Human identification based on ECG signals from wearable health monitoring devices

Abstract

Wearable health monitoring devices have been widely explored to enable continuous monitoring of physiological vital signals, such as electrocardiogram (ECG). In this work, we investigate the applicability of ECG signals from such wearable devices in human identification. In the 5-subject study we undertook, the proposed method exhibits near-100% recognition rates based on single heartbeats, even with a six-month interval between the training and testing data. This indicates that ECG signals can be used as robust biometrics and as an automatic login solution for such wearable health monitoring devices.