Abstract: Electroencephalogram (EEG) is the recording of brain electrical activity and it contains valuable information related to the different physiological states of the brain. Hence, EEG is considered an indispensable tool for diagnosing epilepsy in clinic applications. Epilepsy keeps its importance as a major brain disorder. In this paper, we aimed to classify the EEG signals and diagnose the epileptic seizures directly by using wavelet transform and an artificial neural network model. EEG signals are separated into their spectral components by using wavelet transform, by a method of sub-band decoding. These spectral components are applied to the inputs of the neural network which is then trained to give two outputs to classify whether the signal is epileptic or not. In this paper, the features extracted and the accuracy obtained from this feature set in classifying the data sample as epileptic or not is explained.


Keywords: Wavelet transform, Sub-band decomposition,  Feature Extraction, Back-propagation, Neural network, Accuracy.