Wavelet-based feature extraction technique for classification of different shoulder girdle motions for high-level upper limb amputees

Abstract

The aim of this study is to suggest a system for classification of seven classes of shoulder girdle motions for high-level upper limb amputees using pattern recognition (PR) system. In the suggested system, the wavelet transform was utilised for feature extraction and extreme learning machine (ELM) and linear discriminant analysis (LDA) were used as classifiers. The data were recorded from six intact-limbed subjects, and four amputees, with eight channels involving five electromyography (EMG) channels and 3-axis accelerometer. The study shows that the suggested pattern recognition system has the ability to classify the shoulder girdle motions with 92.67% classification accuracy for intact-limbed subjects and 87.67% classification accuracy for amputees by combining EMG and accelerometer channels. The outcomes of this study show that non-invasive PR system can help to provide control signals to drive a prosthetic arm for high level upper limb amputees.