Detection of electrocardiographic changes in partial epileptic patients using local binary pattern based composite feature.

In this paper, we propose a novel method for detecting electrocardiographic (ECG) changes in partial epileptic patients using a composite feature set. At the core of our approach is a local binary pattern (LBP) based feature representation containing a set of statistical features derived from the distribution of LBPs of the ECG signal. In order to enhance the discriminating power, a set of statistical features are also extracted from the original ECG signal. The composite feature is then generated by combining the two homogeneous feature sets. The discriminating ability of the proposed composite feature is investigated using two different classifiers namely, support vector machine and a bagged ensemble of decision trees. Results from the experimental evaluation on the publicly available MIT-BIH ECG dataset demonstrate the superiority of the proposed features over conventional histogram based LBP features. Our results also show that the proposed approach provides better classification accuracy than methods existing in the literature for classification of normal and partial epileptic beats in ECG.