Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke

Kinematic evaluation of gait is critical for biomechanical analysis and disease diagnosis. Stroke survivors, due to unilateral motor impairments, often exhibit asymmetric gait patterns, significantly altering lower limb joint kinematics. Accurate measurement of lower limb joint angles enables therap...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Guo, Yusuke Sekiguchi, Wen Zeng, Satoru Ebihara, Dai Owaki, Mitsuhiro Hayashibe
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11044411/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850163485107814400
author Yan Guo
Yusuke Sekiguchi
Wen Zeng
Satoru Ebihara
Dai Owaki
Mitsuhiro Hayashibe
author_facet Yan Guo
Yusuke Sekiguchi
Wen Zeng
Satoru Ebihara
Dai Owaki
Mitsuhiro Hayashibe
author_sort Yan Guo
collection DOAJ
description Kinematic evaluation of gait is critical for biomechanical analysis and disease diagnosis. Stroke survivors, due to unilateral motor impairments, often exhibit asymmetric gait patterns, significantly altering lower limb joint kinematics. Accurate measurement of lower limb joint angles enables therapists to assess the functional status of stroke patients, thereby promoting the rehabilitation process. Although optical motion capture systems provide precise measurements, their use is constrained to laboratory and clinical settings. Inertial measurement units (IMUs) offer a promising wearable alternative for monitoring gait during daily life. However, comprehensive segment motion tracking typically requires multiple IMUs, leading to inconvenience and interference with daily activities. This study proposes a physics-informed learning framework utilizing a temporal convolutional network (TCN) for lower-limb kinematics prediction, significantly reducing sensor count to only two IMUs. Geometric physical constraints derived from IMU measurements and human gait modeling are integrated into the neural network during training. Validation on six healthy subjects and seventeen chronic stroke patients indicates the effectiveness of this proposed framework, achieving comparable accuracy with only two IMUs as with four or more IMUs, highlighting its potential for practical rehabilitation applications.
format Article
id doaj-art-fac03c7291024976a6f5406cf2e3d79c
institution OA Journals
issn 1534-4320
1558-0210
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-fac03c7291024976a6f5406cf2e3d79c2025-08-20T02:22:15ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01332475248610.1109/TNSRE.2025.358135211044411Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic StrokeYan Guo0https://orcid.org/0009-0009-6978-7300Yusuke Sekiguchi1Wen Zeng2Satoru Ebihara3Dai Owaki4https://orcid.org/0000-0003-1217-3892Mitsuhiro Hayashibe5https://orcid.org/0000-0001-6179-5706Department of Robotics, Graduate School of Engineering, Tohoku University, Sendai, JapanDepartment of Rehabilitation Medicine, Graduate School of Medicine, Tohoku University Hospital, Sendai, JapanDepartment of Rehabilitation Medicine, Graduate School of Medicine, Tohoku University Hospital, Sendai, JapanDepartment of Rehabilitation Medicine, Graduate School of Medicine, Tohoku University Hospital, Sendai, JapanDepartment of Robotics, Graduate School of Engineering, Tohoku University, Sendai, JapanDepartment of Robotics, Graduate School of Engineering, Tohoku University, Sendai, JapanKinematic evaluation of gait is critical for biomechanical analysis and disease diagnosis. Stroke survivors, due to unilateral motor impairments, often exhibit asymmetric gait patterns, significantly altering lower limb joint kinematics. Accurate measurement of lower limb joint angles enables therapists to assess the functional status of stroke patients, thereby promoting the rehabilitation process. Although optical motion capture systems provide precise measurements, their use is constrained to laboratory and clinical settings. Inertial measurement units (IMUs) offer a promising wearable alternative for monitoring gait during daily life. However, comprehensive segment motion tracking typically requires multiple IMUs, leading to inconvenience and interference with daily activities. This study proposes a physics-informed learning framework utilizing a temporal convolutional network (TCN) for lower-limb kinematics prediction, significantly reducing sensor count to only two IMUs. Geometric physical constraints derived from IMU measurements and human gait modeling are integrated into the neural network during training. Validation on six healthy subjects and seventeen chronic stroke patients indicates the effectiveness of this proposed framework, achieving comparable accuracy with only two IMUs as with four or more IMUs, highlighting its potential for practical rehabilitation applications.https://ieeexplore.ieee.org/document/11044411/Gaitphysics informed learningkinematicssparse sensorschronic stroke
spellingShingle Yan Guo
Yusuke Sekiguchi
Wen Zeng
Satoru Ebihara
Dai Owaki
Mitsuhiro Hayashibe
Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Gait
physics informed learning
kinematics
sparse sensors
chronic stroke
title Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
title_full Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
title_fullStr Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
title_full_unstemmed Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
title_short Physics-Informed Learning Framework for Lower Limb Kinematic Prediction With Sparse Sensors and Its Application in Chronic Stroke
title_sort physics informed learning framework for lower limb kinematic prediction with sparse sensors and its application in chronic stroke
topic Gait
physics informed learning
kinematics
sparse sensors
chronic stroke
url https://ieeexplore.ieee.org/document/11044411/
work_keys_str_mv AT yanguo physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke
AT yusukesekiguchi physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke
AT wenzeng physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke
AT satoruebihara physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke
AT daiowaki physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke
AT mitsuhirohayashibe physicsinformedlearningframeworkforlowerlimbkinematicpredictionwithsparsesensorsanditsapplicationinchronicstroke