Why the study?
ECG-based biometric authentication is vulnerable to a lack of signal continuity verification because systems do not consider signal changes caused by situational changes in a person.
A novel ECG-based biometric authentication method using signal prediction achieved 91% accuracy.
ECG biometrics show promise for authentication; leaves open validation in real-world clinical cohorts.
The use of conventional bio-signals such as an electrocardiogram (ECG) for biometric authentication is vulnerable to a lack of verification of continuity of signals; this is because the system does not consider the change in signals caused by a change in the situation of a person, that is, conventional biological signals. Prediction technology based on tracking and analyzing new signals can overcome this shortcoming. However, since the biological signal data sets are massive, their utilization is crucial for higher accuracy. In this study, we defined a 10 × 10 matrix for 100 points based on the R-peak point and an array for the dimension of the signals. Furthermore, we defined the future predicted signals by analyzing the continuous points in each array of the matrices at the same point. As a result, the accuracy of user authentication was 91%.
No takes yet. Share an insight, caveat, or question.
Ko et al. (2022) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: