Delay Time-Based Epileptic EEG Detection Using Artificial Neural Network

The electroencephalogram (EEG) signal is very important for the diagnosis of epilepsy. The EEG recordings of the ambulatory recording systems generate very lengthy data and the detection of the epileptic activity requires a time-consuming analysis of the entire length of the EEG data by an expert. A neural-network-based automated epileptic EEG detection method is proposed in this paper, which uses delay time as the input feature of an artificial neural network. Mutual information method is applied in this paper for computing the delay time parameter of EEG signals. The results indicate that the delay time values of EEG signals during an epileptic seizure become larger than those of normal EEG signals obviously, and then this phenomenon is utilized for automated epileptic EEG detection combined with probabilistic neural networks (PNN). Delay time parameter is used as the input feature of the neural network for the first time for the detection of epilepsy. It is shown that the overall accuracy as high as 100% can be achieved by using the method proposed in this paper.