The extraction of time-varying muscle synergies during hand-reaching movement with a K-means assisted approach

The production of movement in vertebrate species requisites their nervous system to deal with a high degree of freedom. The strategy that the central nervous system (CNS) recruits to overcome this barrier has been a longstanding question among researchers. A hypothesis that sheds light on this motor control problem is that the CNS uses a modular organization to simplify the task and generate a purposeful movement. In this study, we investigated on this theory by analyzing the time-varying muscle synergy modules. Furthermore, we devised a new plan in the calculation of the relating onset time coefficients by applying K-Means clustering algorithm. We also tested this algorithm in the calculation of time-varying synergy components from the electromyogram (EMG) data we recorded from ten active muscles of four subjects during a hand-reaching movement. The evaluations of the results indicate that a high similarity of synergy components between subjects is evident and this proves the efficiency of the proposed method.