Classification of EEG signal using wavelet transform and support vector machine for epileptic seizure diction

Abstract

Feature extraction and classification of electroencephalogram (EEGs) signals for (normal and epileptic) is a challenge for engineers and scientists. Various signal processing techniques have already been proposed for classification of non-linear and non- stationary signals like EEG. In this work, SVM (support vector machine) based classifier was employed to detect epileptic seizure activity from background electro encephalographs (EEGs). Five types of EEG signals (healthy subject with eye open condition, eye close condition, epileptic, seizure signal from hippocampal region) were selected for the analysis. Signals were preprocessed, decomposed by using discrete wavelet transform DWT till 5th level of decomposition tree. Various features like energy, entropy and standard deviation were computed and consequently used for classification of signals. The results show the promising classification accuracy of nearly 91.2% in detection of abnormal from normal EEG signals. This proposed classifier can be used to design expert system for epilepsy diagnosis purpose in various hospitals.