Prediction of epileptic seizures using accumulated energy in a multiresolution framework

Records of brain electrical activity from intracranial EEG of four patients with different types of epilepsy are analyzed to predict the epileptic seizure onset. A method based on the evolution of the accumulated energy using wavelet analysis is introduced. This is an efficient method to predict epileptic seizures: from 13 preseizure signals, the seizure onset in 12 of those are predicted.