Recent results on the prediction of EEG signals in epilepsy by discrete-time cellular neural networks (DTCNN)

In different investigations it has been shown that nonlinear signal processing can contribute to the task of finding precursors of impending epileptic seizures in the case of a focal epilepsy. Various approaches to this feature extraction problem have been made including Volterra-systems, wavelet-analysis and cellular neural networks (CNN). This paper gives a detailed analysis of a recently proposed prediction algorithm based on a multi-layer delay-time DTCNN. The aim of this contribution is to reduce the high computation complexity caused by the permanent application of a supervised optimization procedure for successive data segments of an EEG recording. Thereby, the prediction algorithm is studied by using different optimization procedures, different network topologies and different template symmetries.