Abstract: According to World Health Organization (WHO), epilepsy is one of the most common primary diseases of the central nervous system worldwide, which is aggravated by the sudden factor that characterizes the occurrence of an epileptic event. Thus, the ability to detect episode before its onset appears as a mitigating factor to the unpleasant effects arising from this situation. In this paper, already implemented to detect epilepsy by using WiSARD neural network classification through this multiple evaluation had been processed. seizure detection, the WiSARD weightless neural network was explored. We proposed in this project to get high accuracy first collect the features of seizures in EEG signal through DWT co-efficient analysis. And then parameters evaluated continuously in multiple level of wavelet, passed the features to SVM classifier giving effective result compare to existing one.
Keywords: Support vector machine(SVM), Discrete Wavelet Transform(DWT), WiSARD, Electroencephalogram (EEG).