Synergy Estimation Method for Simultaneous Activation of Multiple DOFs Using Surface EMG Signals

Abstract

Surface electromyography signals are routinely used for designing prosthetic control systems. The concept of synergy estimation for muscle control interpretation is being explored extensively. Synergies estimated for a single active degree of freedom (DoF) are found to be uncorrelated and provide better results when used for single movement classification; however, an increase of simultaneously active DoFs leads to complex limb movements and multiple DoF detection becomes a challenge. Synergy estimation is a non-convex optimization technique, to provide better estimation this paper proposes the use of regularized non-negative matrix factorization for the evaluation of synergistic weights in complex movements. The use of regularization constraint makes the overall problem bounded and provide smoothness. The proposed technique showed better accuracy when tested for activation of multiple DoF simultaneously at a significantly lower computational time, i.e., by 34%.