IDENTIFICATION OF LOWER ARM MOTIONS USING THE EMG SIGNALS OF SHOULDERMUSCLES

This investigation explored pattern recognition of EMG signals produce d by shoulder area muscles to identify the performance of a select num ber of lower arm motions. The signals were modelled as fourth-order au toregressive processes with the parameters of the models used to class ify the different motions. The recorded EMG signal was bandpass filter ed for each individual to improve discrimination between signals. The method was shown to detect and identify EMG signatures produced by at least two, and sometimes three, different arm motions. Discrimination between the signal models for the motions was not affected by load var iation or muscle fatigue.