A novel adaptive spatial–temporal cross-graph convolutional fusion learning network for skeleton-based abnormal gait recognition

Developing graph-based abnormal gait classification models with high generalization has been a challenging problem in gait analysis. In this study, a novel adaptive spatial–temporal cross-graph convolutional fusion learning network is proposed to accurately recognize skeleton-based abnormal gait pat...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Engineering applications of artificial intelligence Ročník 154; s. 110922
Hlavní autoři: Wang, Liang, Wu, Xiaoyan, Wu, Bin, Wu, Jianning
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 15.08.2025
Témata:
ISSN:0952-1976
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Developing graph-based abnormal gait classification models with high generalization has been a challenging problem in gait analysis. In this study, a novel adaptive spatial–temporal cross-graph convolutional fusion learning network is proposed to accurately recognize skeleton-based abnormal gait patterns. In the proposed model, with an adaptive fusion adjacency matrix including self-adaptive adjacency matrices and cross-adaptive adjacency matrices, a joint–bone gait graph convolutional fusion learning algorithm is constructed to capture spatial gait abnormality features hidden in skeleton data. A temporal convolution network is then adopted to explore temporal dependencies of gait abnormality embedded in the spatial feature space. This could discover the most discriminative spatial–temporal gait abnormality representations containing richer information about interaction coupling across joints and bones for high-generalization. The skeleton data of mimic abnormal gait from 57 participants were collected to evaluate the feasibility of our model. The experimental results based on the leave-one-subject-out (LOSO) cross-validation scheme show that our proposed model reaches the optimal performance with the highest accuracy of 99.43%, and significantly outcompetes several recent state-of-the-art models. Our model can feasibly take advantage of the adaptive fusion adjacency matrix to greatly enhance the aggregation degree of joints and bones. This helps to learn excellent gait abnormality representations containing richer interaction information for high generalization while keeping a low learning complexity. Our findings hopefully provide a powerful technical solution for abnormal gait recognition in practical clinical application.
AbstractList Developing graph-based abnormal gait classification models with high generalization has been a challenging problem in gait analysis. In this study, a novel adaptive spatial–temporal cross-graph convolutional fusion learning network is proposed to accurately recognize skeleton-based abnormal gait patterns. In the proposed model, with an adaptive fusion adjacency matrix including self-adaptive adjacency matrices and cross-adaptive adjacency matrices, a joint–bone gait graph convolutional fusion learning algorithm is constructed to capture spatial gait abnormality features hidden in skeleton data. A temporal convolution network is then adopted to explore temporal dependencies of gait abnormality embedded in the spatial feature space. This could discover the most discriminative spatial–temporal gait abnormality representations containing richer information about interaction coupling across joints and bones for high-generalization. The skeleton data of mimic abnormal gait from 57 participants were collected to evaluate the feasibility of our model. The experimental results based on the leave-one-subject-out (LOSO) cross-validation scheme show that our proposed model reaches the optimal performance with the highest accuracy of 99.43%, and significantly outcompetes several recent state-of-the-art models. Our model can feasibly take advantage of the adaptive fusion adjacency matrix to greatly enhance the aggregation degree of joints and bones. This helps to learn excellent gait abnormality representations containing richer interaction information for high generalization while keeping a low learning complexity. Our findings hopefully provide a powerful technical solution for abnormal gait recognition in practical clinical application.
