Pattern Recognition-Based Real Time Myoelectric System for Robotic Hand Control

This paper proposes a real-time myoelectric control method based on pattern recognition for an anthropomorphic robotic hand platform. The work presented consists of (i)electromyogram (EMG)data acquisition; (ii)hand gesture discrimination including muscle activity detection, data segmentation, feature extraction, classification, and postprocessing; (iii)the development of an anthropomorphic robotic hand platform. Support Vector Machine (SVM)and Linear Discriminant Analysis (LDA)classifiers along with five EMG signal features are examined and compared for constructing a feasible real-time control system. Offline and real-time testing were conducted in two separate experiments involved both able-bodied and disable subjects. The SVM classifier obtained better performance with single feature sets whereas the LDA classifier achieved slightly higher accuracy for the combined multiple features. The experiment and testing results showed that the presented method has the potential to drive robotic system based on real time human hand gestures.