Detection of epileptiform activity using wavelet and neural network

This paper describes a multichannel epileptic seizure detection algorithm based on wavelet transform (WT), artificial neural network (ANN) and the expert system. First, a small set of wavelet coefficients is used to represent the characteristics of a single channel epileptic spike. The purpose of this WT is to reduce the number of inputs to the ANN. Next, three layer feedforward network employing the error backpropagation algorithm is trained and tested using parameters obtained by the WT. Finally, 16 channel expert system based on the context information of adjacent channels is introduced to reject artifacts and produce reliable results. In this study, epileptic spike and normal activities were selected from 32 patient's EEGs (seizure disorder: 12, normal: 20) in consensus among experts. The result was that the WT reduced data input size and the preprocessed ANN had 97% sensitivity and 89.5% selectivity, which were more accurate than that of ANN with the same input size of raw data. Our expert rule system was capable of rejecting a wide variety of artifacts commonly found in EEG recordings. It's average false detection rate was 5.5/h for ANN's threshold=0.65 and false detection was also a little decreased by high thresholds.