Multi-Wavelet Transform Based Epilepsy Seizure Detection

About one percent of the people in the world suffer from epilepsy and 30% of epileptics are not helped by medication. Careful analyses of the EEG signals can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders and helps in identifying epilepsy seizures. Manual analysis of the EEG signals for detection epilepsy is very time consuming, hence researchers are looking towards automatic detection of epilepsy seizures from EEG signals recordings. This paper proposed a Multi-Wavelet based epilepsy seizure detection using ANN as a classifier. The proposed technique is implemented, tested and compared with existing methods based on performance indices such as sensitivity, specificity, accuracy parameters, normal and epilepsy seizures signals were classified with an accuracy of 90%.