Cargando…

Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism

A challenging task for the biological neural signal-based human-exoskeleton interface is to achieve accurate lower limb movement prediction of patients with hemiplegia in rehabilitation training scenarios. The human-exoskeleton interface based on single-modal biological signals such as electroenceph...

Descripción completa

Detalles Bibliográficos
Autores principales: Shi, Kecheng, Mu, Fengjun, Huang, Rui, Huang, Ke, Peng, Zhinan, Zou, Chaobin, Yang, Xiao, Cheng, Hong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9082753/
https://www.ncbi.nlm.nih.gov/pubmed/35546887
http://dx.doi.org/10.3389/fnins.2022.796290
_version_ 1784703273312190464
author Shi, Kecheng
Mu, Fengjun
Huang, Rui
Huang, Ke
Peng, Zhinan
Zou, Chaobin
Yang, Xiao
Cheng, Hong
author_facet Shi, Kecheng
Mu, Fengjun
Huang, Rui
Huang, Ke
Peng, Zhinan
Zou, Chaobin
Yang, Xiao
Cheng, Hong
author_sort Shi, Kecheng
collection PubMed
description A challenging task for the biological neural signal-based human-exoskeleton interface is to achieve accurate lower limb movement prediction of patients with hemiplegia in rehabilitation training scenarios. The human-exoskeleton interface based on single-modal biological signals such as electroencephalogram (EEG) is currently not mature in predicting movements, due to its unreliability. The multimodal human-exoskeleton interface is a very novel solution to this problem. This kind of interface normally combines the EEG signal with surface electromyography (sEMG) signal. However, their use for the lower limb movement prediction is still limited—the connection between sEMG and EEG signals and the deep feature fusion between them are ignored. In this article, a Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet) is proposed for predicting lower limb movement of patients with hemiplegia. The DMEFNet introduces the con-attention structure to extract the common attention between sEMG and EEG signal features. To verify the effectiveness of DMEFNet, an sEMG and EEG data acquisition experiment and an incomplete asynchronous data collection paradigm are designed. The experimental results show that DMEFNet has a good movement prediction performance in both within-subject and cross-subject situations, reaching an accuracy of 82.96 and 88.44%, respectively.
format Online
Article
Text
id pubmed-9082753
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-90827532022-05-10 Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism Shi, Kecheng Mu, Fengjun Huang, Rui Huang, Ke Peng, Zhinan Zou, Chaobin Yang, Xiao Cheng, Hong Front Neurosci Neuroscience A challenging task for the biological neural signal-based human-exoskeleton interface is to achieve accurate lower limb movement prediction of patients with hemiplegia in rehabilitation training scenarios. The human-exoskeleton interface based on single-modal biological signals such as electroencephalogram (EEG) is currently not mature in predicting movements, due to its unreliability. The multimodal human-exoskeleton interface is a very novel solution to this problem. This kind of interface normally combines the EEG signal with surface electromyography (sEMG) signal. However, their use for the lower limb movement prediction is still limited—the connection between sEMG and EEG signals and the deep feature fusion between them are ignored. In this article, a Dense con-attention mechanism-based Multimodal Enhance Fusion Network (DMEFNet) is proposed for predicting lower limb movement of patients with hemiplegia. The DMEFNet introduces the con-attention structure to extract the common attention between sEMG and EEG signal features. To verify the effectiveness of DMEFNet, an sEMG and EEG data acquisition experiment and an incomplete asynchronous data collection paradigm are designed. The experimental results show that DMEFNet has a good movement prediction performance in both within-subject and cross-subject situations, reaching an accuracy of 82.96 and 88.44%, respectively. Frontiers Media S.A. 2022-04-25 /pmc/articles/PMC9082753/ /pubmed/35546887 http://dx.doi.org/10.3389/fnins.2022.796290 Text en Copyright © 2022 Shi, Mu, Huang, Huang, Peng, Zou, Yang and Cheng. 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
Shi, Kecheng
Mu, Fengjun
Huang, Rui
Huang, Ke
Peng, Zhinan
Zou, Chaobin
Yang, Xiao
Cheng, Hong
Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title_full Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title_fullStr Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title_full_unstemmed Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title_short Multimodal Human-Exoskeleton Interface for Lower Limb Movement Prediction Through a Dense Co-Attention Symmetric Mechanism
title_sort multimodal human-exoskeleton interface for lower limb movement prediction through a dense co-attention symmetric mechanism
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9082753/
https://www.ncbi.nlm.nih.gov/pubmed/35546887
http://dx.doi.org/10.3389/fnins.2022.796290
work_keys_str_mv AT shikecheng multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT mufengjun multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT huangrui multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT huangke multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT pengzhinan multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT zouchaobin multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT yangxiao multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism
AT chenghong multimodalhumanexoskeletoninterfaceforlowerlimbmovementpredictionthroughadensecoattentionsymmetricmechanism