Key result
A statistical approach using Gaussian Mixture Models for biometric identity verification based on heart sounds yielded an Equal Error Rate of 15.53%, improving upon other approaches.
A statistical approach using Gaussian Mixture Models for heart sound-based biometric identity verification achieved an Equal Error Rate of 15.53%.
Supports heart sound biometrics exploration; leaves open larger validation before any clinical or security use.
One of the most recent innovations in the field of biometric recognition is the usage of heart sounds as physiological traits for identity verification. In this paper, we propose a statistical approach, supported by Gaussian Mixture Models, to the the problem of biometric identity verification based on heart sounds. The system is validated on a database of heart sounds acquired from 147 people, and shows a significant performance improvement with respect to other approaches, yielding an Equal Error Rate of 15.53%.
No takes yet. Share an insight, caveat, or question.
Beritelli et al. (2010) studied Biometric identity verification (n=147). Statistical approach supported by Gaussian Mixture Models vs. Other approaches was evaluated on Equal Error Rate. A statistical approach using Gaussian Mixture Models for biometric identity verification based on heart sounds yielded an Equal Error Rate of 15.53%, improving upon other approaches.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: