Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework

Lateral walking exercise is beneficial for the hip abductor enhancement. Accurate gait recognition and continuous hip joint angle prediction are essential for the control of exoskeletons. We propose a dual-task learning framework, the “Twin Brother” model, which fuses convolutional neural network (C...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingxiang Luo, Meng Yin, Jinke Li, Ying Li, Worawarit Kobsiriphat, Hongliu Yu, Tiantian Xu, Xinyu Wu, Wujing Cao
Format: Article
Language:English
Published: American Association for the Advancement of Science (AAAS) 2025-01-01
Series:Cyborg and Bionic Systems
Online Access:https://spj.science.org/doi/10.34133/cbsystems.0250
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849316037984518144
author Mingxiang Luo
Meng Yin
Jinke Li
Ying Li
Worawarit Kobsiriphat
Hongliu Yu
Tiantian Xu
Xinyu Wu
Wujing Cao
author_facet Mingxiang Luo
Meng Yin
Jinke Li
Ying Li
Worawarit Kobsiriphat
Hongliu Yu
Tiantian Xu
Xinyu Wu
Wujing Cao
author_sort Mingxiang Luo
collection DOAJ
description Lateral walking exercise is beneficial for the hip abductor enhancement. Accurate gait recognition and continuous hip joint angle prediction are essential for the control of exoskeletons. We propose a dual-task learning framework, the “Twin Brother” model, which fuses convolutional neural network (CNN), long short-term memory (LSTM), neural networks (NNs), and the squeezing-elicited attention mechanism to classify the lateral gait stage and estimate the hip angle from electromyography (EMG) signals. The EMG signals of 6 muscles from 10 subjects during lateral walking were collected. Four gait phases were recognized, and the hip angles of both legs were continuously estimated. The sliding window length of 250 ms and the sliding increment of 3 ms were determined by the requirements of response time and recognition accuracy of the real-time system. We compared the performance of CNN-LSTM, CNN, LSTM, support vector machine, NN, K-nearest neighbor, and the “Twin Brother” models. The “Twin Brother” model achieved a recognition accuracy (mean ± SD) of 98.81% ± 0.14%. The model’s predicted root mean square error (RMSE) for the left and right hip angles are 0.9183° ± 0.024° and 1.0511° ± 0.027°, respectively, where the R2 are 0.9853 ± 0.006 and 0.9808 ± 0.008. The accuracy of recognition and estimation are both better than comparative models. For gait phase percentage prediction, RMSE and R2 predicted by the model can reach 0.152° ± 0.014° and 0.986 ± 0.011, respectively. These results demonstrate that the method can be applied to lateral walking gait recognition and hip joint angle prediction.
format Article
id doaj-art-0da7c146f7c7423d8eb8a1326a74c8ba
institution Kabale University
issn 2692-7632
language English
publishDate 2025-01-01
publisher American Association for the Advancement of Science (AAAS)
record_format Article
series Cyborg and Bionic Systems
spelling doaj-art-0da7c146f7c7423d8eb8a1326a74c8ba2025-08-20T03:51:59ZengAmerican Association for the Advancement of Science (AAAS)Cyborg and Bionic Systems2692-76322025-01-01610.34133/cbsystems.0250Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning FrameworkMingxiang Luo0Meng Yin1Jinke Li2Ying Li3Worawarit Kobsiriphat4Hongliu Yu5Tiantian Xu6Xinyu Wu7Wujing Cao8Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Department of Mechanical and Electrical Engineering, Shenzhen Polytechnic University, Shenzhen, China.National Metal and Materials Technology Center, National Science and Technology Development Agency of Thailand, Khlong Nueng, Thailand.University of Shanghai for Science and Technology, Shanghai, China.Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Guangdong Provincial Key Lab of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.Lateral walking exercise is beneficial for the hip abductor enhancement. Accurate gait recognition and continuous hip joint angle prediction are essential for the control of exoskeletons. We propose a dual-task learning framework, the “Twin Brother” model, which fuses convolutional neural network (CNN), long short-term memory (LSTM), neural networks (NNs), and the squeezing-elicited attention mechanism to classify the lateral gait stage and estimate the hip angle from electromyography (EMG) signals. The EMG signals of 6 muscles from 10 subjects during lateral walking were collected. Four gait phases were recognized, and the hip angles of both legs were continuously estimated. The sliding window length of 250 ms and the sliding increment of 3 ms were determined by the requirements of response time and recognition accuracy of the real-time system. We compared the performance of CNN-LSTM, CNN, LSTM, support vector machine, NN, K-nearest neighbor, and the “Twin Brother” models. The “Twin Brother” model achieved a recognition accuracy (mean ± SD) of 98.81% ± 0.14%. The model’s predicted root mean square error (RMSE) for the left and right hip angles are 0.9183° ± 0.024° and 1.0511° ± 0.027°, respectively, where the R2 are 0.9853 ± 0.006 and 0.9808 ± 0.008. The accuracy of recognition and estimation are both better than comparative models. For gait phase percentage prediction, RMSE and R2 predicted by the model can reach 0.152° ± 0.014° and 0.986 ± 0.011, respectively. These results demonstrate that the method can be applied to lateral walking gait recognition and hip joint angle prediction.https://spj.science.org/doi/10.34133/cbsystems.0250
spellingShingle Mingxiang Luo
Meng Yin
Jinke Li
Ying Li
Worawarit Kobsiriphat
Hongliu Yu
Tiantian Xu
Xinyu Wu
Wujing Cao
Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
Cyborg and Bionic Systems
title Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
title_full Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
title_fullStr Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
title_full_unstemmed Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
title_short Lateral Walking Gait Recognition and Hip Angle Prediction Using a Dual-Task Learning Framework
title_sort lateral walking gait recognition and hip angle prediction using a dual task learning framework
url https://spj.science.org/doi/10.34133/cbsystems.0250
work_keys_str_mv AT mingxiangluo lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT mengyin lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT jinkeli lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT yingli lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT worawaritkobsiriphat lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT hongliuyu lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT tiantianxu lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT xinyuwu lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework
AT wujingcao lateralwalkinggaitrecognitionandhipanglepredictionusingadualtasklearningframework