Sub-phase division method for gait.

<div><p>The precise recognition of human lower limb movements based on wearable sensors is very important for human-computer interaction. However, the existing methods tend to ignore the dynamic spatial information in the process of executing human lower limb movements, leading to challe...

Full description

Saved in:
Bibliographic Details
Main Author: Fo Hu (22394685) (author)
Other Authors: Qinxu Zheng (22394688) (author), Xuanjie Ye (17746134) (author), Zukang Qiao (22394691) (author), Junlong Xiong (12701535) (author), Hongsheng Chang (22394694) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852015934942740480
author Fo Hu (22394685)
author2 Qinxu Zheng (22394688)
Xuanjie Ye (17746134)
Zukang Qiao (22394691)
Junlong Xiong (12701535)
Hongsheng Chang (22394694)
author2_role author
author
author
author
author
author_facet Fo Hu (22394685)
Qinxu Zheng (22394688)
Xuanjie Ye (17746134)
Zukang Qiao (22394691)
Junlong Xiong (12701535)
Hongsheng Chang (22394694)
author_role author
dc.creator.none.fl_str_mv Fo Hu (22394685)
Qinxu Zheng (22394688)
Xuanjie Ye (17746134)
Zukang Qiao (22394691)
Junlong Xiong (12701535)
Hongsheng Chang (22394694)
dc.date.none.fl_str_mv 2025-10-08T17:39:27Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0332947.g003
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Sub-phase_division_method_for_gait_/30309528
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Sociology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
reduced decoding accuracy
predicted gait movements
mine meaningful spatial
inertial measurement unit
highly discriminative power
dynamic spatial information
different skeleton nodes
body partitioning strategy
based skeleton graph
temporal feature representations
existing methods tend
scale convolutional sub
temporal convolutional module
temporal features
mainstream methods
xlink ">
results demonstrate
related deep
precise recognition
limited robustness
fused spatio
extensive comparison
computer interaction
classification module
attention sub
ablation studies
dc.title.none.fl_str_mv Sub-phase division method for gait.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <div><p>The precise recognition of human lower limb movements based on wearable sensors is very important for human-computer interaction. However, the existing methods tend to ignore the dynamic spatial information in the process of executing human lower limb movements, leading to challenges such as reduced decoding accuracy and limited robustness. In this paper, we construct skeleton graph data based on inertial measurement unit (IMU) sensors. Also, a two-branch deep learning model, termed TCNN-MGCHN, is proposed to mine meaningful spatial and temporal feature representations from IMU-based skeleton graph data. Firstly, a temporal convolutional module (consisting of a multi-scale convolutional sub-module and an attention sub-module) is developed to extract temporal feature information with highly discriminative power. Secondly, a multi-scale graph convolutional module and a spatial graph edges’ importance weight assignment method based on body partitioning strategy are proposed to obtain intrinsic spatial feature information between different skeleton nodes. Finally, the fused spatio-temporal features are passed into the classification module to obtain the predicted gait movements and sub-phases. Extensive comparison and ablation studies are conducted on our self-constructed human lower limb movement dataset. The results demonstrate that TCNN-MGCHN delivers superior classification performance compared to the mainstream methods. This study can provide a benchmark for IMU-based human lower limb movement recognition and related deep-learning modeling works.</p></div>
eu_rights_str_mv openAccess
id Manara_7cd8aa5aa5840bb2ab91be2db1d6cbdb
identifier_str_mv 10.1371/journal.pone.0332947.g003
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30309528
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Sub-phase division method for gait.Fo Hu (22394685)Qinxu Zheng (22394688)Xuanjie Ye (17746134)Zukang Qiao (22394691)Junlong Xiong (12701535)Hongsheng Chang (22394694)SociologySpace ScienceEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedreduced decoding accuracypredicted gait movementsmine meaningful spatialinertial measurement unithighly discriminative powerdynamic spatial informationdifferent skeleton nodesbody partitioning strategybased skeleton graphtemporal feature representationsexisting methods tendscale convolutional subtemporal convolutional moduletemporal featuresmainstream methodsxlink ">results demonstraterelated deepprecise recognitionlimited robustnessfused spatioextensive comparisoncomputer interactionclassification moduleattention subablation studies<div><p>The precise recognition of human lower limb movements based on wearable sensors is very important for human-computer interaction. However, the existing methods tend to ignore the dynamic spatial information in the process of executing human lower limb movements, leading to challenges such as reduced decoding accuracy and limited robustness. In this paper, we construct skeleton graph data based on inertial measurement unit (IMU) sensors. Also, a two-branch deep learning model, termed TCNN-MGCHN, is proposed to mine meaningful spatial and temporal feature representations from IMU-based skeleton graph data. Firstly, a temporal convolutional module (consisting of a multi-scale convolutional sub-module and an attention sub-module) is developed to extract temporal feature information with highly discriminative power. Secondly, a multi-scale graph convolutional module and a spatial graph edges’ importance weight assignment method based on body partitioning strategy are proposed to obtain intrinsic spatial feature information between different skeleton nodes. Finally, the fused spatio-temporal features are passed into the classification module to obtain the predicted gait movements and sub-phases. Extensive comparison and ablation studies are conducted on our self-constructed human lower limb movement dataset. The results demonstrate that TCNN-MGCHN delivers superior classification performance compared to the mainstream methods. This study can provide a benchmark for IMU-based human lower limb movement recognition and related deep-learning modeling works.</p></div>2025-10-08T17:39:27ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0332947.g003https://figshare.com/articles/figure/Sub-phase_division_method_for_gait_/30309528CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/303095282025-10-08T17:39:27Z
spellingShingle Sub-phase division method for gait.
Fo Hu (22394685)
Sociology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
reduced decoding accuracy
predicted gait movements
mine meaningful spatial
inertial measurement unit
highly discriminative power
dynamic spatial information
different skeleton nodes
body partitioning strategy
based skeleton graph
temporal feature representations
existing methods tend
scale convolutional sub
temporal convolutional module
temporal features
mainstream methods
xlink ">
results demonstrate
related deep
precise recognition
limited robustness
fused spatio
extensive comparison
computer interaction
classification module
attention sub
ablation studies
status_str publishedVersion
title Sub-phase division method for gait.
title_full Sub-phase division method for gait.
title_fullStr Sub-phase division method for gait.
title_full_unstemmed Sub-phase division method for gait.
title_short Sub-phase division method for gait.
title_sort Sub-phase division method for gait.
topic Sociology
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
reduced decoding accuracy
predicted gait movements
mine meaningful spatial
inertial measurement unit
highly discriminative power
dynamic spatial information
different skeleton nodes
body partitioning strategy
based skeleton graph
temporal feature representations
existing methods tend
scale convolutional sub
temporal convolutional module
temporal features
mainstream methods
xlink ">
results demonstrate
related deep
precise recognition
limited robustness
fused spatio
extensive comparison
computer interaction
classification module
attention sub
ablation studies