DocumentCode
1670818
Title
Computer Based Analysis and Recognition of Heart Sound
Author
Zhou Jing ; He Wei ; Dan Chunmei ; Que Xiaosheng
Author_Institution
Sch. of Elec. Eng., Chongqing Univ., Chongqing
fYear
2008
Firstpage
2076
Lastpage
2079
Abstract
A novel heart sound (HS) analysis and recognition system is presented. Features are extracted from the normalized average Shannon energy (NASN) in wavelet domain. These features are used as inputs to the Full Bayesian Neural Networks (FBNN) for HS recognition. A total of 120 HS are used to train FBNNM for 6 different classes. The results show the suggested methodology offers a promising recognition of HS.
Keywords
Bayes methods; bioacoustics; cardiology; diseases; feature extraction; medical signal processing; neural nets; wavelet transforms; computer based analysis; feature extraction; full Bayesian neural networks; heart sound analysis; heart sound recognition; normalized average Shannon energy; wavelet domain; Bayesian methods; Electrocardiography; Feature extraction; Frequency; Heart; Neural networks; Noise reduction; Sampling methods; Wavelet analysis; Wavelet domain;
fLanguage
English
Publisher
ieee
Conference_Titel
Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on
Conference_Location
Shanghai
Print_ISBN
978-1-4244-1747-6
Electronic_ISBN
978-1-4244-1748-3
Type
conf
DOI
10.1109/ICBBE.2008.848
Filename
4535728
Link To Document