ArticleNumber 110922
Author Wu, Xiaoyan
Wang, Liang
Wu, Bin
Wu, Jianning
Author_xml – sequence: 1
  givenname: Liang
  surname: Wang
  fullname: Wang, Liang
  email: qsx20221304@student.fjnu.edu.cn
  organization: College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, China
– sequence: 2
  givenname: Xiaoyan
  surname: Wu
  fullname: Wu, Xiaoyan
  email: c3034755@newcastle.ac.uk
  organization: Business School, Newcastle University, Newcastle, NE1 7RU, UK
– sequence: 3
  givenname: Bin
  surname: Wu
  fullname: Wu, Bin
  email: wubin@fjnu.edu.cn
  organization: Hospital of Fujian Normal University, Fuzhou 350007, China
– sequence: 4
  givenname: Jianning
  surname: Wu
  fullname: Wu, Jianning
  email: jianningwu@fjnu.edu.cn
  organization: College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, China
BookMark eNqFkE1OwzAQhb0oEm3hCsgXSLGT1CE7qoo_qRIbWFsTexzcpnZku0XsEFfghpyElMKa1Yw07z3N-yZk5LxDQi44m3HGxeV6hq6Fvgc7y1k-n3HO6jwfkTGr53nG60qckkmMa8ZYcVWKMflYUOf32FHQ0Ce7Rxp7SBa6r_fPhNveB-ioCj7GrA3Qv1Dl3d53u2S9Gy5mF4eFdgjBWddSh-nVhw01PtC4wQ6Td1kDETWFxvmwHTwt2EQDKt86e4g5IycGuojnv3NKnm9vnpb32erx7mG5WGUqFzxllc51AaoBA3NVMs1qllcGiwqEGQSl5g1UQpgKqqKsaq04aCPAcM1Qz1lZTIk45v7UCWhkH-wWwpvkTB7oybX8oycP9OSR3mC8Phpx-G5vMcioLDqF2g41ktTe_hfxDXCyheQ
Cites_doi 10.1016/j.artmed.2018.12.007
10.1145/3404835.3463031
10.1109/ACCESS.2019.2952065
10.1109/TMM.2022.3168137
10.3390/app13074205
10.1109/TITS.2019.2935152
10.1109/ACCESS.2020.3022818
10.1007/s13278-024-01271-4
10.1109/CVPR.2019.01230
10.3390/s16111792
10.1016/j.eswa.2021.115582
10.1016/j.gaitpost.2015.05.002
10.1109/ACCESS.2020.3013029
10.1109/TNNLS.2022.3188569
10.1016/S0966-6362(02)00089-9
10.1016/j.neucom.2021.12.004
10.1109/ACCESS.2019.2950254
10.1007/s00371-016-1330-0
10.1016/j.jbi.2016.08.003
10.1016/j.jbiomech.2010.12.013
10.21629/JSEE.2017.01.18
10.1109/TMM.2021.3068609
10.1109/CVPR.2017.143
10.1145/3308558.3313417
10.1016/j.eswa.2023.120968
10.1109/TNSRE.2024.3352004
10.1109/ACCESS.2020.2967845
10.1109/ICCV48922.2021.01311
10.1109/MMUL.2012.24
10.5435/00124635-200702000-00005
10.1016/j.compbiomed.2022.105823
10.3390/s18020676
10.1109/TNNLS.2021.3105602
ContentType Journal Article
Copyright 2025 Elsevier Ltd
Copyright_xml – notice: 2025 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.engappai.2025.110922
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
ExternalDocumentID 10_1016_j_engappai_2025_110922
S0952197625009224
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABJNI
ABMAC
ACDAQ
ACGFS
ACRLP
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGCQF
AGHFR
AGRNS
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
AXJTR
BJAXD
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSH
SST
SSV
SSZ
T5K
TN5
~G-
29G
9DU
AAQXK
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ADJOM
ADMUD
ADNMO
AGQPQ
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
UHS
WUQ
ZMT
~HD
ID FETCH-LOGICAL-c261t-7d2d3acbafa5c40d09027fe37a6f2614d1ba766f7a73479dc1adf6af1d0ed5043
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001488082300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0952-1976
IngestDate Sat Nov 29 07:52:04 EST 2025
Sat Jun 21 16:52:33 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Adaptive learning
Graph fusion learning
Graph convolutional networks
Abnormal gait recognition
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c261t-7d2d3acbafa5c40d09027fe37a6f2614d1ba766f7a73479dc1adf6af1d0ed5043
ParticipantIDs crossref_primary_10_1016_j_engappai_2025_110922
elsevier_sciencedirect_doi_10_1016_j_engappai_2025_110922
PublicationCentury 2000
PublicationDate 2025-08-15
PublicationDateYYYYMMDD 2025-08-15
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-08-15
  day: 15
PublicationDecade 2020
PublicationTitle Engineering applications of artificial intelligence
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Pan, Lin, Dong, Wang, Ji (b24) 2022; 148
He, Y., Liu, X., Cheung, Y.-M., Peng, S.-J., Yi, J., Fan, W., 2021. Cross-graph attention enhanced multi-modal correlation learning for fine-grained image-text retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1865–1869.
Wu, Wu (b36) 2015; 2015
Zhao, Song, Zhang, Liu, Wang, Lin, Deng, Li (b44) 2019; 21
Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y., 2017. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7291–7299.
Zeng, Liu, Yu, Wu, Huo, Han (b41) 2023
Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W., 2021. Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13359–13368.
