Fractional Linear Prediction Technique for EEG signals classification

Abstract

In this paper we present a computer aided method for electroencephalogram signals (EEG) classification using fractional linear prediction (FLP) technique and k-nearest neighbor classifier. Prediction error energy and signal energy parameters are used to train the classifier. The classifier is able to classify the test data with maximum accuracy of 75.67%, 88.33%, 82.33% and 100% for four different combinations (A-B, A-C, A-D and A-E) of EEG signals. The proposed model can be implemented in a computer aided system to identify various abnormalities related to the EEG signals and help the doctor’s medical assistants to take accurate decision on time.