learning
  publication-title: Int. J. Seman. Comput.
– volume: 28
  start-page: 297
  issue: 1
  year: 2019
  ident: 10.1016/j.bspc.2023.105885_b0160
  article-title: Deep channel-correlation network for motor imagery decoding from the same limb
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2019.2953121
– volume: 25
  start-page: 566
  issue: 6
  year: 2016
  ident: 10.1016/j.bspc.2023.105885_b0150
  article-title: A deep learning scheme for motor imagery classification based on restricted Boltzmann machines
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2016.2601240
– volume: 46
  start-page: 529
  year: 2008
  ident: 10.1016/j.bspc.2023.105885_b0100
  article-title: Delta band contribution in cue based single trial classification of real and imaginary wrist movements
  publication-title: Med. Biol. Eng. Compu.
  doi: 10.1007/s11517-008-0345-8
– ident: 10.1016/j.bspc.2023.105885_b0180
– volume: 60
  start-page: 2123
  issue: 8
  year: 2013
  ident: 10.1016/j.bspc.2023.105885_b0050
  article-title: EEG-based classification of fast and slow hand movements using wavelet-CSP algorithm
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2013.2248153
– volume: 19
  start-page: 566
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0080
  article-title: EEG classification of imaginary lower limb stepping movements based on fuzzy support vector machine with kernel-induced membership function
  publication-title: Int. J. Fuzzy Syst.
  doi: 10.1007/s40815-016-0259-9
– start-page: 1047
  year: 2021
  ident: 10.1016/j.bspc.2023.105885_b0210
  article-title: HetEmotionNet: two-stream heterogeneous graph recurrent neural network for multi-modal emotion recognition[C]//Proceedings of
– volume: 10
  start-page: 66
  issue: 11
  year: 2018
  ident: 10.1016/j.bspc.2023.105885_b0045
  article-title: Motor Imagery Training for Gait Rehabilitation of People with Post-Stroke Hemiparesis: Practical Applications and Protocols
  publication-title: Glob. J. Health Sci.
  doi: 10.5539/gjhs.v10n11p66
– volume: 30
  start-page: 496
  year: 2022
  ident: 10.1016/j.bspc.2023.105885_b0165
  article-title: Time-distributed attention network for EEG-based motor imagery decoding from the same limb
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2022.3154369
– volume: 10
  start-page: e0121896
  issue: 4
  year: 2015
  ident: 10.1016/j.bspc.2023.105885_b0090
  article-title: EEG classification of different imaginary movements within the same limb
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0121896
– start-page: 1324
  year: 2020
  ident: 10.1016/j.bspc.2023.105885_b0195
  article-title: GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for
  publication-title: Sleep Stage Classification[C]//IJCAI. 2021
– volume: 7
  start-page: 191
  issue: 1
  year: 2020
  ident: 10.1016/j.bspc.2023.105885_b0095
  article-title: Multi-channel EEG recording during motor imagery of different joints from the same limb
  publication-title: Sci. Data
  doi: 10.1038/s41597-020-0535-2
– volume: 87
  start-page: 268
  issue: 3
  year: 2012
  ident: 10.1016/j.bspc.2023.105885_b0005
  article-title: Brain-computer interfaces in medicine
  publication-title: Mayo clinic proceedings Elsevier
  doi: 10.1016/j.mayocp.2011.12.008
– volume: 55
  start-page: 361
  issue: 1
  year: 2007
  ident: 10.1016/j.bspc.2023.105885_b0015
  article-title: Control of an electrical prosthesis with an SSVEP-based BCI
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2007.897815
– start-page: 178
  year: 2016
  ident: 10.1016/j.bspc.2023.105885_b0140
  article-title: Learning robust features using deep learning for automatic seizure detection
  publication-title: Machine learning for healthcare conference PMLR
– volume: 10
  start-page: 368
  year: 2018
  ident: 10.1016/j.bspc.2023.105885_b0125
  article-title: Hierarchical convolutional neural networks for EEG-based emotion recognition
  publication-title: Cogn. Comput.
  doi: 10.1007/s12559-017-9533-x
– ident: 10.1016/j.bspc.2023.105885_b0175
  doi: 10.1109/ICCE-Asia49877.2020.9276983
– ident: 10.1016/j.bspc.2023.105885_b0220
  doi: 10.1609/aaai.v32i1.12328
– volume: 275
  start-page: 869
  year: 2018
  ident: 10.1016/j.bspc.2023.105885_b0085
  article-title: Multiclass support matrix machine for single trial EEG classification
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2017.09.030
– volume: 10
  start-page: 417
  issue: 03
  year: 2016
  ident: 10.1016/j.bspc.2023.105885_b0115
  article-title: Deep learning
  publication-title: Int. J. Seman. Comput.
