Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme

Convolutional neural network (CNN)-based models are widely used in human movement decoding based on surface electromyography. However, they capture only the spatial information of the surface electromyography and lack prior knowledge of the system, resulting in unsatisfactory decoding accuracy. To a...

Full description

Saved in:
Bibliographic Details
Main Authors: Anyuan Zhang, Qi Li, Zhenlan Li, Jiming Li
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10082987/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762768870178816
author Anyuan Zhang
Qi Li
Zhenlan Li
Jiming Li
author_facet Anyuan Zhang
Qi Li
Zhenlan Li
Jiming Li
author_sort Anyuan Zhang
collection DOAJ
description Convolutional neural network (CNN)-based models are widely used in human movement decoding based on surface electromyography. However, they capture only the spatial information of the surface electromyography and lack prior knowledge of the system, resulting in unsatisfactory decoding accuracy. To address these issues, we propose an attention-based Kalman filter scheme (AKFS), which uses an attention-based CNN model to better extract temporal information and a KF to add prior knowledge of the system. We further solve the problem of insufficient data due to the short training time of new subjects by using a transfer learning method based on a fine-tuning strategy. The proposed scheme was tested in four scenarios: intra-session, intra-session long-time use, inter-subject, and inter-subject with a fine-tuning strategy. The proposed attention-based CNN model outperformed the vanilla CNN model and a hybrid CNN-long short-term memory (LSTM) model in intra-session and intra-session long-time use. After fine-tuning with a small amount of data on a new subject, the attention-based CNN model achieved higher decoding accuracy than the vanilla CNN model and lower response time than CNN-LSTM model. Furthermore, the schemes with KF outperformed the schemes without KF in all scenarios. Our proposed scheme improves the decoding accuracy of the traditional CNN model for a single subject by better capturing the temporal information of the surface electromyography signal and increasing the prior knowledge of the system. Additionally, the proposed scheme can be easily transferred to a new subject using only a small amount of data.
format Article
id doaj-art-464b8b48a2574f02b4a5c8dda0496aae
institution DOAJ
issn 1534-4320
1558-0210
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-464b8b48a2574f02b4a5c8dda0496aae2025-08-20T03:05:39ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102023-01-01311878188710.1109/TNSRE.2023.326226910082987Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter SchemeAnyuan Zhang0https://orcid.org/0000-0001-7854-7071Qi Li1https://orcid.org/0000-0002-2716-449XZhenlan Li2Jiming Li3https://orcid.org/0009-0000-2964-8650School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, ChinaSchool of Computer Science and Technology, Changchun University of Science and Technology, Changchun, ChinaDepartment of Physical Medicine and Rehabilitation, The First Hospital of Jilin University, Changchun, ChinaSchool of Computer Science and Technology, Changchun University of Science and Technology, Changchun, ChinaConvolutional neural network (CNN)-based models are widely used in human movement decoding based on surface electromyography. However, they capture only the spatial information of the surface electromyography and lack prior knowledge of the system, resulting in unsatisfactory decoding accuracy. To address these issues, we propose an attention-based Kalman filter scheme (AKFS), which uses an attention-based CNN model to better extract temporal information and a KF to add prior knowledge of the system. We further solve the problem of insufficient data due to the short training time of new subjects by using a transfer learning method based on a fine-tuning strategy. The proposed scheme was tested in four scenarios: intra-session, intra-session long-time use, inter-subject, and inter-subject with a fine-tuning strategy. The proposed attention-based CNN model outperformed the vanilla CNN model and a hybrid CNN-long short-term memory (LSTM) model in intra-session and intra-session long-time use. After fine-tuning with a small amount of data on a new subject, the attention-based CNN model achieved higher decoding accuracy than the vanilla CNN model and lower response time than CNN-LSTM model. Furthermore, the schemes with KF outperformed the schemes without KF in all scenarios. Our proposed scheme improves the decoding accuracy of the traditional CNN model for a single subject by better capturing the temporal information of the surface electromyography signal and increasing the prior knowledge of the system. Additionally, the proposed scheme can be easily transferred to a new subject using only a small amount of data.https://ieeexplore.ieee.org/document/10082987/Attention mechanismconvolutional neural networkhuman movement decodingKalman filterlong short-term memory
spellingShingle Anyuan Zhang
Qi Li
Zhenlan Li
Jiming Li
Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Attention mechanism
convolutional neural network
human movement decoding
Kalman filter
long short-term memory
title Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
title_full Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
title_fullStr Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
title_full_unstemmed Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
title_short Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme
title_sort upper limb movement decoding scheme based on surface electromyography using attention based kalman filter scheme
topic Attention mechanism
convolutional neural network
human movement decoding
Kalman filter
long short-term memory
url https://ieeexplore.ieee.org/document/10082987/
work_keys_str_mv AT anyuanzhang upperlimbmovementdecodingschemebasedonsurfaceelectromyographyusingattentionbasedkalmanfilterscheme
AT qili upperlimbmovementdecodingschemebasedonsurfaceelectromyographyusingattentionbasedkalmanfilterscheme
AT zhenlanli upperlimbmovementdecodingschemebasedonsurfaceelectromyographyusingattentionbasedkalmanfilterscheme
AT jimingli upperlimbmovementdecodingschemebasedonsurfaceelectromyographyusingattentionbasedkalmanfilterscheme