Nguyen, Huynh, Meunier (b22) 2016; 16
Gao, Gu, Ren, Zhang, Song (b9) 2019; 7
Gouwanda, Senanayake (b10) 2011; 44
Sadeghi (b27) 2003; 17
Bari, Gavrilova (b2) 2019; 7
Zhang (b42) 2012; 19
Mostayed, Mynuddin, Mazumder, Kim, Park (b21) 2008
Tian, Ma, Wu, Li (b31) 2022; 473
Wu, Huang, Wu, Dai (b34) 2023; 233
Yan, Xiong, Lin (b38) 2018; vol. 32
Hu, Wang, Martens, Hagenbuchner, Bennamoun, Tsoi, Lewis (b13) 2021; 34
Peng, He, Liu, Cheung, Xu, Cui (b25) 2022; 35
Lim, Huang, Wu, Girardi, Cammisa (b20) 2007; 15
Xu, McGorry, Chou, Lin, Chang (b37) 2015; 42
Lee, Jun, Lee, Ko, Kim (b18) 2019
Chaaraoui, Padilla-López, Flórez-Revuelta (b4) 2015; vol. 7
Kipf, Welling (b17) 2016
Khokhlova, Migniot, Morozov, Sushkova, Dipanda (b16) 2019; 94
Zhao, Lu, Chen, Liu, Wu (b43) 2017; 28
Li, Wang, Sharf, Cao, Tu, Chen, Yu (b19) 2018; 34
Shi, L., Zhang, Y., Cheng, J., Lu, H., 2019. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 12026–12035.
Wang, H., Zhao, M., Xie, X., Li, W., Guo, M., 2019. Knowledge graph convolutional networks for recommender systems. In: The World Wide Web Conference. pp. 3307–3313.
Wu, Lian, Xu, Wu, Chen (b35) 2020; vol. 34
Guo, Shao, Zhang, Qian (b11) 2021; 24
Jun, Lee, Lee, Lee, Kim (b15) 2020; 8
Nieto-Hidalgo, Ferrández-Pastor, Valdivieso-Sarabia, Mora-Pascual, García-Chamizo (b23) 2016; 63
Jun, Lee, Lee, Lee, Kim (b14) 2020; 8
Duhme, Memmesheimer, Paulus (b7) 2021
Tian, Li, Jiang, Ma, Li, Wu, Li (b30) 2024
Saboor, Kask, Kuusik, Alam, Le Moullec, Niazi, Zoha, Ahmad (b26) 2020; 8
Anwary, Yu, Vassallo (b1) 2018; 18
Tu, Zhang, Li, Chen, Yuan (b32) 2022; 25
Yao, Mao, Luo (b39) 2019; vol. 33
Fout, Byrd, Shariat, Ben-Hur (b8) 2017; 30
Sadeghzadehyazdi, Batabyal, Acton (b28) 2021; 185
Yin, Jiang, Zheng, Yu (b40) 2023; 13
Dhawan, Sharma, Kadam, Sharma, Kumaraguru (b6) 2024; 14
Sadeghzadehyazdi (10.1016/j.engappai.2025.110922_b28) 2021; 185
Zhao (10.1016/j.engappai.2025.110922_b44) 2019; 21
Peng (10.1016/j.engappai.2025.110922_b25) 2022; 35
Tu (10.1016/j.engappai.2025.110922_b32) 2022; 25
Sadeghi (10.1016/j.engappai.2025.110922_b27) 2003; 17
Yan (10.1016/j.engappai.2025.110922_b38) 2018; vol. 32
10.1016/j.engappai.2025.110922_b3
Gouwanda (10.1016/j.engappai.2025.110922_b10) 2011; 44
Zhao (10.1016/j.engappai.2025.110922_b43) 2017; 28
10.1016/j.engappai.2025.110922_b5
Hu (10.1016/j.engappai.2025.110922_b13) 2021; 34
Xu (10.1016/j.engappai.2025.110922_b37) 2015; 42
Dhawan (10.1016/j.engappai.2025.110922_b6) 2024; 14
Lee (10.1016/j.engappai.2025.110922_b18) 2019
Kipf (10.1016/j.engappai.2025.110922_b17) 2016
Lim (10.1016/j.engappai.2025.110922_b20) 2007; 15
Gao (10.1016/j.engappai.2025.110922_b9) 2019; 7
Anwary (10.1016/j.engappai.2025.110922_b1) 2018; 18
Jun (10.1016/j.engappai.2025.110922_b14) 2020; 8
10.1016/j.engappai.2025.110922_b33
Yin (10.1016/j.engappai.2025.110922_b40) 2023; 13
10.1016/j.engappai.2025.110922_b12
Nieto-Hidalgo (10.1016/j.engappai.2025.110922_b23) 2016; 63
Saboor (10.1016/j.engappai.2025.110922_b26) 2020; 8
Nguyen (10.1016/j.engappai.2025.110922_b22) 2016; 16
Wu (10.1016/j.engappai.2025.110922_b35) 2020; vol. 34
Zhang (10.1016/j.engappai.2025.110922_b42) 2012; 19
Mostayed (10.1016/j.engappai.2025.110922_b21) 2008
Jun (10.1016/j.engappai.2025.110922_b15) 2020; 8
Tian (10.1016/j.engappai.2025.110922_b30) 2024
Li (10.1016/j.engappai.2025.110922_b19) 2018; 34
Duhme (10.1016/j.engappai.2025.110922_b7) 2021
Wu (10.1016/j.engappai.2025.110922_b36) 2015; 2015
Khokhlova (10.1016/j.engappai.2025.110922_b16) 2019; 94
10.1016/j.engappai.2025.110922_b29
Tian (10.1016/j.engappai.2025.110922_b31) 2022; 473
