Epileptic Seizures Classification from EEG Signals using Neural Networks

Computer assisted automated detection is highly inevitable for recognizing neurological disorders, as it involves continuous monitoring of Electroencephalogram (EEG) signal. Being a non stationary signal, suitable analysis is essential for EEG to differentiate the normal EEG and epileptic seizures.. This paper proposes classification system for epilepsy based on neural networks A wavelet based feature extraction technique has been adopted to extract features Energy, Covariance Inter-quartile range (IQR) and Median Absolute Deviation (MAD) These features has been applied to Neural Networks for classification The results gave an classification accuracy of 98%. This method makes it possible as a real- time Classifier, which will improve the clinical service of Electroencephalographic recording.