DSpace @ UniMAP
 

iRepository at Perpustakaan UniMAP >
UNIVERSITY LIBRARY >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/10454

Title: Classification of heart sound based on S-Transform and neural network
Authors: H. M., Hadi
Mohd Yusoff, Mashor, Prof. Madya Dr.
Mohd Zubir, Suboh
Mohamed Sapawi, Mohamed
E-mail: yusoff@unimap.edu.my
Keywords: Heart sound
MLP
Neural networks
Neural networks
S-Transform
Valvular heart disease
Issue Date: 10-May-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: p. 189-192
Series/Report no.: Proceedings of the 10th International Conference on Information Sciences, Signal Processing and their Applications (ISSPA) 2010
Abstract: The skill of cardiac auscultatory is very important to physicians for accurate diagnosis of many heart diseases. However, it needs some training and experience to improve the skills of medical students in recognizing and distinguishing the primary symptoms of cardiac diseases based on the heart sound that heard. This paper presents a method for feature extraction and classification of heart sound signals. The S-Transform (ST) technique is used to extract the features of heart sound. Then, the features were applied as inputs to classifier. The Multilayer Perceptron Network has been used to classify heart sound cases. The performance of the technique has been evaluated using 250 cardiac periods of heart sound recorded from heart sound simulator. The result has shown over 98% correct classification which shows the method used is suitable to classify heart sound cases.
Description: Link to publisher's homepage at http://ieeexplore.ieee.org/
URI: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5605543
http://hdl.handle.net/123456789/10454
ISBN: 978-1-4244-7167-6
Appears in Collections:Mohd Yusoff Mashor, Prof. Dr.
Conference Papers

Files in This Item:

File Description SizeFormat
Classification of heart sound based on S.pdf28.92 kBAdobe PDFView/Open
Recommend this item

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! Universiti Malaysia Perlis :: 2007 ::
DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard - Feedback