Cargando…

Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning

Electromyography (EMG) pattern recognition is one of the widely used methods to control the rehabilitation robots and prostheses. However, the changes in the distribution of EMG data due to electrodes shifting results in classification decline, which hinders its clinical application in repeated uses...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Qi, Zhang, Anyuan, Li, Zhenlan, Wu, Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8236575/
https://www.ncbi.nlm.nih.gov/pubmed/34194311
http://dx.doi.org/10.3389/fnbot.2021.699174
_version_ 1783714566656491520
author Li, Qi
Zhang, Anyuan
Li, Zhenlan
Wu, Yan
author_facet Li, Qi
Zhang, Anyuan
Li, Zhenlan
Wu, Yan
author_sort Li, Qi
collection PubMed
description Electromyography (EMG) pattern recognition is one of the widely used methods to control the rehabilitation robots and prostheses. However, the changes in the distribution of EMG data due to electrodes shifting results in classification decline, which hinders its clinical application in repeated uses. Adaptive learning can solve this problem but takes additional time. To address this, an efficient scheme is developed by comparing the performance of 12 combinations of three feature selection methods [no feature selection (NFS), sequential forward search (SFS), and particle swarm optimization (PSO)] and four classification methods [non-adaptive support vector machine (N-SVM), incremental SVM (I-SVM), SVM based on TrAdaBoost (T-SVM), and I-SVM based on TrAdaBoost (TI-SVM)] in the classification of EMG data of 12 subjects for 5 consecutive days. Our results showed that TI-SVM achieved the highest classification accuracy among the classification methods (p < 0.05). The SFS method achieved the same classification accuracy as that of the scheme trained with the feature vectors selected by the NFS method (p = 0.999) while achieving a lower training time than that of TI-SVM combined with the NFS method (p = 0.043). Although the PSO method outperformed the NFS and SFS methods by achieving reduced training and response times (p < 0.05), the PSO method achieved a considerably lower classification accuracy than that of the scheme trained with the feature vectors selected by the NFS (p = 0.001) or SFS (p = 0.001) method. Furthermore, TI-SVM combined with the SFS method outperformed the CNN method with fine-tuning in classification accuracy on a small data set (p = 0.001). The results indicate that TI-SVM combined with the SFS method is suitable for improving the performance of EMG pattern recognition in repeated uses.
format Online
Article
Text
id pubmed-8236575
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-82365752021-06-29 Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning Li, Qi Zhang, Anyuan Li, Zhenlan Wu, Yan Front Neurorobot Neuroscience Electromyography (EMG) pattern recognition is one of the widely used methods to control the rehabilitation robots and prostheses. However, the changes in the distribution of EMG data due to electrodes shifting results in classification decline, which hinders its clinical application in repeated uses. Adaptive learning can solve this problem but takes additional time. To address this, an efficient scheme is developed by comparing the performance of 12 combinations of three feature selection methods [no feature selection (NFS), sequential forward search (SFS), and particle swarm optimization (PSO)] and four classification methods [non-adaptive support vector machine (N-SVM), incremental SVM (I-SVM), SVM based on TrAdaBoost (T-SVM), and I-SVM based on TrAdaBoost (TI-SVM)] in the classification of EMG data of 12 subjects for 5 consecutive days. Our results showed that TI-SVM achieved the highest classification accuracy among the classification methods (p < 0.05). The SFS method achieved the same classification accuracy as that of the scheme trained with the feature vectors selected by the NFS method (p = 0.999) while achieving a lower training time than that of TI-SVM combined with the NFS method (p = 0.043). Although the PSO method outperformed the NFS and SFS methods by achieving reduced training and response times (p < 0.05), the PSO method achieved a considerably lower classification accuracy than that of the scheme trained with the feature vectors selected by the NFS (p = 0.001) or SFS (p = 0.001) method. Furthermore, TI-SVM combined with the SFS method outperformed the CNN method with fine-tuning in classification accuracy on a small data set (p = 0.001). The results indicate that TI-SVM combined with the SFS method is suitable for improving the performance of EMG pattern recognition in repeated uses. Frontiers Media S.A. 2021-06-14 /pmc/articles/PMC8236575/ /pubmed/34194311 http://dx.doi.org/10.3389/fnbot.2021.699174 Text en Copyright © 2021 Li, Zhang, Li and Wu. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Li, Qi
Zhang, Anyuan
Li, Zhenlan
Wu, Yan
Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title_full Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title_fullStr Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title_full_unstemmed Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title_short Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning
title_sort improvement of emg pattern recognition model performance in repeated uses by combining feature selection and incremental transfer learning
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8236575/
https://www.ncbi.nlm.nih.gov/pubmed/34194311
http://dx.doi.org/10.3389/fnbot.2021.699174
work_keys_str_mv AT liqi improvementofemgpatternrecognitionmodelperformanceinrepeatedusesbycombiningfeatureselectionandincrementaltransferlearning
AT zhanganyuan improvementofemgpatternrecognitionmodelperformanceinrepeatedusesbycombiningfeatureselectionandincrementaltransferlearning
AT lizhenlan improvementofemgpatternrecognitionmodelperformanceinrepeatedusesbycombiningfeatureselectionandincrementaltransferlearning
AT wuyan improvementofemgpatternrecognitionmodelperformanceinrepeatedusesbycombiningfeatureselectionandincrementaltransferlearning