Classifying sEMG-based Hand Movements by Means of Principal Component Analysis

Abstract

In order to improve surface electromyography (sEMG) based control of hand prosthesis, we applied Principal Component Analysis (PCA) for feature extraction. The sEMG data from a group of healthy subjects (downloaded from free Ninapro database) comprised the following sets: three grasping, eight wrist, and eleven finger movements. We tested the accuracy of a simple quadratic classifier for two sets of features derived from PCA. Preliminary results suggest that the first two principal components do not guarantee successful hand movement classification. The hand movement classification accuracy significantly increased with using three instead of two features, in all three sets of movements and throughout all subjects.

Keywords

• feature extraction
• healthy subjects
• grasp
• principal component analysis
• surface electromyography