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

• Published in: IEEE journal of biomedical and health informatics Vol. 26; no. 11; pp. 5461 - 5472
• Main Authors: Wang, Shurun, Tang, Hao, Gao, Lifu, Tan, Qi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.11.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Attention mechanism; Convolution; Datasets; Electromyography; Estimation; Exoskeleton; Exoskeletons; Feature extraction; Human motion; Motion estimation; Motion simulation; Neural networks; Performance evaluation; Recurrent neural networks; surface electromyography; Task analysis; temporal convolutional network; Time-domain analysis; Training
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2022.3198640

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 <inline-formula><tex-math notation="LaTeX">\text{R}^{2}</tex-math></inline-formula>) 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 <inline-formula><tex-math notation="LaTeX">\text{R}^{2}</tex-math></inline-formula> 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.