Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm

A human gait recognition method based on the PSO-ELM algorithm is proposed in order to achieve coordinated movement between humans and lower limb exoskeletons. Ground reaction force (GRF) from the foot, and motion capture data (MCD) from two joints were collected through the exoskeleton device. The...

Full description

Saved in:
Bibliographic Details
Main Authors: Ting Liu, Kai Liu, Wuyi Luo, Jiange Kou, Haoran Zhan, Guangkai Yu, Qing Guo, Yan Shi
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/14/3/120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205515706007552
author Ting Liu
Kai Liu
Wuyi Luo
Jiange Kou
Haoran Zhan
Guangkai Yu
Qing Guo
Yan Shi
author_facet Ting Liu
Kai Liu
Wuyi Luo
Jiange Kou
Haoran Zhan
Guangkai Yu
Qing Guo
Yan Shi
author_sort Ting Liu
collection DOAJ
description A human gait recognition method based on the PSO-ELM algorithm is proposed in order to achieve coordinated movement between humans and lower limb exoskeletons. Ground reaction force (GRF) from the foot, and motion capture data (MCD) from two joints were collected through the exoskeleton device. The sample data were obtained through multiple experiments in different action scenarios, including standing still, walking on the flat, climbing up and down stairs, traveling up and down slopes, in addition to squatting down and standing up. The algorithm utilizes short-term posture data to recognize different posture movement patterns, with two advantages: (1) A user-friendly wearable device was constructed based on multi-source sensors distributed throughout the body, addressing multiple subjects with varying weights and heights, while being cost-effective and reliably and easily collecting data. (2) The PSO-ELM algorithm identifies key features of gait data, achieving a higher recognition accuracy than other advanced recognition methods, especially during arbitrary gait transition duration.
format Article
id doaj-art-f63a2516f04f450a8cf32636e18d2dff
institution OA Journals
issn 2076-0825
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-f63a2516f04f450a8cf32636e18d2dff2025-08-20T02:11:04ZengMDPI AGActuators2076-08252025-03-0114312010.3390/act14030120Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine AlgorithmTing Liu0Kai Liu1Wuyi Luo2Jiange Kou3Haoran Zhan4Guangkai Yu5Qing Guo6Yan Shi7State Key Laboratory of Power Grid Environmental Protection, China Electric Power Research Institute, Wuhan 430074, ChinaState Key Laboratory of Power Grid Environmental Protection, China Electric Power Research Institute, Wuhan 430074, ChinaSchool of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing 100191, ChinaSchool of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaState Key Laboratory of Power Grid Environmental Protection, China Electric Power Research Institute, Wuhan 430074, ChinaSchool of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Automation Science and Electrical Engineering, Beihang University (BUAA), Beijing 100191, ChinaA human gait recognition method based on the PSO-ELM algorithm is proposed in order to achieve coordinated movement between humans and lower limb exoskeletons. Ground reaction force (GRF) from the foot, and motion capture data (MCD) from two joints were collected through the exoskeleton device. The sample data were obtained through multiple experiments in different action scenarios, including standing still, walking on the flat, climbing up and down stairs, traveling up and down slopes, in addition to squatting down and standing up. The algorithm utilizes short-term posture data to recognize different posture movement patterns, with two advantages: (1) A user-friendly wearable device was constructed based on multi-source sensors distributed throughout the body, addressing multiple subjects with varying weights and heights, while being cost-effective and reliably and easily collecting data. (2) The PSO-ELM algorithm identifies key features of gait data, achieving a higher recognition accuracy than other advanced recognition methods, especially during arbitrary gait transition duration.https://www.mdpi.com/2076-0825/14/3/120cost-effective gait acquisition devicelower limb exoskeletongait recognitionmachine learningPSO-ELM algorithm
spellingShingle Ting Liu
Kai Liu
Wuyi Luo
Jiange Kou
Haoran Zhan
Guangkai Yu
Qing Guo
Yan Shi
Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
Actuators
cost-effective gait acquisition device
lower limb exoskeleton
gait recognition
machine learning
PSO-ELM algorithm
title Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
title_full Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
title_fullStr Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
title_full_unstemmed Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
title_short Motion Gait Recognition of Lower Limb Exoskeleton Based on Particle Swarm Optimization-Based Extreme Learning Machine Algorithm
title_sort motion gait recognition of lower limb exoskeleton based on particle swarm optimization based extreme learning machine algorithm
topic cost-effective gait acquisition device
lower limb exoskeleton
gait recognition
machine learning
PSO-ELM algorithm
url https://www.mdpi.com/2076-0825/14/3/120
work_keys_str_mv AT tingliu motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT kailiu motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT wuyiluo motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT jiangekou motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT haoranzhan motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT guangkaiyu motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT qingguo motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm
AT yanshi motiongaitrecognitionoflowerlimbexoskeletonbasedonparticleswarmoptimizationbasedextremelearningmachinealgorithm