Fout (10.1016/j.engappai.2025.110922_b8) 2017; 30
Guo (10.1016/j.engappai.2025.110922_b11) 2021; 24
Yao (10.1016/j.engappai.2025.110922_b39) 2019; vol. 33
Chaaraoui (10.1016/j.engappai.2025.110922_b4) 2015; vol. 7
Pan (10.1016/j.engappai.2025.110922_b24) 2022; 148
Wu (10.1016/j.engappai.2025.110922_b34) 2023; 233
Bari (10.1016/j.engappai.2025.110922_b2) 2019; 7
Zeng (10.1016/j.engappai.2025.110922_b41) 2023
References_xml – volume: 8
  start-page: 167830
  year: 2020
  end-page: 167864
  ident: b26
  article-title: Latest research trends in gait analysis using wearable sensors and machine learning: A systematic review
  publication-title: Ieee Access
– volume: 25
  start-page: 1819
  year: 2022
  end-page: 1831
  ident: b32
  article-title: Joint-bone fusion graph convolutional network for semi-supervised skeleton action recognition
  publication-title: IEEE Trans. Multimed.
– reference: Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y., 2017. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7291–7299.
– reference: Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W., 2021. Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 13359–13368.
– reference: Shi, L., Zhang, Y., Cheng, J., Lu, H., 2019. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 12026–12035.
– year: 2024
  ident: b30
  article-title: Cross-spatiotemporal graph convolution networks for skeleton-based Parkinsonian gait MDS-UPDRS score estimation
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– year: 2023
  ident: b41
  article-title: Video-based quantification of gait impairments in Parkinson’s disease using skeleton-silhouette fusion convolution network
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 8
  start-page: 19196
  year: 2020
  end-page: 19207
  ident: b14
  article-title: Feature extraction using an RNN autoencoder for skeleton-based abnormal gait recognition
  publication-title: IEEE Access
– volume: vol. 32
  year: 2018
  ident: b38
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 8
  start-page: 139881
  year: 2020
  end-page: 139891
  ident: b15
  article-title: Pathological gait classification using kinect v2 and gated recurrent neural networks
  publication-title: Ieee Access
– reference: He, Y., Liu, X., Cheung, Y.-M., Peng, S.-J., Yi, J., Fan, W., 2021. Cross-graph attention enhanced multi-modal correlation learning for fine-grained image-text retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1865–1869.
– volume: 14
  start-page: 114
  year: 2024
  ident: b6
  article-title: Game-on: Graph attention network based multimodal fusion for fake news detection
  publication-title: Soc. Netw. Anal. Min.
– volume: 63
  start-page: 82
  year: 2016
  end-page: 89
  ident: b23
  article-title: A vision based proposal for classification of normal and abnormal gait using RGB camera
  publication-title: J. Biomed. Inform.
– volume: 28
  start-page: 162
  year: 2017
  end-page: 169
  ident: b43
  article-title: Convolutional neural networks for time series classification
  publication-title: J. Syst. Eng. Electron.
– volume: 233
  year: 2023
  ident: b34
  article-title: A novel graph-based hybrid deep learning of cumulative GRU and deeper GCN for recognition of abnormal gait patterns using wearable sensors
  publication-title: Expert Syst. Appl.
– volume: 148
  year: 2022
  ident: b24
  article-title: MAMF-GCN: Multi-scale adaptive multi-channel fusion deep graph convolutional network for predicting mental disorder
  publication-title: Comput. Biol. Med.
