Epileptic Seizure Detection using AR Model on EEG Signals

Author

Mousavi, S.R. ; Niknazar, M. ; Vahdat, B. Vosoughi

Author_Institution

Biomed. Eng. Lab., Sharif Univ. of Technol., Tehran

fYear

2008

fDate

18-20 Dec. 2008

Firstpage

1

Lastpage

4

Abstract

This study presents a new method for epilepsy detection based on autoregressive (AR) estimation of EEG signals. In this method, optimum order for AR model is determined by Bayesian Information Criterion (BIC) and then AR parameters of EEG signals (from EEG data set of epilepsy center of the University of Bonn, Germany) and their sub-bands (created with the help of wavelet decomposition) are extracted based on it. These parameters are used as a feature to classify the EEG signals into Healthy, Interictal (seizure free) and Ictal (during a seizure) groups using multilayer perceptron (MLP) classifier. Correct classification scores at the range of 91% to 96% reveals the potential of our approach for epilepsy detection.

Keywords

autoregressive processes; electroencephalography; medical disorders; medical signal processing; multilayer perceptrons; neurophysiology; signal classification; wavelet transforms; AR model; Bayesian Information Criterion; EEG signal classification; MLP classifier; University of Bonn; autoregressive estimation; correct classification scores; epileptic seizure detection; healthy group; ictal group; interictal group; multilayer perceptron classifier; neurological disorder; wavelet decomposition; Brain modeling; Electroencephalography; Epilepsy; Gamma ray detection; Gamma ray detectors; Laboratories; Robustness; Signal analysis; Signal processing; Wavelet analysis; AR model; BIC criterion; EEG signals; Epilepsy; wavelet decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering Conference, 2008. CIBEC 2008. Cairo International

Conference_Location

Cairo

Print_ISBN

978-1-4244-2694-2

Electronic_ISBN

978-1-4244-2695-9

Type

conf

DOI

10.1109/CIBEC.2008.4786067

Filename

4786067