A human identification system based on Heart sounds and Gaussian Mixture Models

Author

Zhao, Zhidong ; Shen, Qinqin

Author_Institution

Coll. of Electron. & Inf., Hang Zhou DianZi Univ., Hangzhou, China

Volume

2

fYear

2011

fDate

15-17 Oct. 2011

Firstpage

597

Lastpage

601

Abstract

In this paper, we propose a novel biometric method based on the Heart sounds and the Gaussian Mixture Model (GMM). Heart sounds are trained by GMM to build an identification system. The MFCC Feature extraction algorithm is studied and GMM model is built. The optimal parameters are achieved by varying experimental parameters. The system has an accurate recognition rate up to 100% under the experimental conditions. The results show that the system based on GMM has a better performance than the system based on Vector Quantization (VQ).

Keywords

acoustic signal processing; bioacoustics; biometrics (access control); cardiology; feature extraction; medical signal processing; GMM; Gaussian mixture models; biometric method; feature extraction algorithm; heart sounds; human identification system; vector quantization; Computational modeling; Heart; Hidden Markov models; Mathematical model; Mel frequency cepstral coefficient; Testing; Training; Biometric; Gaussian Mixture Model (GMM); Heart sounds; Mel Frequency Cepstrum Coefficient (MFCC);

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Informatics (BMEI), 2011 4th International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-9351-7

Type

conf

DOI

10.1109/BMEI.2011.6098471

Filename

6098471