EMG and MMG Signal Recognition Using Ensemble of One-Feature Classifiers with Pruning via Clustering Method

The paper presents a novel concept of ensemble classifier applied to the classification of electromyographic (EMG) and mechanomyographic (MMG) signals in the system of bioprosthetic hand control. In the developed multiclassifier (MC) system, first the base classifiers are grouped in terms of diversity using the novel criterion based on the type of uncertainty in the classification process. In the next step, the ensemble is pruned by selecting the best classifiers from each cluster. One-feature classifiers have been adopted as the base classifiers, i.e. pruning of classifier ensemble denotes also a feature selection procedure. The classification quality of proposed recognition method was experimentally tested and compared with seven literature ensemble systems with pruning classifiers and feature selection procedure based on Kolmogorov criterion. Real EMG and MMG biosignals for the classification of 11 types of grasping movements were used in experiments.