Cognitive Task Classification Using Fuzzy Based Empirical Wavelet Transform

Abstract

Brain-Computer Interfaces (BCIs) systems convert brain signals into outputs commands those allow to user to communicate even absence of other body nerves and muscles activities. Response to cognitive activity (mental task) grounded BCI system is one of the dominate areas of research interest. Electroencephalography (EEG) signals are utilized to characterize the brain activities in the BCI domain. Efficient feature extraction from EEG signal is the most important aspect of good per-formance of classification model. Two known feature extraction methods for non-linear and non-stationary signals are Wavelet Transform and Empirical Mode Decomposition. By exploiting both techniques, an adaptive-filter based approach was proposed earlier famous as Empirical Wavelet Transform (EWT) to de-compose such dynamic signals. But EWT failed to provide useful features for dynamic signals which has overlapping in frequency domain and time domain. To overcome this problem, we utilized fuzzy c-means algorithm along with EWT in our experiment. A well-known multivariate feature selection technique named Linear Regression is used to avoid the problem of the small ratio of samples to features. Further, the Quadratic discriminant classifier (QDC) has been utilized to develop the classification model. The experiments have been done on a publicly available task-based EEG data for comparing the proposed approach with EWT based cognitive activity (mental task) classification. The experimental results show that the proposed fuzzy-based EWT approach for EEG classification gives superior performance over the original EWT. © 2018 IEEE.