Enhanced myoelectric control against arm position change with weighted recursive Gaussian process

Abstract

Listen

Translate article

In the last decade, there has been huge advancement in biomechatronic systems by the integration of pattern recognition and regression algorithms. In many myoelectric control studies, high accuracy in estimating a subject’s wrist movement was reported by measuring electromyography (EMG) signal from subjects’ forearms. However, many algorithms suffer from limited robustness against undesired disturbance in the real-world environment. In particular, arm position change is an inevitable disturbance that results in severe degradation of performance. In this study, the weighted recursive Gaussian process (WRGP) is proposed to overcome this effect. In the algorithm, the noise variance is weighted by covariate shift adaptation, which is able to handle the uncertainties. WRGP is compared with the commonly used linear regression (LR) and multilayer perceptron (MLP). LR, MLP, and WRGP are trained with the EMG dataset acquired at an arm position and tested with the different EMG dataset acquired at another arm position. Also, WRGP with uniform weights and WRGP with the weights estimated from the covariate shift adaptation are compared. The results show that WRGP with uniform weights is more robust than LR and MLP regardless of the arm position (0.16 and 0.16 higher average $$R^2$$ index, respectively). The performance of WRGP with the weights estimated from the covariate shift adaptation is significantly higher ( $$p<0.05$$ ) than the performance of LR and MLP (0.30 and 0.33 higher average $$R^2$$ index, respectively).