Upper-limb movement classification based on sEMG signal validation with continuous channel selection

This paper aims to provide an efficient, automatic and auto-adaptive approach to establish a continuous electromyography (EMG) signal monitoring, to constantly identify an optimal electrode assortment to use as input of a pattern recognition method through time. The average classification accuracy for the adaptive input selection method was 83,96±5,79% against 72,06±7,15% in a non-adaptive system. Both systems make use of a neural network to classify 9 distinguish upper-limb movements.