Motor Imagery EEG Signal Processing and Classification Using Machine Learning Approach

Motor imagery (MI) signals recorded via electroencephalography (EEG) is the most convenient basis for designing brain-computer interfaces (BCIs). As MI based BCI provides high degree of freedom, it helps motor disabled people to communicate with the device by performing sequence of MI tasks. But inter-subject variability, extracting user-specific features and increasing accuracy of the classifier is still a challenging task in MI based BCIs. In this work, we propose an approach to overcome the above mentioned issues. The proposed approach follows the pipeline such as channel selection, band-pass filter based CSP (common spatial pattern), feature extraction, feature selection using two different techniques and modeling using Gaussian Naïve Bayes (GNB) classifier. Since the optimal features are selected by feature selection techniques, it helps to overcome inter-subject variability and improves performance of GNB classifier. To the best of our knowledge, the proposed methodology has not been used for MI-based BCI applications. The proposed approach is validated using BCI competition III dataset IVa. The result of our proposed approach is compared with two conventional classifiers such as linear discriminant analysis (LDA) and support vector machine (SVM). The results prove that the proposed method provides an improved accuracy than LDA and SVM classifiers. The proposed method can be further developed to design a reliable and real-time MI-based BCI application.