Gamma frequency range based EEG analysis for epilepsy detection

Abstract

A significant portion of the population (0.5%-0.8%) suffers from epilepsy. This study is an effort to predict seizures in epileptic patients. The electroencephalogram (EEG) is one of the most widely used in the bioinformatics field due to its rich information about human tasks. The authors in their previous work demonstrated the use of wavelet transforms in epilepsy detection and its performance. This paper attempts hybridisation of wavelet transforms and fast Fourier transforms (FFT) by transforming wavelet coefficient into spectral components through FFT. The derived data pertaining to frequency band (30-100) Hz which has been considered for classification of the subject as either epileptic or normal. The variations in the amplitude for epileptic subjects significantly depart from the normal in the gamma band. © 2010 Inderscience Enterprises Ltd.