A Robust Human Identification by Normalized Time-Domain Features of Electrocardiogram

Abstract

This study investigates the possibility of using the normalized time-domain features of Electrocardiogram (ECG) for improving the capability of human identification. For this purpose, we measured lead-1 rest ECG (normal heart rate) and physically active one (fast heart rate) from the pre-selected group. The characteristic points on the ECG waveform, P, QRS, T are extracted in terms of its time location and the ECG data is reconstructed in beat-by-beat basis by Fourier synthesis. R-T interval, Q-T interval, and QRS interval on the reconstructed ECG sequence in rest and in physical active mode are computed. The beat-by-beat based discriminatory analysis is performed on the rest and physical active ECG data by applying Malalanobis distance between these intervals.