Title: Intelligent identification and classification of epileptic seizures using wavelet transform

Authors: D. Najumnissa, S. ShenbagaDevi

Addresses: Department of Instrumentation and Control Engineering, BSA Crescent Engineering College, Chennai, India. ' Center for Medical Electronics, Department of Electronics and Communication Engineering, College of Engineering, Guindy, Anna University, Chennai, India

Abstract: Epilepsy is a common neurological disorder. The need of the hour is an automated analysis of the Electroencephalographs (EEGs), which enhances efficiency of diagnosis. This paper presents simple and new approach for classifying the types of epileptic seizures. A set of feed forward neural network with wavelet feature extraction are used to process time, frequency to detect and classify the type of seizure like absence, Tonic-clonic, Febrile and Complex partial seizures. Tests of the system on EEG indicate a success rate of 94.3%. This method makes it possible as a real-time detector, which will improve the clinical service of Electroencephalographic recording.

Keywords: artificial neural networks; ANNs; Daubechies; EEG recording; intelligent identification; intelligent classification; epileptic seizures; wavelet transform; electroencephalographs; feature extraction; biomedical technology; epilepsy.

DOI: 10.1504/IJBET.2008.016963

International Journal of Biomedical Engineering and Technology, 2008 Vol.1 No.3, pp.293 - 314

Published online: 01 Feb 2008 *

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