CISUC

Epileptic Seizure Classification Using Neural Networks With 14 Features

Authors

Rui Costa
Pedro Oliveira
Pedro Oliveira
Guilherme Rodrigues
Bruno Miguel Direito Pereira Leitão
António Dourado

Abstract

Epilepsy is one of the most frequent neurological disorders.
The main method used in epilepsy diagnosis is electroencephalogram
(EEG) signal analysis. However this method requires a time-consuming
analysis when made manually by an expert due to the length of EEG
recordings. This paper proposes an automatic classi cation system for
epilepsy based on neural networks and EEG signals. The neural networks
use 14 features (extracted from EEG) in order to classify the brain state
into one of four possible epileptic behaviors: inter-ictal, pre-ictal, ictal
and pos-ictal. Experiments were made in a (i) single patient (ii) di erent
patients and (ii) multiple patients, using two datasets. The classi cation
accuracies of 6 types of neuronal networks architectures are compared.
We concluded that with the 14 features and using the data of a single
patient results in a classi cation accuracy of 99% for the data patient,
while using a network trained for multiple patients an accuracy of 98%
is achieved.

Keywords

Neural Networks, Epilepsy, Seizure Prediction, Data Mining,

Cited by

Year 2015 : 2 citations

 Seizure prediction for therapeutic devices: a review
K Gadhoumi, JM Lina, F Mormann, J Gotman - Journal of neuroscience …, 2015 - Elsevier
Abstract Research in seizure prediction has come a long way since its debut almost 4
decades ago. Early studies suffered methodological caveats leading to overoptimistic results
and lack of statistical significance. The publication of guidelines addressing mainly the ...

 Online epileptic seizure prediction using wavelet-based bi-phase correlation of electrical signals tomography
Z Vahabi, R Amirfattahi, F Shayegh… - International journal of …, 2015 - World Scientific
Considerable efforts have been made in order to predict seizures. Among these methods,
the ones that quantify synchronization between brain areas, are the most important methods.
However, to date, a practically acceptable result has not been reported. In this paper, we ...

Year 2014 : 4 citations

 EEG seizure detection and prediction algorithms: a survey
TN Alotaiby, SA Alshebeili, T Alshawi, I Ahmad… - EURASIP Journal on …, 2014 - Springer
Abstract Epilepsy patients experience challenges in daily life due to precautions they have
to take in order to cope with this condition. When a seizure occurs, it might cause injuries or
endanger the life of the patients or others, especially when they are using heavy ...

 A Neural Network Model for Predicting Epileptic Seizures based on Fourier-Bessel Functions.
S Husain, KS Rao - International Journal of Signal Processing, Image …, 2014 - sersc.org

 Performance analysis of wavelet transforms and morphological operator-based classification of epilepsy risk levels
R Harikumar, T Vijayakumar - EURASIP Journal on Advances in Signal …, 2014 - Springer

 Wavelets and Morphological Operators Based Classification of Epilepsy Risk Levels
H Rajaguru, V Thangavel - Mathematical Problems in Engineering, 2014 - hindawi.com

Year 2012 : 3 citations

 Classification of EEG signals for epileptic seizure prediction using ANN
J Kevric, A Subasi - 2012 - eprints.ibu.edu.ba

 Nearest neighbor estimate of conditional mutual information in feature selection
A Tsimpiris, I Vlachos, D Kugiumtzis - Expert Systems with Applications, 2012 - Elsevier

 Detection of epileptic seizures: the reservoir computing approach
P Buteneers - 2012 - biblio.ugent.be

Year 2011 : 2 citations

 Automatic detection of epileptic seizures on the intra-cranial electroencephalogram of rats using reservoir computing
P Buteneers, D Verstraeten, P van Mierlo… - Artificial intelligence in …, 2011 - Elsevier

 Evaluating bio-inspired approaches for advance prediction of epileptic seizures
N Moghim, D Corne - … (NaBIC), 2011 Third World Congress on, 2011 - ieeexplore.ieee.org