Abstract:
Real time controlling devices based on myoelectric
singles (MES) is one of the challenging research problems. This
paper presents a new approach to reduce the computational
cost of real time systems driven by Myoelectric signals (MES)
(a.k.a Electromyography -EMG). The new approach evaluates
the significance of feature/channel selection on MES pattern
recognition. Particle Swarm Optimization (PSO), an
evolutionary computational technique, is employed to search
the feature/channel space for important subsets. These
important subsets will be evaluated using a multilayer
perceptron trained with back propagation neural network
(BPNN). Practical results acquired from tests done on six
subject’s datasets of MES signals measured in a noninvasive
manner using surface electrodes are presented. It is proved
that minimum error rates can be achieved by considering the
correct combination of features/channels, thus providing a
feasible system for practical implementation purpose for
rehabilitation of patients.
