A Time-Frequency Based Method for the Detection of Epileptic Seizures in EEG Recordings

Authors:
Alexandros T. Tzallas;Markos G. Tsipouras;Dimitrios I. Fotiadis
Affiliations:
IEEE Student Member/ University of Ioannina, Greece;IEEE Student Member/ University of Ioannina, Greece;IEEE Senior Member/ University of Ioannina, Greece
Venue:
CBMS '07 Proceedings of the Twentieth IEEE International Symposium on Computer-Based Medical Systems
Year:
2007

Citing 0
Cited 2

Classification of EEG signals using relative wavelet energy and artificial neural networks

Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Automatic feature extraction using genetic programming: An application to epileptic EEG classification

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

novel three-stage method for the analysis of electroencephalographic (EEG) signals, concerning epileptic seizures, is proposed. First, segments of the EEG signals are analyzed using a time-frequency distribution and then, several features are extracted for each segment, representing the energy distribution over the time-frequency plane. Those features are used as an input in an artificial neural network (ANN), which provides the final classification of the EEG segments (existence of epileptic seizure or not). The evaluation results are very promising, indicating overall accuracy from 89.4% to 99%.