Cargando…
Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition
As a machine-learning-driven decision-making problem, the surface electromyography (sEMG)-based hand movement recognition is one of the key issues in robust control of noninvasive neural interfaces such as myoelectric prosthesis and rehabilitation robot. Despite the recent success in sEMG-based hand...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8731285/ https://www.ncbi.nlm.nih.gov/pubmed/35003244 http://dx.doi.org/10.1155/2021/4454648 |
_version_ | 1784627326183538688 |
---|---|
author | Wei, Wentao Hu, Xuhui Liu, Hua Zhou, Ming Song, Yan |
author_facet | Wei, Wentao Hu, Xuhui Liu, Hua Zhou, Ming Song, Yan |
author_sort | Wei, Wentao |
collection | PubMed |
description | As a machine-learning-driven decision-making problem, the surface electromyography (sEMG)-based hand movement recognition is one of the key issues in robust control of noninvasive neural interfaces such as myoelectric prosthesis and rehabilitation robot. Despite the recent success in sEMG-based hand movement recognition using end-to-end deep feature learning technologies based on deep learning models, the performance of today's sEMG-based hand movement recognition system is still limited by the noisy, random, and nonstationary nature of sEMG signals and researchers have come up with a number of methods that improve sEMG-based hand movement via feature engineering. Aiming at achieving higher sEMG-based hand movement recognition accuracies while enabling a trade-off between performance and computational complexity, this study proposed a progressive fusion network (PFNet) framework, which improves sEMG-based hand movement recognition via integration of domain knowledge-guided feature engineering and deep feature learning. In particular, it learns high-level feature representations from raw sEMG signals and engineered time-frequency domain features via a feature learning network and a domain knowledge network, respectively, and then employs a 3-stage progressive fusion strategy to progressively fuse the two networks together and obtain the final decisions. Extensive experiments were conducted on five sEMG datasets to evaluate our proposed PFNet, and the experimental results showed that the proposed PFNet could achieve the average hand movement recognition accuracies of 87.8%, 85.4%, 68.3%, 71.7%, and 90.3% on the five datasets, respectively, which outperformed those achieved by the state of the arts. |
format | Online Article Text |
id | pubmed-8731285 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-87312852022-01-06 Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition Wei, Wentao Hu, Xuhui Liu, Hua Zhou, Ming Song, Yan Comput Intell Neurosci Research Article As a machine-learning-driven decision-making problem, the surface electromyography (sEMG)-based hand movement recognition is one of the key issues in robust control of noninvasive neural interfaces such as myoelectric prosthesis and rehabilitation robot. Despite the recent success in sEMG-based hand movement recognition using end-to-end deep feature learning technologies based on deep learning models, the performance of today's sEMG-based hand movement recognition system is still limited by the noisy, random, and nonstationary nature of sEMG signals and researchers have come up with a number of methods that improve sEMG-based hand movement via feature engineering. Aiming at achieving higher sEMG-based hand movement recognition accuracies while enabling a trade-off between performance and computational complexity, this study proposed a progressive fusion network (PFNet) framework, which improves sEMG-based hand movement recognition via integration of domain knowledge-guided feature engineering and deep feature learning. In particular, it learns high-level feature representations from raw sEMG signals and engineered time-frequency domain features via a feature learning network and a domain knowledge network, respectively, and then employs a 3-stage progressive fusion strategy to progressively fuse the two networks together and obtain the final decisions. Extensive experiments were conducted on five sEMG datasets to evaluate our proposed PFNet, and the experimental results showed that the proposed PFNet could achieve the average hand movement recognition accuracies of 87.8%, 85.4%, 68.3%, 71.7%, and 90.3% on the five datasets, respectively, which outperformed those achieved by the state of the arts. Hindawi 2021-12-29 /pmc/articles/PMC8731285/ /pubmed/35003244 http://dx.doi.org/10.1155/2021/4454648 Text en Copyright © 2021 Wentao Wei et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Wei, Wentao Hu, Xuhui Liu, Hua Zhou, Ming Song, Yan Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title_full | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title_fullStr | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title_full_unstemmed | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title_short | Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition |
title_sort | towards integration of domain knowledge-guided feature engineering and deep feature learning in surface electromyography-based hand movement recognition |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8731285/ https://www.ncbi.nlm.nih.gov/pubmed/35003244 http://dx.doi.org/10.1155/2021/4454648 |
work_keys_str_mv | AT weiwentao towardsintegrationofdomainknowledgeguidedfeatureengineeringanddeepfeaturelearninginsurfaceelectromyographybasedhandmovementrecognition AT huxuhui towardsintegrationofdomainknowledgeguidedfeatureengineeringanddeepfeaturelearninginsurfaceelectromyographybasedhandmovementrecognition AT liuhua towardsintegrationofdomainknowledgeguidedfeatureengineeringanddeepfeaturelearninginsurfaceelectromyographybasedhandmovementrecognition AT zhouming towardsintegrationofdomainknowledgeguidedfeatureengineeringanddeepfeaturelearninginsurfaceelectromyographybasedhandmovementrecognition AT songyan towardsintegrationofdomainknowledgeguidedfeatureengineeringanddeepfeaturelearninginsurfaceelectromyographybasedhandmovementrecognition |