Multiuser gesture recognition using sEMG signals via canonical correlation analysis and optimal transport

• Published in: Computers in biology and medicine Vol. 130; p. 104188
• Main Authors: Xue, Bo, Wu, Le, Wang, Kun, Zhang, Xu, Cheng, Juan, Chen, Xiang, Chen, Xun
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2021; Elsevier Limited
• Subjects: Canonical correlation analysis; Classification; Control systems; Correlation analysis; Distribution functions; Domain adaptation; Electromyography; Gesture recognition; Human-computer interface; Interfaces; Internal Medicine; Myoelectric control; Myoelectricity; Optimal transport; Other; Pattern recognition; Probability; Probability distribution; Probability distribution functions; Prostheses; Rehabilitation; Signal processing; Surface electromyogram; Surface electromyogram; Domain adaptation; Optimal transport; Canonical correlation analysis; Gesture recognition
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2020.104188

Myoelectric interfaces have received much attention in the field of prosthesis control, neuro-rehabilitation systems and human-computer interaction. However, when different users perform the same gesture, the electromyography (EMG) signals can vary greatly. It is essential to design a multiuser myoelectric interface that can be simply used by novel users while maintaining good gesture classification performance. To cope with this problem, canonical correlation analysis (CCA) has been used to extract the inherent user-independent properties of EMG signals generated from the same gestures from multiple users and demonstrated superior performance. In this paper, we move forward to propose a novel framework based on CCA and optimal transport (OT), termed as CCA-OT. By optimal transport, the discrepancies in data distribution between the transformed feature matrix from the training and the testing sets can be further reduced. Experimental results on the defined 13 Chinese sign language gestures performed by 10 intact-limbed subjects demonstrated that the classification rate of our proposed CCA-OT framework is significantly higher than that of the CCA-only framework with an 8.49% promotion, which shows the necessity to reduce the drift in probability distribution functions (PDFs) of the different domains. The CCA-OT framework provides a promising method for the multiuser myoelectric interface which can be easily adapted to new users. This improvement will further facilitate the widespread implementation of myoelectric control systems using pattern recognition techniques. •We propose a novel framework termed as CCA-OT, to deal with the multiuser gesture recognition problem.•The data distribution divergence can be dramatically reduced between the training users and testing users by our framework.•The classification accuracy can be further improved by CCA-OT compared to CCA only.