Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals

In the human–exoskeleton interaction process, accurately recognizing gait phases is crucial for effectively assessing the assistance provided by the exoskeleton. However, due to the similarity in muscle activation patterns between adjacent gait phases, the recognition accuracy is often low, which ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Xin Shi, Xiaheng Zhang, Pengjie Qin, Liangwen Huang, Yaqin Zhu, Zixiang Yang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Biosensors
Subjects:
Online Access:https://www.mdpi.com/2079-6374/15/5/305
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327659770707968
author Xin Shi
Xiaheng Zhang
Pengjie Qin
Liangwen Huang
Yaqin Zhu
Zixiang Yang
author_facet Xin Shi
Xiaheng Zhang
Pengjie Qin
Liangwen Huang
Yaqin Zhu
Zixiang Yang
author_sort Xin Shi
collection DOAJ
description In the human–exoskeleton interaction process, accurately recognizing gait phases is crucial for effectively assessing the assistance provided by the exoskeleton. However, due to the similarity in muscle activation patterns between adjacent gait phases, the recognition accuracy is often low, which can easily lead to confusion in surface electromyography (sEMG) feature extraction. This paper proposes a real-time recognition method based on multi-scale fuzzy approximate root mean entropy (MFAREn) and an Efficient Multi-Scale Attention Convolutional Neural Network (EMACNN), building upon the concept of fuzzy approximate entropy. MFAREn is used to extract the dynamic complexity and energy intensity features of sEMG signals, serving as the input matrix for EMACNN to achieve fast and accurate gait phase recognition. This study collected sEMG signals from 10 subjects performing continuous lower limb gait movements in five common motion scenarios for experimental validation. The results show that the proposed method achieves an average recognition accuracy of 95.72%, outperforming the other comparison methods. The method proposed in this paper is significantly different compared to other methods (<i>p</i> < 0.001). Notably, the recognition accuracy for walking in level walking, stairs ascending, and ramp ascending exceeds 95.5%. This method demonstrates a high recognition accuracy, enabling sEMG-based gait phase recognition and meeting the requirements for effective human–exoskeleton interaction.
format Article
id doaj-art-c4fec3d51f4a4b35a8fd425361a3130d
institution Kabale University
issn 2079-6374
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Biosensors
spelling doaj-art-c4fec3d51f4a4b35a8fd425361a3130d2025-08-20T03:47:48ZengMDPI AGBiosensors2079-63742025-05-0115530510.3390/bios15050305Gait Phase Recognition in Multi-Task Scenarios Based on sEMG SignalsXin Shi0Xiaheng Zhang1Pengjie Qin2Liangwen Huang3Yaqin Zhu4Zixiang Yang5School of Automation, Chongqing University, Chongqing 400044, ChinaSchool of Automation, Chongqing University, Chongqing 400044, ChinaShenzhen Insitute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaSchool of Automation, Chongqing University, Chongqing 400044, ChinaSchool of Automation, Chongqing University, Chongqing 400044, ChinaSchool of Automation, Chongqing University, Chongqing 400044, ChinaIn the human–exoskeleton interaction process, accurately recognizing gait phases is crucial for effectively assessing the assistance provided by the exoskeleton. However, due to the similarity in muscle activation patterns between adjacent gait phases, the recognition accuracy is often low, which can easily lead to confusion in surface electromyography (sEMG) feature extraction. This paper proposes a real-time recognition method based on multi-scale fuzzy approximate root mean entropy (MFAREn) and an Efficient Multi-Scale Attention Convolutional Neural Network (EMACNN), building upon the concept of fuzzy approximate entropy. MFAREn is used to extract the dynamic complexity and energy intensity features of sEMG signals, serving as the input matrix for EMACNN to achieve fast and accurate gait phase recognition. This study collected sEMG signals from 10 subjects performing continuous lower limb gait movements in five common motion scenarios for experimental validation. The results show that the proposed method achieves an average recognition accuracy of 95.72%, outperforming the other comparison methods. The method proposed in this paper is significantly different compared to other methods (<i>p</i> < 0.001). Notably, the recognition accuracy for walking in level walking, stairs ascending, and ramp ascending exceeds 95.5%. This method demonstrates a high recognition accuracy, enabling sEMG-based gait phase recognition and meeting the requirements for effective human–exoskeleton interaction.https://www.mdpi.com/2079-6374/15/5/305gait phase recognitionsEMGfApEnfeature extractionCNN
spellingShingle Xin Shi
Xiaheng Zhang
Pengjie Qin
Liangwen Huang
Yaqin Zhu
Zixiang Yang
Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
Biosensors
gait phase recognition
sEMG
fApEn
feature extraction
CNN
title Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
title_full Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
title_fullStr Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
title_full_unstemmed Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
title_short Gait Phase Recognition in Multi-Task Scenarios Based on sEMG Signals
title_sort gait phase recognition in multi task scenarios based on semg signals
topic gait phase recognition
sEMG
fApEn
feature extraction
CNN
url https://www.mdpi.com/2079-6374/15/5/305
work_keys_str_mv AT xinshi gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals
AT xiahengzhang gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals
AT pengjieqin gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals
AT liangwenhuang gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals
AT yaqinzhu gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals
AT zixiangyang gaitphaserecognitioninmultitaskscenariosbasedonsemgsignals