Detection of interictal epileptic events in EEG using ANN
Khan YU., Tarassenko L.
This paper describes a system for the detection of interictal spikes in the EEG using Artificial Neural Networks (ANN). The input layer of the ANN, a multi layer perceptron (MLP), utilizes a feature vector which quantifies slope, sharpness and autoregressive parameters extracted from the EEG every second. There are two classes, namely, normal and epileptic. The MLP classification error rates evaluated for two subjects (referred to as A and B) are 6.04% and 7.33% respectively. It is clear, that the problem of subject specificity requires further work.