心音信号是一种具有非线性和非平稳特性的振动信号，基于线性时变或时不变模型的特征提取方法势必会忽略信号的一些内在信息，为了更好的反映心音的本质特征，提出了一种经验模式分解（Empirical Mode Decomposition，EMD）结合Mel频率倒谱系数（Mel-frequency Cepstrum Coefficient，MFCC）的舒张期心杂音的分类识别方法。心音信号经EMD分解得到有限个固有模态函数（Intrinsic Mode Function，IMF），利用互相关系数准则筛选出主IMF分量，分别提取主IMF分量的MFCC、MFCC的一阶差分系数和Delta值，以此作为隐马尔科夫模型的输入向量实现对临床采集的正常心音和2类舒张期心杂音分类识别，实验结果表明，该方法能有效的识别心音。
Abstract
Heart sound is a kind of vibration signal with the characteristic of nonlinearity and non-stationarity. So the feature extraction methods based on linear time-variant or time-invariant models cannot avoid ignoring some important internal information. To better reveal the essential properties of the heart sound signals, a new feature extraction method based on the empirical mode decomposition (EMD) and Mel-frequency cepstrum coefficient (MFCC) was proposed to classify the diastolic heart murmurs. Firstly, the heart sounds were decomposed into a finite number of intrinsic mode function (IMF) by the EMD. Then the feature vectors MFCC, the first-order differential coefficient of MFCC (△MFCC) and the Delta value were extracted respectively from the main IMF components selected by the mutual correlation coefficient. Finally, the feature vectors were put into the hidden Markov model (HMM) for the classification and recognition of the normal heart sounds (NHSs) and two kinds of diastolic heart murmurs acquired from clinic. The clinic data test results show that the proposed methods can distinguish the three types of heart sound signals effectively.
关键词
舒张期心杂音 /
经验模式分解 /
Mel频率倒谱系数 /
隐马尔科夫模型
{{custom_keyword}} /
Key words
diastolic heart murmurs /
empirical mode decomposition /
Mel-frequency cepstrum coefficient /
hidden Markov model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 陈文彬，潘祥林，康熙雄，等. 诊断学[M]. 北京：人民卫生出版社，2008：137-147.
[2] Gharehbaghi A, Borga M, Sjöberg B J, et al. A novel method for discrimination between innocent and pathological heart murmurs [J]. Medical engineering & physics, 2015, 37(7): 674-682.
[3] Uğuz H, Arslan A, Türkoğlu İ. A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases [J]. Pattern Recognition Letters, 2007, 28(4): 395-404.
[4] Babaei S, Geranmayeh A. Heart sound reproduction based on neural network classification of cardiac valve disorders using wavelet transforms of PCG signals [J]. Computers in biology and medicine, 2009, 39(1): 8-15.
[5] Zheng Y, Guo X, Ding X. A novel hybrid energy fraction and entropy-based approach for systolic heart murmurs identification[J]. Expert Systems with Applications, 2015, 42(5):2710-2721.
[6] 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 [C]// Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. The Royal Society, 1998, 454(1971): 903-995.
[7] 余建潮，张瑞林. 基于MFCC和LPCC的说话人识别[J]. 计算机工程与设计，2009, 30(5):1189-1191.
YU Jian-chao, ZHANG Rui-lin. Speaker recognition method using MFCC and LPCC features [J], Computer Engineering and Design, 2009, 30(5):1189-1191.
[8] Hussain S, Kamarulafizam I, Noor A M, et al. Classification of heart sound based on multipoint auscultation system [C]// IEEE. 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), 2013: 174-179.
[9] 柳新民，刘冠军，邱 静. 基于HMM-SVM的故障诊断模型及应用[J]. 仪器仪表学报，2006, 27(1):45-48+53.
LIU Xin-min, LIU Guan-jun, QIU Jing. Hybrid HMM and SVM Approach for Fault Diagnosis [J]. Chinese Journal of Scientific Instrument, 2006, 27(1): 45-48+53.
[10] 赵力.语音信号处理[M]. 北京：机械工业出版社，2003：98-100.
[11] Zhai G, Chen J, Li C, et al. Pattern recognition approach to identify loose particle material based on modified MFCC and HMMs [J]. Neurocomputing, 2015, 155: 135-145.
[12] Saito T, Horimi H, Hasegawa T, et al. Isolated tricuspid valve stenosis caused by infective endocarditis in an adult: report of a case [J]. Surgery today, 1993, 23(12): 1081-1084.
[13] Cheng X F, Zhang Z. Denoising method of heart sound signals based on self-construct heart sound wavelet [J]. AIP Advances, 2014, 4(8): 087108.
[14] 张国华，袁中凡，李彬彬. 心音信号特征提取小波包算法研究[J]. 振动与冲击，2008, 27(7):47-49+185.
ZHANG Guo-hua, YUAN Zhong-fan, LI Bin-bin. RESEAR ON WAVELET PACKET ALGORITHM FOR FEATURE EXTRACTION OF HEART SOUND SIGNAL [J]. Journal of vibration and shock, 2008, 27(7):47-49+185.
[15] 张文英，郭兴明，翁 渐. 改进的高斯混合模型在心音信号分类识别中应用[J]. 振动与冲击，2014, 33(6):29-34.
ZHANG Wen-ying, GUO Xing-ming, WEN Jian. Application of improved GMM in classification and recognition of heart sound [J]. Journal of vibration and shock, 2014, 33(6):29-34
[16] 蔡莲红，黄德智，蔡锐. 现代语音技术基础与应用[M]. 北京：清华大学出版社，2003:236-238.
[17] Zhai G, Chen J, Li C, et al. Pattern recognition approach to identify loose particle material based on modified MFCC and HMMs[J]. Neurocomputing, 2015, 155(C):135-145.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(932 KB)
