AUTHOR=Yang Xiao , Fu Zhe , Li Bing , Liu Jun 

TITLE=An sEMG-Based Human-Exoskeleton Interface Fusing Convolutional Neural Networks With Hand-Crafted Features

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2022.938345

DOI=10.3389/fnbot.2022.938345

ISSN=1662-5218

ABSTRACT=In recent years, the human-robot interfaces (HRI) based on surface electromyography (sEMG) have been widely used in lower-limb exoskeleton robots for movement prediction during rehabilitation training for hemiplegic patients. However, accurate and efficient lower-limb movement prediction for hemiplegic patients remains a challenge due to complex movement information and individual differences. Traditional movement prediction methods usually use hand-crafted features, which are computationally cheap, but can only extract some shallow heuristic information. Deep learning-based methods have a stronger feature expression ability, but it is easy to fall into the dilemma of local features, resulting in poor generalization performance of the method. In this paper, a human-exoskeleton interface fusing convolutional neural networks with hand-crafted features is proposed. On the basis of our previous work, a lower-limb movement prediction framework (HCSNet) in hemiplegic patients is constructed by fusing time and frequency domain hand-crafted features and channel synergy learning-based features. An sEMG data acquisition experiment is designed to compare and analyze the effectiveness of HCSNet. Experimental results show that the method can achieve $95.93\%$ and $90.37\%$ prediction accuracy in both within-subject and cross-subject cases, respectively. Compared with related lower-limb movement prediction methods, the proposed method has better prediction performance.