随机森林算法在心音分类中的应用研究
Application of Random Forest Algorithm in Heart Sound Classification

DOI: 10.12677/CSA.2020.104061, PP. 591-600

Keywords: 随机森林算法，心音，短时傅里叶变换，特征提取
Random Forest Algorithm, Heart Sound, STFT, Feature Extraction

Full-Text   Cite this paper   Add to My Lib

Abstract:

本研究旨在利用随机森林算法对心音进行分类，为心脏疾病的诊断提供依据。本文结构组织如下: 首先通过电子听诊器采集心音，然后基于小波变换对其进行预处理；其次，基于短时傅立叶变换定义并提取时频域有效宽度以表征第一和第二心音的时频域特征；最后，采用随机森林算法对心音进行分类研究以区分正常和异常心音信号。通过高达93.24%分类精度验证了本系统区分正常与异常心音可行性。因此，本研究可以为医护人员或患者提供一种有效的异常心音鉴别方法。
The study aims as utilizing the random forest algorithm to classify heart sounds for diagnosing heart diseases. This paper is organized as follows: the heart sounds are firstly collected via a electronic stethoscope and preprocessed based on the wavelets transform, and secondly the short-time Fourier transform-based (STFT), the frequency domain features and time domain feature are defined and extracted to characterize the features of the first and the second heart sound in time-frequency domain. Finally, the random forest algorithm is employed to classify normal and abnormal heart sounds. The performance evaluation is validated by the achieved accuracy of 93.24% for distinguishing between normal and abnormal signals. Therefore, this study can pro-vide an efficient way to discriminate abnormal sounds for the medical workers or patients.

References

[1]	胡盛寿, 高润霖, 刘力生, 等. “中国心血管病报告2018”概要[J]. 中国循环杂志, 2019, 34(3): 209-220.
[2]	Cover, T.M. and Peter, E.H. (1967) Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, 13, 21-27. https://doi.org/10.1109/TIT.1967.1053964
[3]	King, M.W. and Patricia, A.R. (2014) Data Mining in Psychological Treatment Research: A Primer on Classification and Regression Trees. Journal of Consulting and Clin-ical Psychology, 82, 895. https://doi.org/10.1037/a0035886
[4]	Choi, S. and Jiang, Z. (2010) Cardiac Sound Murmurs Classification with Autoregressive Spectral Analysis and Multi-Support Vector Machine Technique. Com-puters in Biology and Medicine, 40, 8-20. https://doi.org/10.1016/j.compbiomed.2009.10.003
[5]	Mannini, A. and Angelo, M.S. (2010) Machine Learning Methods for Classifying Human Physical Activity from on-Body Accelerometers. Sensors, 10, 1154-1175. https://doi.org/10.3390/s100201154
[6]	Annarumma, M. et al. (2019) Automated Triaging of Adult Chest Ra-diographs with Deep Artificial Neural Networks. Radiology, 2019, Article ID: 180921. https://doi.org/10.1148/radiol.2018180921
[7]	Littmann Library. http://www.3m.com/healthcare/littmann/mmm-library.html
[8]	Coubes, J.M., Grossmann, A. and Tchanmitchian, P. (1989) Wavelet, Time-Frequency Methods and Phase Space. Springer, Berlin. https://doi.org/10.1007/978-3-642-97177-8
[9]	Goupillaud, P., Alex, G. and Jean, M. (1984) Cycle-Octave and Related Transforms in Seismic Signal Analysis. Geoexploration, 23, 85-102. https://doi.org/10.1016/0016-7142(84)90025-5
[10]	Ali, M.N., El-Dahshan, E.-S.A. and Yahia, A.H. (2017) De-noising of Heart Sound Signals Using Discrete Wavelet Transform. Circuits, Systems, and Signal Processing, 36, 4482-4497. https://doi.org/10.1007/s00034-017-0524-7
[11]	Leng, S., et al. (2015) The Electronic Stethoscope. Biomedical Engineering Online, 14, 66. https://doi.org/10.1186/s12938-015-0056-y
[12]	刘翔, 孙静, 赵洋, 等. 基于 MFCC 的心音信号特征提取及识别研究[J]. 电子测量技术, 2018(2): 1-5.
[13]	Audone, B., et al. (2016) The Short Time Fourier Transform and the Spectrograms to Characterize EMI Emissions. 2016 International Symposium on Electromagnetic Compatibility-EMC EUROPE, Wroclaw, Poland, 5-9 September 2016. https://doi.org/10.1109/EMCEurope.2016.7739239
[14]	Yeap, Y.M. and Ukil, A. (2016) Fault Detection in HVDC System Using Short Time Fourier Transform. 2016 IEEE Power and Energy Society General Meeting (PESGM), Boston, MA, 17-21 July 2016. https://doi.org/10.1109/PESGM.2016.7741323
[15]	Breiman, L. (2001) Random Forests. Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324

Full-Text