Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Heart sound identification based on MFCC and short-term energy
Ist Teil von
2017 Chinese Automation Congress (CAC), 2017, p.7411-7415
Ort / Verlag
IEEE
Erscheinungsjahr
2017
Quelle
IEEE Xplore
Beschreibungen/Notizen
This paper analyzes the research status and development trend of heart sound identification at home and abroad. Concerning the dynamic characteristics and timedomain characteristics of heart sound signals, a new improved identification algorithm is proposed. It put the MFCC and shortterm energy together as new combined parameters. In order to further verify the validity of the parameters, an identification system based on support vector machine is established. In the experiment, the identification performance influenced by different parameters is compared, and the optimal parameter settings are obtained. The average recognition rate of heart sounds is over 94%. The experimental results show that the identification system with new parameters has a higher recognition rate and lower computational complexity than that with MFCC+AMFCC. The method proposed in the paper can effectively improve the speed of heart sound identification.