Combined strategy neural network using AR parameters for epileptic EEG signals classification

Abstract

This paper describes the use of combined neural network for the classification of electroencephalogram (EEG) signals. Five types of EEG signals are defined for this work: Sets A and B for normal signals, Sets C and D for interictal signals, and Set E for ictal signal (we can found that in Bonn university). The EEG signals were decomposed using the autoregressive coefficients; this phase is named the feature extraction, and for that two methods are used: Yule-Walker and Burg, the combination of all methods is described. There are several classifiers and different neural networks which are available for the classification of anyway signal; in our work the multilayer preceptron neural network (MLPNN) is utilised for that. MLPNN is described by his architecture and characteristics like a hidden layer in which his size is changed for improving the results of classification. In outputs, three classes are defined (ADE, ACE, BDE, BCE), the accuracies are higher and they are not lower than 90% in which the best is calculated at 97.76%. Our method is very effective for the diagnosis of epileptic EEG signals.