AUTOMATIC DISCRIMINATION OF MYOELECTRIC SIGNALS VIA PARALLEL CASCADE IDENTIFICATION

It has recently been shown that it is possible to discriminate accurat ely among myoelectric signals underlying different muscle contraction types, specifically elbow flexion and extension and forearm pronation and supination. It was reported that once a number of distinctive feat ures had been extracted from the myoelectric signals, a neural network could be trained to distinguish the contraction types with an impress ively high accuracy. In the present paper, we show that a technique kn own as parallel cascade identification can be used to construct classi fiers that can also accurately differentiate the contraction types. Th e use of parallel cascades has the benefit of dispensing with the need for feature extraction, so that raw myoelectric signal data can be us ed directly. In addition, very Little data are required to train the p arallel cascades to distinguish accurately novel incoming myoelectric signals. Results of using parallel cascades to distinguish forearm pro nation, supination, and elbow flexion are presented.