Epileptic seizure identification from electroencephalography signal using DE-RBFNs ensemble

In this paper, an ensemble of radial basis function neural networks (RBFNs) optimized by differential evolution (DE) (DERBFNs) is presented for identification of epileptic seizure by analyzing the electroencephalography (EEG) signal. The ensemble is based on the bagging approach and the base learner is DE-RBFNs. The EEGs are decomposed with wavelet transform into different sub-bands and some statistical information is extracted from the wavelet coefficients to supply as the input to ensemble of DE-RBFNs. A benchmark publicly available dataset is used to evaluate the proposed method. The classification results confirm that the proposed ensemble of DE-RBFNs has greater potentiality to identify the epileptic disorders. (C) 2013 The Authors. Published by Elsevier B.V.