Motor-Imagery Task Classification using Mel-Cepstral and Fractal Fusion based Features

Abstract

A brain-actuated wheelchair can be used to aid the movement of differentially enabled communities who face much difficulties while commuting from one place to another. In this research work, the active brain signals emanated from subjects while performing four different kinesthetic motor imagery tasks are recorded using Electroencephalography (EEG). Three different feature sets, namely, Fractal Dimension (FD), Mel-Frequency Cepstral Coefficients (MFCCs) and combined features of FD with MFCCs are extracted from the recorded EEG signals. The extracted features are then associated to classify the type of motor imagery tasks and three feedforward multi-layer Perceptrons trained with Levenberg-Marquardt method are developed. The performance of the three features are evaluated in term of classification rate and compared. Simple Elman network and NARX network models are then developed using the extracted features and evaluated. From the results, it is observed that the Elman network model trained with combined features of FD with MFCCs has yielded a higher classification accuracy for all the 5 subjects in the range of 98.98-100percent. The obtained result clearly indicates that the Elman network and combined features of FD with MFCCs has potential to classify the four different motor imagery tasks.