Automated Detection of Epileptic Seizure Using Artificial Neural Network

The embedding dimension of electroencephalogram (EEG) time series is used as the input feature of artificial neural network for detecting epileptic seizure automatedly. Cao's method is applied for computing the embedding dimension of normal and epileptic EEG time series. The probabilistic neural networks (PNN) is used in this paper for the automated detection of epilepsy. The results show that the overall accuracy as high as 100% can be achieved by using the method proposed in this paper. An interesting phenomenon is also found by Cao's method that normal EEG time series is of randomness, whereas epileptic EEG time series is of some degree of determinacy, which means that epileptic EEG time series can be predicted well.