Feature extraction and classification for EMG signals using linear discriminant analysis

Analysis of EMG signal has been an interested topic in recent years for classifying surface myoelectric signal patterns. Myoelectric control is an unconventional method to control the upper limb prostheses, human-assisting robots and rehabilitation devices. The aim of present work is to assess the time-domain features of EMG signal for myoelectric control of upper extremity prostheses by utilizing scatter plot. Classification accuracy is calculated using linear discriminant classifier for different combination of feature vectors using principal component analysis (PCA) and uncorrelated linear discriminant analysis (ULDA) feature reduction techniques. Results show that willison amplitude and waveform length are the best features for separating the distinct upper-limb motions.