抄録
In general, activation of muscles is recorded as electromyography (EMG) with surface electrodes. Because a muscle in our body is composed of motor units (MUs), it is obvious that EMG contains several motor unit action potentials (MUAPs). Also, uncertainty of their mixing ratio makes this task be hard to handle. Then, decomposing EMG into MUAPs is one of the attractive topics today especially in the field of motion analysis. In order to challenge this severe problem, independent component analysis (ICA) is adopted in this study. And, as the first step, some primitive experiments with biomimetic EMG signals are executed to estimate its applicability. As a result, it is found that the proposed method shows good performance even though some problems are revealed.
