Automatic heart sound analysis with short-time fourier transform and support vector machines

Wen Chung Kao, Chih Chao Wei, Jen Jui Liu, Pei Yung Hsiao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretation 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 staff. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The kernels of heart beat cycle segmentation and recognition are based on autocorrelation, short-time Fourier transform, and support vector machines. The experiments are done by a public heart sound database released by Texas Heart Institute. A very promising recognition rate has been achieved.

Original languageEnglish
Title of host publication2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09
Pages188-191
Number of pages4
DOIs
Publication statusPublished - 2009 Dec 1
Event2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09 - Cancun, Mexico
Duration: 2009 Aug 22009 Aug 5

Publication series

NameMidwest Symposium on Circuits and Systems
ISSN (Print)1548-3746

Other

Other2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09
CountryMexico
CityCancun
Period09/8/209/8/5

Fingerprint

Support vector machines
Fourier transforms
Acoustic waves
Autocorrelation
Computer systems
Experiments

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Kao, W. C., Wei, C. C., Liu, J. J., & Hsiao, P. Y. (2009). Automatic heart sound analysis with short-time fourier transform and support vector machines. In 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09 (pp. 188-191). [5236120] (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.2009.5236120

Automatic heart sound analysis with short-time fourier transform and support vector machines. / Kao, Wen Chung; Wei, Chih Chao; Liu, Jen Jui; Hsiao, Pei Yung.

2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09. 2009. p. 188-191 5236120 (Midwest Symposium on Circuits and Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kao, WC, Wei, CC, Liu, JJ & Hsiao, PY 2009, Automatic heart sound analysis with short-time fourier transform and support vector machines. in 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09., 5236120, Midwest Symposium on Circuits and Systems, pp. 188-191, 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09, Cancun, Mexico, 09/8/2. https://doi.org/10.1109/MWSCAS.2009.5236120
Kao WC, Wei CC, Liu JJ, Hsiao PY. Automatic heart sound analysis with short-time fourier transform and support vector machines. In 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09. 2009. p. 188-191. 5236120. (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.2009.5236120
Kao, Wen Chung ; Wei, Chih Chao ; Liu, Jen Jui ; Hsiao, Pei Yung. / Automatic heart sound analysis with short-time fourier transform and support vector machines. 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09. 2009. pp. 188-191 (Midwest Symposium on Circuits and Systems).
@inproceedings{dce4f60f0e4a4a479339ab599e46f9be,
title = "Automatic heart sound analysis with short-time fourier transform and support vector machines",
abstract = "Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretation 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 staff. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The kernels of heart beat cycle segmentation and recognition are based on autocorrelation, short-time Fourier transform, and support vector machines. The experiments are done by a public heart sound database released by Texas Heart Institute. A very promising recognition rate has been achieved.",
author = "Kao, {Wen Chung} and Wei, {Chih Chao} and Liu, {Jen Jui} and Hsiao, {Pei Yung}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/MWSCAS.2009.5236120",
language = "English",
isbn = "9781424444793",
series = "Midwest Symposium on Circuits and Systems",
pages = "188--191",
booktitle = "2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09",

}

TY - GEN

T1 - Automatic heart sound analysis with short-time fourier transform and support vector machines

AU - Kao, Wen Chung

AU - Wei, Chih Chao

AU - Liu, Jen Jui

AU - Hsiao, Pei Yung

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretation 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 staff. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The kernels of heart beat cycle segmentation and recognition are based on autocorrelation, short-time Fourier transform, and support vector machines. The experiments are done by a public heart sound database released by Texas Heart Institute. A very promising recognition rate has been achieved.

AB - Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretation 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 staff. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. The kernels of heart beat cycle segmentation and recognition are based on autocorrelation, short-time Fourier transform, and support vector machines. The experiments are done by a public heart sound database released by Texas Heart Institute. A very promising recognition rate has been achieved.

UR - http://www.scopus.com/inward/record.url?scp=77950643484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950643484&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2009.5236120

DO - 10.1109/MWSCAS.2009.5236120

M3 - Conference contribution

AN - SCOPUS:77950643484

SN - 9781424444793

T3 - Midwest Symposium on Circuits and Systems

SP - 188

EP - 191

BT - 2009 52nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS '09

ER -