ECG based biometric identification using one-dimensional local difference pattern

Abstract

In this work, an enhanced version of 1D local binary pattern is proposed, for the derivation of the most relevant features for ECG-based human recognition. Generally, ECG signal characteristics by nature impose some notable challenges, mostly related to its sensitivity to noises, artifacts, behavioral and emotional disorders and other variability factors. To deal with this critical issue, we use a One-dimensional Local Difference Pattern (1D-LDP) operator to extract the discriminating statistical features from ECG by using the difference between consecutive neighboring samples to capture both the micro and macro patterns information in the heartbeat activity while reducing the local and global variation occurred in ECG over time. To verify its robustness, K-nearest neighbors (KNN) linear support vector machine (SVM) and neural network were performed as the classifier models in this work. Obtained results show that the 1D-LDP operator clearly outperforms existing 1D-LBP variants on MIT-BIH Normal Sinus Rhythm and ECG-ID database.