Cover Image

Hybrid multilayered perceptron network for classification of bundle branch blocks

Link to publisher's homepage at http://ieeexplore.ieee.org/

Saved in:
Bibliographic Details
Main Authors: Megat Syahirul Amin, Megat Ali, Ahmad Nasrul, Norali, Aisyah Hartini, Jahidin
Other Authors: megatsyahirul@salam.uitm.edu.my
Format: Working Paper
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2012
Subjects:
Bundle branch blocks
Pattern recognition
Hybrid multilayered perceptron network
Learning algorithms
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/20844
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-20844
record_format dspace
spelling my.unimap-208442012-09-05T14:31:38Z Hybrid multilayered perceptron network for classification of bundle branch blocks Megat Syahirul Amin, Megat Ali Ahmad Nasrul, Norali Aisyah Hartini, Jahidin megatsyahirul@salam.uitm.edu.my ahmadnasrul@unimap.edu.my Bundle branch blocks Pattern recognition Hybrid multilayered perceptron network Learning algorithms Link to publisher's homepage at http://ieeexplore.ieee.org/ Electrocardiogram is an electrical representation of heart activities that provide vital information on the cardiac condition. Development of reliable intelligent systems through analysis of cardiac rhythms has been paramount for automated classification of cardiac diseases. Bundle branch block is an arrhythmia caused by defects in the conduction pathways that alters the flow and speed of electrical impulses, leading to loss of cardiac output, and in severe cases, death. This paper proposes and investigates HMLP network for classification of bundle branch block arrhythmias. Samples of normal, right bundle branch block, and left bundle branch block beats were obtained from the PTB Diagnostic ECG database. Initially, the original signal underwent a filtering process and the baseline drift were rectified using the polynomial curve fitting technique. Five morphological features were then extracted through median threshold method for a total of 150 beat samples. The features were then used for training of the single hidden layer HMLP network. The training stage employed four different learning algorithms for four hidden node implementations. Results show that the Polak-Ribiere conjugate gradient algorithm achieved the best convergence speed with 100% classification accuracy. Overall, the various HMLP network structures managed to attain 99.6% average classification accuracy. 2012-09-05T14:31:38Z 2012-09-05T14:31:38Z 2012-02-27 Working Paper p. 149-154 978-145771989-9 http://ezproxy.unimap.edu.my:2080/stamp/stamp.jsp?tp=&arnumber=6178973 http://hdl.handle.net/123456789/20844 en Proceedings of the International Conference on Biomedical Engineering (ICoBE 2012) Institute of Electrical and Electronics Engineers (IEEE)
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Bundle branch blocks
Pattern recognition
Hybrid multilayered perceptron network
Learning algorithms
spellingShingle Bundle branch blocks
Pattern recognition
Hybrid multilayered perceptron network
Learning algorithms
Megat Syahirul Amin, Megat Ali
Ahmad Nasrul, Norali
Aisyah Hartini, Jahidin
Hybrid multilayered perceptron network for classification of bundle branch blocks
description Link to publisher's homepage at http://ieeexplore.ieee.org/
author2 megatsyahirul@salam.uitm.edu.my
author_facet megatsyahirul@salam.uitm.edu.my
Megat Syahirul Amin, Megat Ali
Ahmad Nasrul, Norali
Aisyah Hartini, Jahidin
format Working Paper
author Megat Syahirul Amin, Megat Ali
Ahmad Nasrul, Norali
Aisyah Hartini, Jahidin
author_sort Megat Syahirul Amin, Megat Ali
title Hybrid multilayered perceptron network for classification of bundle branch blocks
title_short Hybrid multilayered perceptron network for classification of bundle branch blocks
title_full Hybrid multilayered perceptron network for classification of bundle branch blocks
title_fullStr Hybrid multilayered perceptron network for classification of bundle branch blocks
title_full_unstemmed Hybrid multilayered perceptron network for classification of bundle branch blocks
title_sort hybrid multilayered perceptron network for classification of bundle branch blocks
publisher Institute of Electrical and Electronics Engineers (IEEE)
publishDate 2012
url http://dspace.unimap.edu.my/xmlui/handle/123456789/20844
_version_ 1643793196001525760
score 13.222552

Similar Items