Automatic phonocardiograph signal analysis for detecting heart valve disorders

被引：50

作者：

Kao, Wen-Chung ^{[1
]}

Wei, Chih-Chao ^{[1
]}

机构：

[1] Natl Taiwan Normal Univ, Dept Appl Elect Technol, Taipei, Taiwan

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2011年 / 38卷 / 06期

关键词：

Phonocardiogram (PCG); Short-time Fourier transform; 2-D discrete cosine transform; Adaptive feature extraction; Support vector machines (SVMs); CARDIAC SOUND; NEURAL-NETWORK; SYSTEM; DIAGNOSIS;

D O I：

10.1016/j.eswa.2010.11.100

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretations of heart sounds is a very special skill which is quite difficult to teach in a structured way. Because of this reason, automatic heart sound analysis in computer systems would be very helpful for medical staffs. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The process of heart beat cycle segmentation includes autocorrelation for predicting the cycle time of a heart beat. The feature extraction pipeline includes stages of the short-time Fourier transform, the discrete cosine transform, and the adaptive feature selection. Many features are extracted, but only a few specific ones are selected for the classification of each hyperplane based on a systematic approach. The experiments are done by a public heart sound database released by Texas Heart Institute. A very promising recognition rate has been achieved. (c) 2010 Elsevier Ltd. All rights reserved.

引用

页码：6458 / 6468

页数：11

共 17 条

[1]

ALPERT JS, 2001, CARDIOLOGY PRIMARY C

[2] In search of an optimization technique for Artificial Neural Network to classify abnormal heart sounds [J].

Ari, Samit ;

Saha, Goutam .

APPLIED SOFT COMPUTING, 2009, 9 (01) :330-340

[3] A computer-aided MFCC-based HMM system for automatic auscultation [J].

Chauhan, Sunita ;

Wang, Ping ;

Lim, Chu Sing ;

Anantharaman, V. .

COMPUTERS IN BIOLOGY AND MEDICINE, 2008, 38 (02) :221-233

[4] Detection of valvular heart disorders using wavelet packet decomposition and support vector machine [J].

Choi, Samjin .

EXPERT SYSTEMS WITH APPLICATIONS, 2008, 35 (04) :1679-1687

[5] Comparison of envelope extraction algorithms for cardiac sound signal segmentation [J].

Choi, Samjin ;

Jiang, Zhongwei .

EXPERT SYSTEMS WITH APPLICATIONS, 2008, 34 (02) :1056-1069

[6] A decision support system based on support vector machines for diagnosis of the heart valve diseases [J].

Comak, Emre ;

Arslan, Ahmet ;

Turkoglu, Ibrahim .

COMPUTERS IN BIOLOGY AND MEDICINE, 2007, 37 (01) :21-27

[7] Computerized heart sounds analysis [J].

Debbal, S. M. ;

Bereksi-Reguig, F. .

COMPUTERS IN BIOLOGY AND MEDICINE, 2008, 38 (02) :263-280

[8] Automatic measure of the split in the second cardiac sound by using the wavelet transform technique [J].

Debbal, S. M. ;

Bereksi-Reguig, F. .

COMPUTERS IN BIOLOGY AND MEDICINE, 2007, 37 (03) :269-276

[9] Birth of the stethoscope [J].

Geddes, LA .

IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2005, 24 (01) :84-86

[10] Neural network classification of homomorphic segmented heart sounds [J].

Gupta, Cota Navin ;

Palaniappan, Ramaswamy ;

Swaminathan, Sundaram ;

Krishnan, Shankar M. .

APPLIED SOFT COMPUTING, 2007, 7 (01) :286-297

← 1 2 →