Publication Type:

Conference Paper


International Conference onConference on Computational Intelligence and Multimedia Applications (2007)




Artificial Neural Network, Artificial neural networks, automatic EEG epileptic spike detection, Brain, Computational intelligence, Continuous wavelet transforms, Diseases, Electroencephalography, epilepsy, epilepsy classification, Event detection, Feature extraction, Inspection, medical signal detection, neural nets, Neurophysiology, signal classification, wavelet transform, Wavelet transforms


Various problems associated with epilepsy detection is that the epileptic spike essentially change from one patient to the other and we are in need of trained professional to classify normal brain activity, where the non-pathological events that resemble pathological ones. The aim of this work is the automatic detection of Epileptic and non-Epileptic spike in EEG which plays a vital role in the determination of epilepsy. The present study proposes a system that integrates wavelet transform, Feature extraction and Artificial Neural Network for the detection and classification of Epilepsy. The system was evaluated on testing data from 25 patients of which 86.0% of the epileptic spikes and 80% of the non-epileptic spikes were detected correctly. This system has good performance in detecting epileptic activities and it is found that the Wavelet based Artificial Neural Network approach is an appropriate way of detecting the epileptic spikes in EEG.

Cite this Research Publication

M. Ganesan, Sathidevi, P. S., and Indiradevi, K. P., “A Novel Approach for the Analysis of Epileptic Spikes in EEG”, in International Conference onConference on Computational Intelligence and Multimedia Applications, 2007.