Classification of Normal and Epileptic Seizure EEG Signals Based on Empirical Mode Decomposition

Abstract

Epileptic seizure occurs as a result of abnormal transient disturbance in the electrical activities of the brain. The electrical activities of brain fluctuate frequently and can be analyzed using electroencephalogram (EEG) signals. Therefore, the EEG signals are commonly used signals for obtaining the information related to the pathological states of brain. The EEG recordings of an epileptic patient contain a large amount of EEG data which may require time-consuming manual interpretations. Thus, automatic EEG signal analysis using advanced signal processing techniques plays a significant role to recognize epilepsy in EEG recordings. In this work, the empirical mode decomposition (EMD) has been applied for analysis of normal and epileptic seizure EEG signals. The EMD generates the set of amplitude and frequency modulated components known as intrinsic mode functions (IMFs). Two area measures have been computed, one for the graph obtained as the analytic signal representation of IMFs in complex plane and another for second-order difference plot (SODP) of IMFs of EEG signals. Both of these area measures have been computed for first four IMFs of the normal and epileptic seizure EEG signals. These eight features obtained from both area measures of first four IMFs have been used as input feature set for classification of normal and epileptic seizure EEG signals using least square support vector machine (LS-SVM) classifier. Among all three kernel functions namely, linear, polynomial, and radial basis function (RBF) used for classification, the RBF kernel has provided best classification accuracy in the classification of normal and epileptic seizure EEG signals. The proposed method based on the two area measures of IMFs obtained using EMD process, together with LS-SVM classifier has been studied on EEG dataset publicly available by the University of Bonn, Germany. Experimental results have been included to show the effectiveness of the proposed method in comparison to other existing methods.