The neoteric feature extraction method of epilepsy EEG based on the vertex strength distribution of weighted complex network

The study of epilepsy detection has great clinical significance. The focus of this study is feature extraction method, which has significant impacts on the performance of epilepsy detection. Recently, the statistic properties of complex network show ability to describe the dynamics of nonlinear time series. In this paper, a feature extraction method of epileptic EEG, based on statistical properties of weighted complex network, is proposed. The weighted network of epileptic EEG is first constructed and the vertex strength distribution of the converted network is studied. Then the weighted mean value of the vertex strength distribution is defined and extracted as the classification feature. Experimental results indicate that the extracted feature can clearly reflect the difference between ictal EEGs and interictal EEGs and the single feature classification based on extracted feature gets higher classification accuracy up to 95.50%.