Time-frequency and time-scale techniques for the classification of native and bioprosthetic heart valve sounds

被引：44

作者：

Bentley, PM

Grant, PM

McDonnell, JTE

机构：

[1] Univ Edinburgh, Edinburgh EH9 3JL, Midlothian, Scotland

[2] Hewlett Packard Labs, Bristol BS12 6QZ, Avon, England

[3] Nokia R&D, Camberley GU15 3XD, England

来源：

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING | 1998年 / 45卷 / 01期

关键词：

classification; feature analysis; Fourier transform; phonocardiograph; time-frequency analysis; wavelet;

D O I：

10.1109/10.650366

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

The determination of diagnostic features in recorded heart sounds was investigated with Carpentier-Edwards (CE) bioprosthetic valves, Morphological features, extracted using the Choi-Williams distribution, achieved between 96 and 61% correct classification, The timescale wavelet-transform feature set achieved 100% correct classification with native valve populations, and 87% with the CE replacements.

引用

页码：125 / 128

页数：4

共 14 条

[1]

BENTLEY PM, 1994, P 16 ANN INT C IEEE, V2, P1282

[2]

BENTLEY PM, 1995, CD ROM P 17 INT C IE

[3]

BENTLEY PM, 1995, THESIS U EDINBURGH E

[4]

CHEN D, 1994, P 16 ANN INT C IEEE, V2, P1276