Classification of Elbow Motion Based on Mechanomyogram Signals Using Discriminant Analysis Approaches

Abstract

The objective of this paper is to propose a mechanomyogram (MMG)-based motion classification system that comprises a muscle-activity onset detector and a motion classifier. The detector identifies muscle-activity onset time using sampled time-series of MMG signals of biceps brachii of a human upper arm. The classifier is based on a discriminant analysis algorithm, and distinguishes the flexion and extension of an elbow directly from time-series data of MMG signals of biceps and triceps brachii. Experimental performance test results with research participants verified the feasibility of the system, and showed our system could achieve high classification accuracy.