Features of sEMG based on source separation and fractal properties to detect wrist movements

Classification of surface electromyogram (sEMG) for identification of hand and finger flexions has a number of applications such as sEMG-based controllers for near elbow amputees and human-computer interface devices for the elderly. However, the classification of an sEMG becomes difficult when the level of muscle contraction is low and when there are multiple active muscles. The presence of noise and crosstalk from closely located and simultaneously active muscles is exaggerated when muscles are weakly active such as during sustained wrist and finger flexion and of people with neuropathological disorders or who are amputees. This paper reports analysis of fractal length and fractal dimension of two channels to obtain accurate identification of hand and finger flexion. An alternate technique, which consists of source separation of an sEMG to obtain individual muscle activity to identify the finger and hand flexion actions, is also reported. The results show that both the fractal features and muscle activity obtained using modified independent component analysis of an sEMG from the forearm can accurately identify a set of finger and wrist flexion-based actions even when the muscle activity is very weak