EPILEPTIC SEIZURE DETECTION IN EEG SIGNALS USING MULTIFRACTAL ANALYSIS AND WAVELET TRANSFORM

Abstract

This paper explores the three different methods to explicitly recognize the healthy and epileptic EEG signals: Modified, Improved, and Advanced forms of Generalized Fractal Dimensions (GFD). The newly proposed scheme is based on GFD and the discrete wavelet transform (DWT) for analyzing the EEG signals. First EEG signals are decomposed into approximation and detail coefficients using DWT and then GFD values of the original EEGs, approximation and detail coefficients are computed. Significant differences are observed among the GFD values of the healthy and epileptic EEGs allowing us to classify seizures with high accuracy. It is shown that the classification rate is very less accurate without DWT as a preprocessing step. The proposed idea is illustrated through the graphical and statistical tools. The EEG data is further tested for linearity by using normal probability plot and we proved that epileptic EEG had significant nonlinearity whereas healthy EEG distributed normally and similar to Gaussian linear process. Therefore, we conclude that the GFD and the wavelet decomposition through DWT are the strong indicators of the state of illness of epileptic patients.