Classification of heart abnormalities using artificial neural network

Mohamad Hanif Md Saad, Mohd. Jailani Mohd Nor, Fadzlul Rahimi Ahmad Bustami, Ruzelita Ngadiran

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper describes heart abnormalities classification procedures utilising features obtained from Time-Frequency Spectogram and Image Processing Techniques. Enhanced spatial features of time-frequency spectrogram were extracted and fed into a Multi-Layer, Back-Propagation trained Artificial Neural Network and the corresponding abnormalities were classified. A confidence factor is calculated for every classification result indicating the degree of belief that the classification is true. It was observed that the classification method was able to give 100% correct classification based on features that was extracted from the training data sets and the validation data sets.

Original languageEnglish
Pages (from-to)820-825
Number of pages6
JournalJournal of Applied Sciences
Volume7
Issue number6
Publication statusPublished - 15 Mar 2007

Fingerprint

Neural networks
Backpropagation
Image processing

Keywords

  • Artificial neural network
  • Heart abnormalities classification
  • Simultaneous time-frequency analysis

ASJC Scopus subject areas

  • General

Cite this

Classification of heart abnormalities using artificial neural network. / Md Saad, Mohamad Hanif; Mohd Nor, Mohd. Jailani; Bustami, Fadzlul Rahimi Ahmad; Ngadiran, Ruzelita.

In: Journal of Applied Sciences, Vol. 7, No. 6, 15.03.2007, p. 820-825.

Research output: Contribution to journalArticle

Md Saad, Mohamad Hanif ; Mohd Nor, Mohd. Jailani ; Bustami, Fadzlul Rahimi Ahmad ; Ngadiran, Ruzelita. / Classification of heart abnormalities using artificial neural network. In: Journal of Applied Sciences. 2007 ; Vol. 7, No. 6. pp. 820-825.
@article{4b4703f790ca44fdaf272940d03b116a,
title = "Classification of heart abnormalities using artificial neural network",
abstract = "This paper describes heart abnormalities classification procedures utilising features obtained from Time-Frequency Spectogram and Image Processing Techniques. Enhanced spatial features of time-frequency spectrogram were extracted and fed into a Multi-Layer, Back-Propagation trained Artificial Neural Network and the corresponding abnormalities were classified. A confidence factor is calculated for every classification result indicating the degree of belief that the classification is true. It was observed that the classification method was able to give 100{\%} correct classification based on features that was extracted from the training data sets and the validation data sets.",
keywords = "Artificial neural network, Heart abnormalities classification, Simultaneous time-frequency analysis",
author = "{Md Saad}, {Mohamad Hanif} and {Mohd Nor}, {Mohd. Jailani} and Bustami, {Fadzlul Rahimi Ahmad} and Ruzelita Ngadiran",
year = "2007",
month = "3",
day = "15",
language = "English",
volume = "7",
pages = "820--825",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "6",

}

TY - JOUR

T1 - Classification of heart abnormalities using artificial neural network

AU - Md Saad, Mohamad Hanif

AU - Mohd Nor, Mohd. Jailani

AU - Bustami, Fadzlul Rahimi Ahmad

AU - Ngadiran, Ruzelita

PY - 2007/3/15

Y1 - 2007/3/15

N2 - This paper describes heart abnormalities classification procedures utilising features obtained from Time-Frequency Spectogram and Image Processing Techniques. Enhanced spatial features of time-frequency spectrogram were extracted and fed into a Multi-Layer, Back-Propagation trained Artificial Neural Network and the corresponding abnormalities were classified. A confidence factor is calculated for every classification result indicating the degree of belief that the classification is true. It was observed that the classification method was able to give 100% correct classification based on features that was extracted from the training data sets and the validation data sets.

AB - This paper describes heart abnormalities classification procedures utilising features obtained from Time-Frequency Spectogram and Image Processing Techniques. Enhanced spatial features of time-frequency spectrogram were extracted and fed into a Multi-Layer, Back-Propagation trained Artificial Neural Network and the corresponding abnormalities were classified. A confidence factor is calculated for every classification result indicating the degree of belief that the classification is true. It was observed that the classification method was able to give 100% correct classification based on features that was extracted from the training data sets and the validation data sets.

KW - Artificial neural network

KW - Heart abnormalities classification

KW - Simultaneous time-frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=34249816149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249816149&partnerID=8YFLogxK

M3 - Article

VL - 7

SP - 820

EP - 825

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 6

ER -