Estimation of continuous and constraint-free 3 DoF wrist movements from surface electromyogram signal using kernel recursive least square tracker

• Published in: Biomedical signal processing and control Vol. 46; pp. 104 - 115
• Main Authors: Bakshi, Koushik, Manjunatha, M., Kumar, C.S.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2018
• Subjects: Kernel recursive least square tracker (KRLS-T); Kernel ridge regression (KRR); Simultaneous and proportional control (SPC); Surface electromyogram (sEMG); Upper limb prosthesis; Simultaneous and proportional control (SPC); Upper limb prosthesis; Kernel ridge regression (KRR); Kernel recursive least square tracker (KRLS-T); Surface electromyogram (sEMG)
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2018.06.012

•Forearm Electromyogram signal based wrist motion tracking. The dynamic constraint-free 3 dimensional wrist motion profiles considered, are very much similar to various daily life activities or vocational activities.•Use of nonlinear regression algorithm KRLS-T and performance comparison with artificial neural network, kernel ridge regression.•Pseudo-online simulation of KRLS-T based wrist motion estimator showing average accuracy of 90% or more. It can be realized in real time prosthesis controller. We have employed Kernel Least Square Tracker (KRLS-T), a nonlinear kernel based recursive algorithm, to estimate 3 dimensional wrist kinematics from sEMG signals of forearm muscle groups. KRLS-T combines the advantage of kernel techniques and adaptive estimation and hence has been considered for predicting 3 dimensional wrist angles from nonlinear and non-stationary sEMG. We have been able to successfully predict 6 basic and 2 dynamic, continuous and constraint-free wrist motions for 10 normal subjects in an offline mode with more than 90% accuracy. The continuous wrist motion profiles, considered here, resemble the complex and dexterous wrist motions involved in various activities of daily life. Statistical significance analysis shows that KRLS-T performs better than Kernel Ridge Regression (KRR) and a feed-forward back propagation neural network during a 10-fold cross validation stage. Subsequently, a real-life scenario has been emulated for the KRLS-T based motion predictor where 2 different trials’ data are combined and given sequentially as input to the estimator. Its fast adaptation capability to the nonstationary sEMG-wrist angle relationship, as reported here, makes it a promising option for implementing intuitive prosthesis control.