Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network

doi:10.1109/JBHI.2022.3198640

	Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network
	Wang, Shurun 2; Tang, Hao 2; Gao, Lifu 1; Tan, Qi 2
刊名	IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
	2022-11-01
卷号	26
关键词	Attention mechanism motion estimation surface electromyography temporal convolutional network
ISSN号	2168-2194
DOI	10.1109/JBHI.2022.3198640
通讯作者	Tang, Hao(htang@hfut.edu.cn)
英文摘要	Intention recognition based on surface electromyography (sEMG) signals is pivotal in human-machine interaction (HMI), where continuous motion estimation with high accuracy has been the challenge. The convolutional neural network (CNN) possesses excellent feature extraction capability. Still, it is difficult for ordinary CNN to explore the dependencies of time-series data, so most researchers adopt the recurrent neural network or its variants (e.g., LSTM) for motion estimation tasks. This paper proposes a multi-feature temporal convolutional attention-based network (MFTCAN) to recognize joint angles continuously. First, we recruited ten subjects to accomplish the signal acquisition experiments in different motion patterns. Then, we developed a joint training mechanism that integrates MFTCAN with commonly used statistical algorithms, and the integrated architectures were named MFTCAN-KNR, MFTCAN-SVR and MFTCAN-LR. Last, we utilized two performance indicators (RMSE and R-2) to evaluate the effect of different methods. Moreover, we further validated the performance of the proposed method on the open dataset (Ninapro DB2). When evaluating on the original dataset, the average RMSE of the estimations obtained by MFTCAN-KNR is 0.14, which is significantly less than the results obtained by LSTM (0.20) and BP (0.21). The average R-2 of the estimations obtained by MFTCAN-KNR is 0.87, indicating the anti-disturbance ability of the architecture. Moreover, MFTCAN-KNR also achieves high performance when evaluating on the open dataset. The proposed methods can effectively accomplish the task of motion estimation, allowing further implementations in the human-exoskeleton interaction systems.
资助项目	National Key R&D Program of China[2017YFE0129700]
WOS关键词	MOVEMENTS
WOS研究方向	Computer Science ; Mathematical & Computational Biology ; Medical Informatics
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000882005700023
资助机构	National Key R&D Program of China
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/130343]
专题	中国科学院合肥物质科学研究院
通讯作者	Tang, Hao
作者单位	1.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China 2.Hefei Univ Technol, Sch Elect Engn & Automat, Hefei 230009, Peoples R China
推荐引用方式 GB/T 7714	Wang, Shurun,Tang, Hao,Gao, Lifu,et al. Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2022,26.
APA	Wang, Shurun,Tang, Hao,Gao, Lifu,&Tan, Qi.(2022).Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,26.
MLA	Wang, Shurun,et al."Continuous Estimation of Human Joint Angles From sEMG Using a Multi-Feature Temporal Convolutional Attention-Based Network".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 26(2022).