Cargando…

sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm

The surface electromyography (sEMG) signal is widely used as a control source of the upper limb exoskeleton rehabilitation robot. However, the traditional way of controlling the exoskeleton robot by the sEMG signal requires one to specially extract and calculate for complex sEMG features. Moreover,...

Descripción completa

Detalles Bibliográficos
Autores principales: Bu, Dongdong, Guo, Shuxiang, Li, He
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8778025/
https://www.ncbi.nlm.nih.gov/pubmed/35054457
http://dx.doi.org/10.3390/life12010064
_version_ 1784637217260437504
author Bu, Dongdong
Guo, Shuxiang
Li, He
author_facet Bu, Dongdong
Guo, Shuxiang
Li, He
author_sort Bu, Dongdong
collection PubMed
description The surface electromyography (sEMG) signal is widely used as a control source of the upper limb exoskeleton rehabilitation robot. However, the traditional way of controlling the exoskeleton robot by the sEMG signal requires one to specially extract and calculate for complex sEMG features. Moreover, due to the huge amount of calculation and individualized difference, the real-time control of the exoskeleton robot cannot be realized. Therefore, this paper proposes a novel method using an improved detection algorithm to recognize limb joint motion and detect joint angle based on sEMG images, aiming to obtain a high-security and fast-processing action recognition strategy. In this paper, MobileNetV2 combined the Ghost module as the feature extraction network to obtain the pretraining model. Then, the target detection network Yolo-V4 was used to estimate the six movement categories of the upper limb joints and to predict the joint movement angles. The experimental results showed that the proposed motion recognition methods were available. Every 100 pictures can be accurately identified in approximately 78 pictures, and the processing speed of every single picture on the PC side was 17.97 ms. For the train data, the mAP@0.5 could reach 82.3%, and mAP@0.5–0.95 could reach 0.42; for the verification data, the average recognition accuracy could reach 80.7%.
format Online
Article
Text
id pubmed-8778025
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87780252022-01-22 sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm Bu, Dongdong Guo, Shuxiang Li, He Life (Basel) Article The surface electromyography (sEMG) signal is widely used as a control source of the upper limb exoskeleton rehabilitation robot. However, the traditional way of controlling the exoskeleton robot by the sEMG signal requires one to specially extract and calculate for complex sEMG features. Moreover, due to the huge amount of calculation and individualized difference, the real-time control of the exoskeleton robot cannot be realized. Therefore, this paper proposes a novel method using an improved detection algorithm to recognize limb joint motion and detect joint angle based on sEMG images, aiming to obtain a high-security and fast-processing action recognition strategy. In this paper, MobileNetV2 combined the Ghost module as the feature extraction network to obtain the pretraining model. Then, the target detection network Yolo-V4 was used to estimate the six movement categories of the upper limb joints and to predict the joint movement angles. The experimental results showed that the proposed motion recognition methods were available. Every 100 pictures can be accurately identified in approximately 78 pictures, and the processing speed of every single picture on the PC side was 17.97 ms. For the train data, the mAP@0.5 could reach 82.3%, and mAP@0.5–0.95 could reach 0.42; for the verification data, the average recognition accuracy could reach 80.7%. MDPI 2022-01-03 /pmc/articles/PMC8778025/ /pubmed/35054457 http://dx.doi.org/10.3390/life12010064 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Bu, Dongdong
Guo, Shuxiang
Li, He
sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title_full sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title_fullStr sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title_full_unstemmed sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title_short sEMG-Based Motion Recognition of Upper Limb Rehabilitation Using the Improved Yolo-v4 Algorithm
title_sort semg-based motion recognition of upper limb rehabilitation using the improved yolo-v4 algorithm
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8778025/
https://www.ncbi.nlm.nih.gov/pubmed/35054457
http://dx.doi.org/10.3390/life12010064
work_keys_str_mv AT budongdong semgbasedmotionrecognitionofupperlimbrehabilitationusingtheimprovedyolov4algorithm
AT guoshuxiang semgbasedmotionrecognitionofupperlimbrehabilitationusingtheimprovedyolov4algorithm
AT lihe semgbasedmotionrecognitionofupperlimbrehabilitationusingtheimprovedyolov4algorithm