Features for analysis of electrocardiographic changes in partial epileptic patients

Abstract

In this paper, the usage of features in analysis of electrocardiographic changes in partial epileptic patients was presented. Two types of electrocardiogram (ECG) beats (normal and partial epilepsy) were obtained from the MIT-BIH database. Post-ictal heart rate oscillations were studied in a heterogeneous group of patients with partial epilepsy. The classification accuracies of modified mixture of experts (MME), which were trained on diverse features, were obtained. The eigenvector methods (Pisarenko, multiple signal classification – MUSIC, and Minimum-Norm) were selected to generate the power spectral density (PSD) estimates. The features from the eigenvector PSD estimates, wavelet coefficients and Lyapunov exponents of the ECG signals were computed and statistical features were calculated to depict their distribution. The statistical features, which were used for obtaining the diverse features of the ECG signals, were then input into the implemented neural network models for training and testing purposes. The present study demonstrated that the MME trained on the diverse features achieved high accuracy rates (total classification accuracy of the MME is 99.44%).