Human identity verification based on Mel frequency analysis of digital heart sounds

Author

Beritelli, Francesco ; Spadaccini, Andrea

Author_Institution

Dipt. di Ing. Inf. e delle Telecomun., Univ. of Catania, Catania, Italy

fYear

2009

fDate

5-7 July 2009

Firstpage

1

Lastpage

5

Abstract

This paper presents new results in human identity verification via frequency analysis of cardiac sounds. More specifically, the paper proposes a pattern recognition approach based on a feature set of 13 Mel Frequency Cepstral Coefficients (MFCCs) extracted from the first (S1) and second (S2) heart sounds and a metric based on the power ratio of S1 to S2. The new algorithm yields significantly better performances with respect to the previous method based on the Chirp z-transform, guaranteeing an equal error rate (EER) below 9%.

Keywords

Z transforms; biometrics (access control); cardiology; medical signal processing; pattern recognition; chirp z-transform; digital heart sounds; equal error rate; human identity verification; mel frequency analysis; mel frequency cepstral coefficients; pattern recognition; Biometrics; Cepstral analysis; Databases; Heart; Humans; Low pass filters; Mel frequency cepstral coefficient; Performance evaluation; Testing; Valves; MFCC; biometry; digital heart sound analysis; human identity recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing, 2009 16th International Conference on

Conference_Location

Santorini-Hellas

Print_ISBN

978-1-4244-3297-4

Electronic_ISBN

978-1-4244-3298-1

Type

conf

DOI

10.1109/ICDSP.2009.5201109

Filename

5201109