– volume: 16
  start-page: 1792
  year: 2016
  ident: b22
  article-title: Skeleton-based abnormal gait detection
  publication-title: Sensors
– volume: 34
  start-page: 1588
  year: 2021
  end-page: 1600
  ident: b13
  article-title: Graph fusion network-based multimodal learning for freezing of gait detection
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 94
  start-page: 54
  year: 2019
  end-page: 66
  ident: b16
  article-title: Normal and pathological gait classification LSTM model
  publication-title: Artif. Intell. Med.
– start-page: 542
  year: 2019
  end-page: 545
  ident: b18
  article-title: Abnormal gait recognition using 3D joint information of multiple kinects system and RNN-LSTM
  publication-title: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
– volume: 42
  start-page: 145
  year: 2015
  end-page: 151
  ident: b37
  article-title: Accuracy of the microsoft kinect™ for measuring gait parameters during treadmill walking
  publication-title: Gait Posture
– volume: vol. 34
  start-page: 1054
  year: 2020
  end-page: 1061
  ident: b35
  article-title: Graph convolutional networks with Markov random field reasoning for social spammer detection
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– reference: Wang, H., Zhao, M., Xie, X., Li, W., Guo, M., 2019. Knowledge graph convolutional networks for recommender systems. In: The World Wide Web Conference. pp. 3307–3313.
– volume: 35
  start-page: 2194
  year: 2022
  end-page: 2207
  ident: b25
  article-title: Relation-aggregated cross-graph correlation learning for fine-grained image–text retrieval
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– start-page: 36
  year: 2008
  end-page: 40
  ident: b21
  article-title: Abnormal gait detection using discrete fourier transform
  publication-title: 2008 International Conference on Multimedia and Ubiquitous Engineering
– volume: vol. 7
  start-page: 1
  year: 2015
  end-page: 6
  ident: b4
  article-title: Abnormal gait detection with RGB-D devices using joint motion history features
  publication-title: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition
– volume: 44
  start-page: 972
  year: 2011
  end-page: 978
  ident: b10
  article-title: Identifying gait asymmetry using gyroscopes—A cross-correlation and normalized symmetry index approach
  publication-title: J. Biomech.
– volume: 2015
  year: 2015
  ident: b36
  article-title: The novel quantitative technique for assessment of gait symmetry using advanced statistical learning algorithm
  publication-title: BioMed. Res. Int.
– volume: 17
  start-page: 197
  year: 2003
  end-page: 204
  ident: b27
  article-title: Local or global asymmetry in gait of people without impairments
  publication-title: Gait Posture
– start-page: 265
  year: 2021
  end-page: 281
  ident: b7
  article-title: Fusion-gcn: Multimodal action recognition using graph convolutional networks
  publication-title: DAGM German Conference on Pattern Recognition
– year: 2016
  ident: b17
  article-title: Semi-supervised classification with graph convolutional networks
– volume: 7
  start-page: 162708
  year: 2019
  end-page: 162722
  ident: b2
  article-title: Artificial neural network based gait recognition using kinect sensor
  publication-title: Ieee Access
– volume: 15
  start-page: 107
  year: 2007
  end-page: 117
  ident: b20
  article-title: Evaluation of the elderly patient with an abnormal gait
  publication-title: JAAOS- J. Am. Acad. Orthop. Surg.
– volume: 13
  start-page: 4205
  year: 2023
  ident: b40
  article-title: STJA-GCN: A multi-branch spatial–temporal joint attention graph convolutional network for abnormal gait recognition
  publication-title: Appl. Sci.
– volume: 30
  year: 2017
  ident: b8
  article-title: Protein interface prediction using graph convolutional networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 34
  start-page: 229
  year: 2018
  end-page: 241
  ident: b19
  article-title: Classification of gait anomalies from kinect
  publication-title: Vis. Comput.
– volume: 21
  start-page: 3848
  year: 2019
  end-page: 3858
  ident: b44
  article-title: T-GCN: A temporal graph convolutional network for traffic prediction
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 18
  start-page: 676
  year: 2018
  ident: b1
  article-title: An automatic gait feature extraction method for identifying gait asymmetry using wearable sensors
  publication-title: Sensors
– volume: 24
  start-page: 1583
  year: 2021
  end-page: 1594
  ident: b11
  article-title: Multi-scale sparse graph convolutional network for the assessment of Parkinsonian gait
  publication-title: IEEE Trans. Multimed.
