Performance Analysis of Epileptic Seizure Detection Using DWT & ICA with Neural Networks

The electroencephalogram (EEG) signal plays an important role in the detection of epilepsy. The EEG recordings of the ambulatory recording systems generate very lengthy data and the detection of the epileptic activity requires a timeconsuming analysis of the entire length of the EEG data by an expert. The aim of this work is compare the automatic detection of EEG patterns using Discrete wavelet Transform (DWT) and Independent Component Analysis (ICA). Our method consists of EEG data collection, feature extraction and classification stages. DWT & ICA methods are used for feature extraction in the principle of time – frequency domain analysis. In classification stage we implement SVM & NN to detect epileptic seizure. Nural Network provides binary classification between preictal/ictal and interictal states. The study is carried out on EEG recordings of two epileptic patients; two classification models are derived from each patient. The models are then tested on the same patient and the other patient, comparing the specificity, sensitivity and accuracy of each of the models. Index terms — Discrete Wavelet Transform (DWT), Independent Component Analysis (ICA), Support Vector Machines (SVM), Electroencephalogram (EEG).