  doi: 10.1142/S1793351X16500045
– volume: 34
  start-page: 964
  issue: 7
  year: 2012
  ident: 10.1016/j.bspc.2023.105885_b0155
  article-title: A two-stage four-class BCI based on imaginary movements of the left and the right wrist
  publication-title: Med. Eng. Phys.
  doi: 10.1016/j.medengphy.2011.11.001
– volume: 16
  start-page: 317
  issue: 4
  year: 2008
  ident: 10.1016/j.bspc.2023.105885_b0060
  article-title: Comparative analysis of spectral approaches to feature extraction for EEG-based motor imagery classification
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2008.926694
– ident: 10.1016/j.bspc.2023.105885_b0035
  doi: 10.1007/978-3-540-88906-9_42
– ident: 10.1016/j.bspc.2023.105885_b0130
  doi: 10.1109/IMCCC.2015.156
– volume: 12
  start-page: e0182578
  issue: 8
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0105
  article-title: Upper limb movements can be decoded from the time-domain of low-frequency EEG
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0182578
– volume: 12
  start-page: e0188293
  issue: 11
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0075
  article-title: Evaluating the versatility of EEG models generated from motor imagery tasks: An exploratory investigation on upper-limb elbow-centered motor imagery tasks
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0188293
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: 10.1016/j.bspc.2023.105885_b0230
  article-title: Dropout: a simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– volume: 118
  start-page: 2128
  issue: 10
  year: 2007
  ident: 10.1016/j.bspc.2023.105885_b0020
  article-title: Updating P300: an integrative theory of P3a and P3b
  publication-title: Clin. Neurophysiol.
  doi: 10.1016/j.clinph.2007.04.019
– volume: 28
  start-page: 219
  year: 2021
  ident: 10.1016/j.bspc.2023.105885_b0185
  article-title: Adaptive spatiotemporal graph convolutional networks for motor imagery classification
  publication-title: IEEE Signal Process Lett.
  doi: 10.1109/LSP.2021.3049683
– volume: 134
  start-page: 9
  issue: 1
  year: 2004
  ident: 10.1016/j.bspc.2023.105885_b0200
  article-title: EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis
  publication-title: J. Neurosci. Methods
  doi: 10.1016/j.jneumeth.2003.10.009
– volume: 25
  start-page: 1998
  issue: 11
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0135
  article-title: DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2017.2721116
– volume: 6
  start-page: 723
  issue: 8
  year: 2014
  ident: 10.1016/j.bspc.2023.105885_b0010
  article-title: Is motor-imagery brain-computer interface feasible in stroke rehabilitation?
  publication-title: PM&R
  doi: 10.1016/j.pmrj.2014.01.006
– volume: 17
  issue: 4
  year: 2020
  ident: 10.1016/j.bspc.2023.105885_b0110
  article-title: Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/aba7cd
– ident: 10.1016/j.bspc.2023.105885_b0225
– start-page: 2069
  year: 2021
  ident: 10.1016/j.bspc.2023.105885_b0215
  article-title: Graph contrastive learning with adaptive augmentation
  publication-title: Proceedings of the Web Conference
– ident: 10.1016/j.bspc.2023.105885_b0170
– volume: 46
  start-page: 310
  issue: 4
  year: 2015
  ident: 10.1016/j.bspc.2023.105885_b0040
  article-title: A randomized controlled trial of EEG-based motor imagery brain-computer interface robotic rehabilitation for stroke
  publication-title: Clin. EEG Neurosci.
  doi: 10.1177/1550059414522229
– ident: 10.1016/j.bspc.2023.105885_b0055
  doi: 10.1145/2816839.2816845
– volume: 12
  start-page: e0174161
  issue: 3
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0070
  article-title: Classifying three imaginary states of the same upper extremity using time-domain features
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0174161
– volume: 89
  start-page: 1123
  issue: 7
  year: 2001
  ident: 10.1016/j.bspc.2023.105885_b0025
  article-title: Motor imagery and direct brain-computer communication
  publication-title: Proc. IEEE
  doi: 10.1109/5.939829
– volume: 9
  issue: 11
  year: 2008
  ident: 10.1016/j.bspc.2023.105885_b0240
  article-title: Visualizing data using t-SNE
  publication-title: J. Mach. Learn. Res.
