By Topic

A study of heartbeat sound separation using independent component analysis technique

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Usman, K. ; Dept. of Electr. Eng., Sekolah Tinggi Teknologi Telekomunikasi, Bandung, Indonesia ; Sadiq, M.A. ; Juzoji, H. ; Nakajima, I.

Physician often infers the patient's heart problem by listening to heartbeat sound. Such technique is well known as auscultation. The doctor's auscultation skill was gain after he or she experiencing a lot of cases of heart diseases and heartbeat sounds. There is a need of computer-aided equipment to analyze heartbeat sound especially for young doctors to gain a quick learning process. For this purpose, we need accurate and dependable equipment for heartbeat analysis. To improve the heartbeat analysis, we investigate the possibility of the heartbeat sound analysis, especially the separation and localization of heartbeat signal, using independent component analysis technique. The separation or localization of heartbeat signal using independent component analysis is made possible by putting several probe at appropriate places in body. Our aim is to separate two major beat sequences, which are referred as S1 and S2. The S1 beat is due to the closure of mitral-tricuspid valve and the S2 beat is due to the closure of aortic-pulmonary valve. Since the pairs of mitral-tricuspid and aortic-pulmonary valves are physically separated and can be viewed as independent sources, we can treat the beats produced by them as independent components. The FastICA algorithm was used in this study, and we do experience with a healthy 29 year-old man. The experiment showed a promising result. A refinement in the scheme of experiment, especially technique to reduce signal saturation and noise during data acquisition, will lead us to scheme for the real application.

Published in:

Enterprise Networking and Computing in Healthcare Industry, 2004. HEALTHCOM 2004. Proceedings. 6th International Workshop on

Date of Conference:

28-29 June 2004