Research on biometric method of heart sound signal based on GMM / 中国医疗器械杂志
Chinese Journal of Medical Instrumentation
;
(6): 92-99, 2013.
Article
Dans Chinois
| WPRIM
| ID: wpr-264265
ABSTRACT
<p><b>OBJECTIVE</b>Extraction of cepstral coefficients combined with Gaussian Mixture Model (GMM) is used to propose a biometric method based on heart sound signal.</p><p><b>METHODS</b>Firstly, the original heart sounds signal was preprocessed by wavelet denoising. Then, Linear Prediction Cepstral Coefficients (LPCC) and Mel Frequency Cepstral Coefficients (MFCC) are compared to extract representative features and develops hidden Markov model (HMM) for signal classification. At last, the experiment collects 100 heart sounds from 50 people to test the proposed algorithm.</p><p><b>RESULTS</b>The comparative experiments prove that LPCC is more suitable than MFCC for heart sound biometric, and by wavelet denoising in each piece of heart sound signal, the system achieves higher recognition rate than traditional GMM.</p><p><b>CONCLUSION</b>Those results show that this method can effectively improve the recognition performance of the system and achieve a satisfactory effect.</p>
Texte intégral:
Disponible
Indice:
WPRIM (Pacifique occidental)
Sujet Principal:
Phonocardiographie
/
Physiologie
/
Algorithmes
/
Chaines de Markov
/
Biométrie
/
Analyse en ondelettes
/
Coeur
/
Méthodes
/
Modèles biologiques
Type d'étude:
Évaluation en économique de la santé
/
Étude pronostique
Limites du sujet:
Humains
langue:
Chinois
Texte intégral:
Chinese Journal of Medical Instrumentation
Année:
2013
Type:
Article
Documents relatifs à ce sujet
MEDLINE
...
LILACS
LIS