Classification and recognition of diastolic heart murmurs based on EMD and MFCC

被引：0
|
作者：
Li H. [1 ]
Guo X. [1 ]
Zheng Y. [1 ]
机构：
[1] Chongqing Engineering Research Center for Medical Electronic Technology, College of Bioengineering, Chongqing University, Chongqing
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2017年 / 36卷 / 11期
关键词：
Diastolic heart murmurs; Empirical mode decomposition (EMD); Hidden Markov model; Mel-frequency cepstral coefficient (MFCC);
D O I：
10.13465/j.cnki.jvs.2017.11.002
中图分类号：
学科分类号：
摘要：
Heart sound is a kind of vibration signals with characteristics of nonlinearity and non-stationarity. So the feature extraction methods based on linear time-variant or time-invariant models are bound to ignore some important internal information of heart sound signals. To better reveal the essential features of heart sound signals, a new feature extraction method based on the empirical mode decomposition (EMD) and Mel-frequency cepstral coefficient (MFCC) was proposed to classify diastolic heart murmurs. Firstly, the heart sounds were decomposed into finite intrinsic mode functions (IMFs) with EMD. Then the main IMF components were selected with the mutual correlation coefficient criterion. The main IMF components' MFCCs, MFCCs' first-order difference coefficients and Delta values were extracted, respectively. Finally, those were taken as input vectors of a hidden Markov model (HMM) to classify and identify normal heart sounds (NHSs) and two kinds of diastolic heart murmurs acquired from clinic. The test results showed that the proposed method can be used to distinguish the three types of heart sound signals effectively. © 2017, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：8 / 13
页数：5
相关论文
共 13 条
  • [1] Gharehbaghi A., Borga M., Sjoberg B.J., Et al., A novel method for discrimination between innocent and pathological heart murmurs, Medical Engineering & Physics, 37, 7, pp. 674-682, (2015)
  • [2] Uguz H., Arslan A., Turkoglu I., A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases, Pattern Recognition Letters, 28, 4, pp. 395-404, (2007)
  • [3] Babaei S., Geranmayeh A., Heart sound reproduction based on neural network classification of cardiac valve disorders using wavelet transforms of PCG signals, Computers in Biology and Medicine, 39, 1, pp. 8-15, (2009)
  • [4] Zheng Y., Guo X., Ding X., A novel hybrid energy fraction and entropy-based approach for systolic heart murmurs identification, Expert Systems with Applications, 42, 5, pp. 2710-2721, (2015)
  • [5] Huang N.E., Shen Z., Long S.R., Et al., The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceedings of the Royal Society of London A: Mathematical Physical and Engineering Sciences, 454, 1971, pp. 903-995, (1998)
  • [6] Yu J., Zhang R., Speaker recognition method using MFCC and LPCC features, Computer Engineering and Design, 30, 5, pp. 1189-1191, (2009)
  • [7] Hussain S., Kamarulafizam I., Noor A.M., Et al., Classification of heart sound based on multipoint auscultation system, 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), pp. 174-179, (2013)
  • [8] Liu X., Liu G., Qiu J., Hybrid HMM and SVM approach for fault diagnosis, Chinese Journal of Scientific Instrument, 27, 1, pp. 45-48, (2006)
  • [9] Zhai G., Chen J., Li C., Et al., Pattern recognition approach to identify loose particle material based on modified MFCC and HMMs, Neurocomputing, 155, pp. 135-145, (2015)
  • [10] Saito T., Horimi H., Hasegawa T., Et al., Isolated tricuspid valve stenosis caused by infective endocarditis in an adult: report of a case, Surgery Today, 23, 12, pp. 1081-1084, (1993)
12