Single channel-based myoelectric control of hand movements with Empirical Mode Decomposition

Myoelectric control has been an important area of research for the past 40 years for prosthetic control, since it targets amputees who lost their body limbs. Advances were achieved concerning the number of movements to be classified with high accuracy. Hence, not much research was done to extract information from single channel Electromyogram (EMG). This paper presents Empirical Mode Decomposition (EMD) for Feature Extraction (FE) from single-channel EMG for ten class wrist movements and handgrips. Two classification schemes were applied based on Time Domain-Auto Regression (TDAR) features (a commonly used approach in the Literature) and EMD, with Principle Component Analysis (PCA) for dimensionality reduction, and Support Vector Machine (SVM) for classification. With the use of only one single-channel EMG, the EMD achieved an improvement in the classification rate for a single flexor and extensor EMG channel of 11.2% (from 83.7% to 94.4%) and 13% (from 80.16% to 93.16%), respectively. The results suggested that EMD remarkably improves the classification performance for a single-channel EMG over the traditional time domain FE technique. This will reduce the computational cost of applying only one channel EMG and facilitates the acquisition of the EMG. The main drawback of using EMD technique is that it is not suitable for real time processing of prosthetic control.