Finger-Based ECG Biometric System
Author Information
Author(s): Lourenço André, Silva Hugo, Fred Ana
Primary Institution: Instituto Superior de Engenharia de Lisboa
Hypothesis
Can ECG signals collected from fingers be used for biometric identification?
Conclusion
The study demonstrates that a finger-based ECG biometric system can achieve a recognition rate of 94.3% for subject identification.
Supporting Evidence
- The proposed system achieved a 94.3% recognition rate in subject identification.
- A user-tuned threshold selection method improved the equal error rate to 10.1%.
- The study utilized a minimally intrusive 1-lead ECG setup for signal acquisition.
Takeaway
This study shows that we can use heart signals from our fingers to tell who we are, just like a fingerprint.
Methodology
The study used a minimally intrusive 1-lead ECG setup to collect signals from the fingers and applied time domain processing techniques for feature extraction.
Potential Biases
Potential bias due to the small sample size and the variability of ECG signals.
Limitations
The study was limited by a small sample size of 16 subjects and only one data-recording session.
Participant Demographics
16 subjects participated in the study.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website