Epileptic Seizure Prediction and The

Authors

Abstract

Seizures prediction may substantially improve the quality of
life of epileptic patients. Processing EEG signals, by extracting a con-
venient set of features, is the most promising way to classify the brain
state and to predict with some antecedence its evolution to a seizure con-
dition. In this work neural networks are proposed as eective classiers
of brain state among 4 classes: interictal, preictal, ictal and postictal.
A two channels set of 26 features is extracted. By correlation analysis
and by extracting the principal components, a reduced features space is
obtained where, by an appropriate neural network, over 90% successful
classications are achieved, for dataset with several patients from the
Freiburg database

Keywords

Classification, Neural Networks, Feature Selection, PCA,Correlation, Epilepsy, Seizure Prediction, EEG Processing

Subject

epilepsy; seizure prediction; Fp7 projec

Related Project

EPILEPSIAE- Evolving Platform for Improving Living Expectation of Patients

Conference

19th International Conference on Artificial Neural Networks, September 2009