Expert model for detection of epileptic activity in EEG signature

Seizure detection and classification using signal processing methods has been an important issue of research for the last two decades. In the present study, a novel scheme was presented to detect epileptic seizure activity with very fast and high accuracy from background electro encephalogram (EEG) data recorded from epileptic and normal subjects. The proposed scheme is based on discrete wavelet transform (DWT) and energy estimation at each node of the decomposition tree followed by application of probabilistic neural network (PNN) for classification. Normal as well as epileptic EEG epochs were decomposed into approximation and details coefficients till the sixth-level using DWT. Approximate energy (EDA) values of the wavelet coefficients at all nodes of the down sampled tree were used as a feature vector to characterize the predictability of the epileptic activity within the records of EEG data. In order to demonstrate the classification accuracy of the proposed probabilistic neural network, tenfold cross-validation was implemented in the expert model. Clinical EEG data recorded from normal as well as epileptic subjects were used to test the performance of this new scheme. It was found that with the proposed scheme, the detection is 99.33% accurate with sensitivity and specificity as 99.6% and 99%, respectively. The proposed model can be widely used in developing countries where there is an acute shortage of trained neurologist.