Detection and classification of systolic murmur using a neural network

Author

Nakamitsu, Toshiyuki ; Shino, Hideaki ; Kotani, Tomoya ; Yana, Kazuo ; Harada, Kensuke ; Sudoh, Jiro ; Harasawa, Eishi ; Itoh, Hideki

Author_Institution

Dept. of Electron. Inf., Hosei Univ., Tokyo, Japan

fYear

1996

fDate

29-31 Mar 1996

Firstpage

365

Lastpage

366

Abstract

Introduces a method for the automatic classification of the phonocardiogram. The method utilizes a multilayer perceptron for detecting the presence of the systolic murmur and a spectral analysis technique for separating innocent murmur from pathological murmur. The effectiveness of the method was confirmed by applying the method to data collected from a nationwide phonocardiogram screening study of Japanese elementary school children

Keywords

bioacoustics; cardiology; medical signal processing; multilayer perceptrons; spectral analysis; Japan; automatic classification; elementary school children; heart sounds analysis; innocent murmur; nationwide phonocardiogram screening; pathological murmur; phonocardiogram; spectral analysis technique; systolic murmur classification; Artificial neural networks; Cardiac disease; Cities and towns; Educational institutions; Electrocardiography; Heart; Neural networks; Pathology; Pediatrics; Spectral analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering Conference, 1996., Proceedings of the 1996 Fifteenth Southern

Conference_Location

Dayton, OH

Print_ISBN

0-7803-3131-1

Type

conf

DOI

10.1109/SBEC.1996.493227

Filename

493227