– volume: 23
  start-page: 1323
  year: 2020
  ident: 10.1016/j.bspc.2023.105885_b0065
  article-title: Learning CNN features from DE features for EEG-based emotion recognition
  publication-title: Pattern Anal. Appl.
  doi: 10.1007/s10044-019-00860-w
– volume: 7
  start-page: 162
  issue: 3
  year: 2015
  ident: 10.1016/j.bspc.2023.105885_b0120
  article-title: Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks
  publication-title: IEEE Trans. Auton. Ment. Dev.
  doi: 10.1109/TAMD.2015.2431497
– volume: 42
  start-page: 1169
  issue: 6
  year: 2012
  ident: 10.1016/j.bspc.2023.105885_b0030
  article-title: A new gaze-BCI-driven control of an upper limb exoskeleton for rehabilitation in real-world tasks
  publication-title: IEEE Trans. Syst. Man Cybern. Part C (applications and Reviews)
  doi: 10.1109/TSMCC.2012.2226444
– volume: 2006
  start-page: 130
  year: 2006
  ident: 10.1016/j.bspc.2023.105885_b0205
  article-title: Automatic removal of ocular artifacts in the EEG without an EOG reference channel[C]//Proceedings of the 7th Nordic signal processing symposium-NORSIG
  publication-title: IEEE
– volume: 15
  issue: 5
  year: 2018
  ident: 10.1016/j.bspc.2023.105885_b0190
  article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/aace8c
– volume: 38
  start-page: 5391
  issue: 11
  year: 2017
  ident: 10.1016/j.bspc.2023.105885_b0145
  article-title: Deep learning with convolutional neural networks for EEG decoding and visualization
  publication-title: Hum. Brain Mapp.
  doi: 10.1002/hbm.23730
– ident: 10.1016/j.bspc.2023.105885_b0235
SSID ssj0048714
Score 2.331359
Snippet •A novel coarse-to-fine classification approach is proposed to decode MI tasks of the same upper limb.•A adaptive spatial–temporal graph convolutional network...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 105885
SubjectTerms Adaptive spatial–temporal graph convolutional network
Brain Computer Interface(BCI)
Coarse-to-fine classification approach
Different joints of the same limb
Motor Imagery (MI)
Title A coarse-to-fine adaptive spatial–temporal graph convolution network with residuals for motor imagery decoding from the same limb
URI https://dx.doi.org/10.1016/j.bspc.2023.105885
Volume 90
WOSCitedRecordID wos001152576000001&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
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect database
  customDbUrl:
  eissn: 1746-8108
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0048714
  issn: 1746-8094
  databaseCode: AIEXJ
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Li9RAEG7GXQ96EJ-4vuiDt5Alr04nx0FWdJBFcIW5he50R7PMZMLOzLLeBH-C_8Cf5i-xqh-Z7CqigpcQGjoJXR-Vqur6vibkuSpKIRMF3q9gZpuRhyVvklDqWEN0ykUkDVH4DT8-Lubz8u1k8s1zYc4XvOuKi4uy_6-mhjEwNlJn_8Lcw0NhAO7B6HAFs8P1jww_DeoVZKs63KzCBmNIoURvGoTW2D0tFr6_IXWyVIvAqFabBnT3ZUFnu8NtmRYyckPZMtINAdgWe9iXKH7xKVCQvhpezMBTWYulDhbtUl7aLzYsf0vBbD9gBNxbhoLnSLqW-V0de2sqBrod3NLWlmpn7QiKrtg9bUW7m-kGZwD8j27clTWScTeMqbV5vs2uuQndM89QPtkei3yoR2NxVIx9uj2C9Kffg61UnB7KdY_ylUmKxxwX9sygK7Lb7_C5-CrI0WJwfPk1sp9wVoLn3J--PprP_P8eMj6jID98m6Nm2S7Cq2_6dfgzCmlObpNbLhehU4uhO2Siu7vk5kih8h75MqWX0UQ9mqhD0_fPXz2OqMERHeGIOhxRxBEdcEQBR9TgiDocUY8jijiigCOKOKKIo_vk_cujkxevQnduR1hDtLwJ61zWmiuZJDpXIs8jFWdxw7JUN3Ekolw2qcoLpgUTDeMqbkou4ihXLFNJyhRLH5C9btXph4RmCreRo5RLlmQwo5S1QglcXmR1WqT6gAR-OaveyrNUvm_xtMLFr3DxK7v4B4T5Fa9cgGkDxwoA8pt5j_5x3mNyYwftJ2Rvc7bVT8n1-nzTrs-eORz9AKUWphU
linkProvider Elsevier
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%3Ajournal&rft.genre=article&rft.atitle=A+coarse-to-fine+adaptive+spatial%E2%80%93temporal+graph+convolution+network+with+residuals+for+motor+imagery+decoding+from+the+same+limb&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Zhu%2C+Lei&rft.au=Yuan%2C+Jie&rft.au=Huang%2C+Aiai&rft.au=Zhang%2C+Jianhai&rft.date=2024-04-01&rft.pub=Elsevier+Ltd&rft.issn=1746-8094&rft.eissn=1746-8108&rft.volume=90&rft_id=info:doi/10.1016%2Fj.bspc.2023.105885&rft.externalDocID=S1746809423013186
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon