Hybrid HMM-MLP classifier for prosthetic arm control purpose

This paper describes an approach for classifying electromyographic (EMG) signals using multilayer perceptrons (MLPs) and hidden Markov models (HMMs) hybrid classifier. Instead of using MLPs as probability generators for HMMs we propose to use MLPs as the second classifiers to increase the discrimination rates of myoelectric patterns. This strategy is proposed to overcome weak discrimination and to consider the dynamic properties of EMG signals. Three discrimination strategies (DHMM, cascaded DHMMs, and HMM with three subnet MLPs) for discriminating signals representative of 6 primitive class of motions are described and compared. The proposed strategy increase the discrimination results considerably. Results are presented to support this approach