Title: Combined odd pair autoregressive coefficients for epileptic EEG signals classification by radial basis function neural network

Authors: Boukari Nassim

Addresses: Department of Electrical and Electronics Engineering, Faculty of Engineering, Skikda 21000, Algeria

Abstract: This paper describes the use of odd pair autoregressive coefficients (Yule-Walker and Burg) for the feature extraction of electroencephalogram (EEG) signals. In the classification, the Radial Basis Function Neural Network (RBFNN) is employed. The RBFNN is described by his architecture and his characteristics, as the RBF is defined by the spread which is modified for improving the results of the classification. Five types of EEG signals are defined for this work: Set A, Set B for normal signals, Set C, Set D for interictal signals, and Set E for ictal signal (we can found that in Bonn university). In outputs two classes are given (AC, AD, AE, BC, BD, BE, CE, DE); the best accuracy is calculated at 99% for the combined odd pair autoregressive coefficients. Our method is very effective for the diagnosis of epileptic EEG signals.

Keywords: epilepsy diagnosis; electroencephalograms; EEG signals; signal classification; combined odd pair autoregressive coefficients; radial basis function neural networks; RBFNN.

DOI: 10.1504/IJBET.2016.081219

International Journal of Biomedical Engineering and Technology, 2016 Vol.22 No.4, pp.314 - 324

Received: 12 Jan 2016
Accepted: 08 Mar 2016

Published online: 27 Dec 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article