Heart sound denoising by dynamic noise estimation.
10.7507/1001-5515.202002023
- Author:
Chundong XU
1
;
Jing ZHOU
1
;
Dongwen YING
2
,
3
;
Pengli XIN
1
Author Information
1. School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, P.R.China.
2. School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, P.R.China
3. School of Electronic, Electronical, and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, P.R.China.
- Publication Type:Journal Article
- Keywords:
heart sound classification;
heart sound denoising;
improved minimum control recursive average;
noise estimate;
optimally modified log-spectral amplitude
- MeSH:
Algorithms;
Heart Sounds;
Humans;
Signal Processing, Computer-Assisted;
Signal-To-Noise Ratio;
Wavelet Analysis
- From:
Journal of Biomedical Engineering
2020;37(5):775-785
- CountryChina
- Language:Chinese
-
Abstract:
Denoising methods based on wavelet analysis and empirical mode decomposition cannot essentially track and eliminate noise, which usually cause distortion of heart sounds. Based on this problem, a heart sound denoising method based on improved minimum control recursive average and optimally modified log-spectral amplitude is proposed in this paper. The proposed method uses a short-time window to smoothly and dynamically track and estimate the minimum noise value. The noise estimation results are used to obtain the optimal spectrum gain function, and to minimize the noise by minimizing the difference between the clean heart sound and the estimated clean heart sound. In addition, combined with the subjective analysis of spectrum and the objective analysis of contribution to normal and abnormal heart sound classification system, we propose a more rigorous evaluation mechanism. The experimental results show that the proposed method effectively improves the time-frequency features, and obtains higher scores in the normal and abnormal heart sound classification systems. The proposed method can help medical workers to improve the accuracy of their diagnosis, and also has great reference value for the construction and application of computer-aided diagnosis system.
