Human identification based on ECG signals from wearable health monitoring devices

Authors:
Can Ye;B. V. K. Vijaya Kumar;Miguel Tavares Coimbra
Affiliations:
Carnegie Mellon University, and Faculdade de Ciências da Universidade do Porto, Portugal;Carnegie Mellon University;Faculdade de Ciências da Universidade do Porto, Portugal
Venue:
Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies
Year:
2011

Citing 5
Cited 0

Automatic detection of wave boundaries in multilead ECG signals: validation with the CSE database

Computers and Biomedical Research
Probability Estimates for Multi-class Classification by Pairwise Coupling

The Journal of Machine Learning Research
A survey on wearable sensor-based systems for health monitoring and prognosis

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Biometrics: Theory, Methods, and Applications

Biometrics: Theory, Methods, and Applications
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

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.