Title: HeartID - Recent Advances in ECG-based Human Authentication

Speaker: Thirimachos Bourlai, University of Georgia

Abstract: Electrocardiography (ECG) is the process of recording the electrical activity of the human heart over time using electrodes that are placed over the skin. While the primary usage of electrocardiograms, the recorded signals, has been focused on the check of signs of heart-related diseases, recent studies have moved also toward their usage for human authentication. Thus, an ECG signal can be unique enough to be used independently as a biometric modality. In addition to its inherent liveness detection, it is easy to collect and can be easily captured either via sensors attached to the human body (fingertips, chest, wrist) or even passively using wireless sensors. In this presentation, we will discuss a novel approach that exploits the spectro-temporal dynamic characteristics of the ECG signal to establish personal recognition system using both short-time Fourier transform (STFT) and generalized Morse wavelets (CWT). The proposed STFT-based approach yields an average identification rate, equal error rate (EER), and area under curve (AUC) of 97.86%, 2.68%, and 0.9933 respectively, whereas the proposed CWT-based approach yields the following comparable results, i.e. 97.5% (average rate), 3.86% (EER), and 0.9882 (AUC) respectively. The presentation is expected to go beyond the selected topic and provide a brief overview on a relevant research focused on heart arrhythmia detection using machine learning.