Recognizing hand movements from a single SEMG sensor using guided under-determined source signal separation.

Rehabilitation devices, prosthesis and human machine interfaces are among many applications for which surface electromyographic signals (sEMG) can be employed. Systems reliant on these muscle-generated electrical signals require various forms of machine learning algorithms for specific signature recognition. Those systems vary in terms of the signal detection methods, the feature selection and the classification algorithm used. However, in all those cases, the use of multiple sensors is a constant. In this paper, we present a new technique for source signal separation that relies on a single sEMG sensor. This proposed technique was employed in a classification framework for hand movements that achieved comparable results to other approaches in the literature, but yet, it relied on a much simpler classifier and used a very small number of features.