– volume: 473
  start-page: 116
  year: 2022
  end-page: 126
  ident: b31
  article-title: Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks
  publication-title: Neurocomputing
– volume: 7
  start-page: 163180
  year: 2019
  end-page: 163190
  ident: b9
  article-title: Abnormal gait recognition algorithm based on LSTM-CNN fusion network
  publication-title: IEEE Access
– volume: vol. 33
  start-page: 7370
  year: 2019
  end-page: 7377
  ident: b39
  article-title: Graph convolutional networks for text classification
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 185
  year: 2021
  ident: b28
  article-title: Modeling spatiotemporal patterns of gait anomaly with a CNN-LSTM deep neural network
  publication-title: Expert Syst. Appl.
– volume: 19
  start-page: 4
  year: 2012
  end-page: 10
  ident: b42
  article-title: Microsoft kinect sensor and its effect
  publication-title: IEEE Multimedia
– volume: 30
  year: 2017
  ident: 10.1016/j.engappai.2025.110922_b8
  article-title: Protein interface prediction using graph convolutional networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: vol. 33
  start-page: 7370
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b39
  article-title: Graph convolutional networks for text classification
– volume: 94
  start-page: 54
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b16
  article-title: Normal and pathological gait classification LSTM model
  publication-title: Artif. Intell. Med.
  doi: 10.1016/j.artmed.2018.12.007
– volume: vol. 32
  year: 2018
  ident: 10.1016/j.engappai.2025.110922_b38
  article-title: Spatial temporal graph convolutional networks for skeleton-based action recognition
– ident: 10.1016/j.engappai.2025.110922_b12
  doi: 10.1145/3404835.3463031
– volume: 7
  start-page: 162708
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b2
  article-title: Artificial neural network based gait recognition using kinect sensor
  publication-title: Ieee Access
  doi: 10.1109/ACCESS.2019.2952065
– volume: 25
  start-page: 1819
  year: 2022
  ident: 10.1016/j.engappai.2025.110922_b32
  article-title: Joint-bone fusion graph convolutional network for semi-supervised skeleton action recognition
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2022.3168137
– volume: vol. 34
  start-page: 1054
  year: 2020
  ident: 10.1016/j.engappai.2025.110922_b35
  article-title: Graph convolutional networks with Markov random field reasoning for social spammer detection
– volume: 13
  start-page: 4205
  issue: 7
  year: 2023
  ident: 10.1016/j.engappai.2025.110922_b40
  article-title: STJA-GCN: A multi-branch spatial–temporal joint attention graph convolutional network for abnormal gait recognition
  publication-title: Appl. Sci.
  doi: 10.3390/app13074205
– volume: 21
  start-page: 3848
  issue: 9
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b44
  article-title: T-GCN: A temporal graph convolutional network for traffic prediction
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2019.2935152
– start-page: 36
  year: 2008
  ident: 10.1016/j.engappai.2025.110922_b21
  article-title: Abnormal gait detection using discrete fourier transform
– volume: 8
  start-page: 167830
  year: 2020
  ident: 10.1016/j.engappai.2025.110922_b26
  article-title: Latest research trends in gait analysis using wearable sensors and machine learning: A systematic review
  publication-title: Ieee Access
  doi: 10.1109/ACCESS.2020.3022818
– volume: 14
  start-page: 114
  issue: 1
  year: 2024
  ident: 10.1016/j.engappai.2025.110922_b6
  article-title: Game-on: Graph attention network based multimodal fusion for fake news detection
  publication-title: Soc. Netw. Anal. Min.
