Epileptic Activity Detection in EEGwith Neu- ral Networks

Electroencephalogram (EEG) is an important clinical tool for diagnosing, monitoring, and managing neurological disorders related to epilepsy. Neural networks provide intriguing possibilities for the analysis of the EEG. In this paper we propose a neural network based system to detect epileptic activity. The system comprises of three main components: feature extraction, feature quantization and classi cation. Key components in the proposed approach are the Self Organizing Maps (SOMs) used to quantize feature vectors and the Multilayer Perceptron (MLP) network used to classify the quantized vectors. We performed tests with three sets of features: Fourier spectral energy features, wavelet energy features, and Haralick's co-occurrence features. Over 96% of the epileptic activity was correctly identi ed with wavelet and Fourier features and with Haralick features the detection rate was in excess of 99%. Though roughly 95% of the normal activity was also correctly identi ed room for improvement still exists.