Real-time Classification of Finger Movements using Two-channel Surface Electromyography

Abstract

The use of a small number of Electromyography (EMG) channels for classifying the finger movement is a challenging task. This paper proposes the recognition system for decoding the individual and combined finger movements using two channels surface EMG. The proposed system utilizes Spectral Regression Discriminant Analysis (SRDA) for dimensionality reduction, Extreme Learning Machine (ELM) for classification and the majority vote for the classification smoothness. The experimental results show that the proposed system was able to classify ten classes of individual and combined finger movements, offline and online with accuracy 97.96 % and 97.07% respectively.