  doi: 10.1007/s13278-024-01271-4
– ident: 10.1016/j.engappai.2025.110922_b29
  doi: 10.1109/CVPR.2019.01230
– volume: 16
  start-page: 1792
  issue: 11
  year: 2016
  ident: 10.1016/j.engappai.2025.110922_b22
  article-title: Skeleton-based abnormal gait detection
  publication-title: Sensors
  doi: 10.3390/s16111792
– volume: 185
  year: 2021
  ident: 10.1016/j.engappai.2025.110922_b28
  article-title: Modeling spatiotemporal patterns of gait anomaly with a CNN-LSTM deep neural network
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2021.115582
– volume: 42
  start-page: 145
  issue: 2
  year: 2015
  ident: 10.1016/j.engappai.2025.110922_b37
  article-title: Accuracy of the microsoft kinect™ for measuring gait parameters during treadmill walking
  publication-title: Gait Posture
  doi: 10.1016/j.gaitpost.2015.05.002
– volume: 8
  start-page: 139881
  year: 2020
  ident: 10.1016/j.engappai.2025.110922_b15
  article-title: Pathological gait classification using kinect v2 and gated recurrent neural networks
  publication-title: Ieee Access
  doi: 10.1109/ACCESS.2020.3013029
– volume: 35
  start-page: 2194
  issue: 2
  year: 2022
  ident: 10.1016/j.engappai.2025.110922_b25
  article-title: Relation-aggregated cross-graph correlation learning for fine-grained image–text retrieval
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2022.3188569
– year: 2016
  ident: 10.1016/j.engappai.2025.110922_b17
– start-page: 265
  year: 2021
  ident: 10.1016/j.engappai.2025.110922_b7
  article-title: Fusion-gcn: Multimodal action recognition using graph convolutional networks
– volume: 17
  start-page: 197
  issue: 3
  year: 2003
  ident: 10.1016/j.engappai.2025.110922_b27
  article-title: Local or global asymmetry in gait of people without impairments
  publication-title: Gait Posture
  doi: 10.1016/S0966-6362(02)00089-9
– volume: 473
  start-page: 116
  year: 2022
  ident: 10.1016/j.engappai.2025.110922_b31
  article-title: Skeleton-based abnormal gait recognition with spatio-temporal attention enhanced gait-structural graph convolutional networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.12.004
– volume: 7
  start-page: 163180
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b9
  article-title: Abnormal gait recognition algorithm based on LSTM-CNN fusion network
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2950254
– volume: 34
  start-page: 229
  year: 2018
  ident: 10.1016/j.engappai.2025.110922_b19
  article-title: Classification of gait anomalies from kinect
  publication-title: Vis. Comput.
  doi: 10.1007/s00371-016-1330-0
– volume: 63
  start-page: 82
  year: 2016
  ident: 10.1016/j.engappai.2025.110922_b23
  article-title: A vision based proposal for classification of normal and abnormal gait using RGB camera
  publication-title: J. Biomed. Inform.
  doi: 10.1016/j.jbi.2016.08.003
– volume: 44
  start-page: 972
  issue: 5
  year: 2011
  ident: 10.1016/j.engappai.2025.110922_b10
  article-title: Identifying gait asymmetry using gyroscopes—A cross-correlation and normalized symmetry index approach
  publication-title: J. Biomech.
  doi: 10.1016/j.jbiomech.2010.12.013
– volume: 28
  start-page: 162
  issue: 1
  year: 2017
  ident: 10.1016/j.engappai.2025.110922_b43
  article-title: Convolutional neural networks for time series classification
  publication-title: J. Syst. Eng. Electron.
  doi: 10.21629/JSEE.2017.01.18
– volume: 24
  start-page: 1583
  year: 2021
  ident: 10.1016/j.engappai.2025.110922_b11
  article-title: Multi-scale sparse graph convolutional network for the assessment of Parkinsonian gait
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2021.3068609
– ident: 10.1016/j.engappai.2025.110922_b3
  doi: 10.1109/CVPR.2017.143
– ident: 10.1016/j.engappai.2025.110922_b33
  doi: 10.1145/3308558.3313417
– volume: 233
  year: 2023
  ident: 10.1016/j.engappai.2025.110922_b34
  article-title: A novel graph-based hybrid deep learning of cumulative GRU and deeper GCN for recognition of abnormal gait patterns using wearable sensors
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2023.120968
– volume: vol. 7
  start-page: 1
  year: 2015
  ident: 10.1016/j.engappai.2025.110922_b4
  article-title: Abnormal gait detection with RGB-D devices using joint motion history features
– year: 2024
  ident: 10.1016/j.engappai.2025.110922_b30
  article-title: Cross-spatiotemporal graph convolution networks for skeleton-based Parkinsonian gait MDS-UPDRS score estimation
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2024.3352004
– volume: 8
  start-page: 19196
  year: 2020
  ident: 10.1016/j.engappai.2025.110922_b14
  article-title: Feature extraction using an RNN autoencoder for skeleton-based abnormal gait recognition
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2967845
– start-page: 542
  year: 2019
  ident: 10.1016/j.engappai.2025.110922_b18
  article-title: Abnormal gait recognition using 3D joint information of multiple kinects system and RNN-LSTM
– ident: 10.1016/j.engappai.2025.110922_b5
  doi: 10.1109/ICCV48922.2021.01311
– volume: 19
  start-page: 4
  issue: 2
  year: 2012
  ident: 10.1016/j.engappai.2025.110922_b42
  article-title: Microsoft kinect sensor and its effect
  publication-title: IEEE Multimedia
  doi: 10.1109/MMUL.2012.24
– volume: 15
  start-page: 107
  issue: 2
  year: 2007
  ident: 10.1016/j.engappai.2025.110922_b20
  article-title: Evaluation of the elderly patient with an abnormal gait
  publication-title: JAAOS- J. Am. Acad. Orthop. Surg.
  doi: 10.5435/00124635-200702000-00005
– volume: 148
  year: 2022
  ident: 10.1016/j.engappai.2025.110922_b24
  article-title: MAMF-GCN: Multi-scale adaptive multi-channel fusion deep graph convolutional network for predicting mental disorder
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2022.105823
– volume: 2015
  issue: 1
  year: 2015
  ident: 10.1016/j.engappai.2025.110922_b36
  article-title: The novel quantitative technique for assessment of gait symmetry using advanced statistical learning algorithm
  publication-title: BioMed. Res. Int.
