Epileptic seizure detection on EEG signal using statistical signal processing and neural networks

Authors:
N. Sivasankari;K. Thanushkodi
Affiliations:
Dept of ECE, CIET, Anna University, Coimbatore, India;CIET, Coimbatore, India
Venue:
SENSIG'08 Proceedings of the 1st WSEAS international conference on Sensors and signals
Year:
2008

Citing 2
Cited 0

Neural networks at work

IEEE Spectrum
Recurrent neural networks employing Lyapunov exponents for EEG signals classification

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Epilepsy is a common chronic neurological disorder that is depicted by frequent unproved seizures. Epilepsy acutely affects the customary activities of a human being. The divination of epileptic seizures assures a novel diagnostic application and a new approach for seizure control. Conventionally epilepsy is diagnosed using any one of the following technologies namely, Electroencephalogram (EEG), Magnetic resonance imaging (MRI), Positron emission tomography (PET) etc... The prime focus of this paper is on the discerning of epileptic seizure from the data that exists in the EEG signals. The seizure is identified with the aid of Statistical Signal Processing Technique, ICA and the ascertained signals are trained employing Artificial Neural Networks technique namely Back propagation algorithm. The proposed work hauled out a number of features from EEG segments and consequently these features were used to categorize the segments relating to the epileptic seizures.