– year: 2023
  ident: 10.1016/j.engappai.2025.110922_b41
  article-title: Video-based quantification of gait impairments in Parkinson’s disease using skeleton-silhouette fusion convolution network
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 18
  start-page: 676
  issue: 2
  year: 2018
  ident: 10.1016/j.engappai.2025.110922_b1
  article-title: An automatic gait feature extraction method for identifying gait asymmetry using wearable sensors
  publication-title: Sensors
  doi: 10.3390/s18020676
– volume: 34
  start-page: 1588
  issue: 3
  year: 2021
  ident: 10.1016/j.engappai.2025.110922_b13
  article-title: Graph fusion network-based multimodal learning for freezing of gait detection
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2021.3105602
SSID ssj0003846
Score 2.4335232
Snippet Developing graph-based abnormal gait classification models with high generalization has been a challenging problem in gait analysis. In this study, a novel...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 110922
SubjectTerms Abnormal gait recognition
Adaptive learning
Graph convolutional networks
Graph fusion learning
Title A novel adaptive spatial–temporal cross-graph convolutional fusion learning network for skeleton-based abnormal gait recognition
URI https://dx.doi.org/10.1016/j.engappai.2025.110922
Volume 154
WOSCitedRecordID wos001488082300002&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: Elsevier SD Freedom Collection Journals 2021
  issn: 0952-1976
  databaseCode: AIEXJ
  dateStart: 19950201
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0003846
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlgMXylO0PLQHbpZD_MrGxxQVQVVVHArKzRp715GLtYnyUrlV_AX-Dr-mv6SzL9spFdADFysaxWs783nnkW9mCHkbM0hKNir8gIccA5Qk91MoYr-IY3zNUyECzfL9esJOT0eTSfq51_vlamE2NZNydHGRzv-rqlGGylals3dQd7MoCvAzKh2PqHY8_pPix56cbUTtAYe55gUtFWkaakdriGw3qtrTFtLXLas1-9zelippXKskmhspMfWkIYtrTuLyG1oqNXhYGUDuQS6V21t7U6hWXsNHstp2Of-266HX_ctcsxAWmq6kh4d0-oO2mX6zG50gjqeNcK1Ekwpm31t0G-FhdUNwXJmxTN38RpiohK2p8GwSlaEfpGZKTLNnJ3Fn11VdU011828GweQmzvtCTvHxoOqrS_TbE7Y7cN-wjA1f0VHhzjO3TqbWycw698huyJIU99Td8aejyXHjCUQjUyjmnqBToX77Hd3uHHUcnrNH5KGNVOjYIOwx6Qn5hOzZqIVam7BEkRsM4mRPyY8x1RikDoPUYvDq8qdDH-2gj26hjxr0UYc-atFHEX10G33UoY8q9NEO-p6RLx-Ozt5_9O2wD7_AIH7lM9wrIihyKCEp4gFXfGFWiojBsMQvxDzIgQ2HJQOmip95EQAvh1AGfCC4asP3nOzImRQvCEUbI9gAWKiigTRK8hJjZowUeJQLBnGwT965Xzmbm54u2Z81vE9Sp4zMeqbG48wQZ3859-DOV3tJHrQvwiuys1qsxWtyv9isquXijQXZNc1fvIM
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+novel+adaptive+spatial%E2%80%93temporal+cross-graph+convolutional+fusion+learning+network+for+skeleton-based+abnormal+gait+recognition&rft.jtitle=Engineering+applications+of+artificial+intelligence&rft.au=Wang%2C+Liang&rft.au=Wu%2C+Xiaoyan&rft.au=Wu%2C+Bin&rft.au=Wu%2C+Jianning&rft.date=2025-08-15&rft.issn=0952-1976&rft.volume=154&rft.spage=110922&rft_id=info:doi/10.1016%2Fj.engappai.2025.110922&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_engappai_2025_110922
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0952-1976&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0952-1976&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0952-1976&client=summon