Staff View: Detection of arrhythmia from the analysis of ECG signal using artificial neural networks

Detection of arrhythmia from the analysis of ECG signal using artificial neural networks

Arrhythmia is a heart rhythm problem that could indicate a symptom of heart disease that often contributes to the increase in hospitalization in many developed countries. The patient of heart disease requires continuous monitoring and close attention to their vital sign such as the heart rate. There...

Full description

Saved in:

Bibliographic Details
Main Authors:	Panatik, Kamarul Zaman, Kamardin, Kamilia, Amir Sjarif, Nilam Nur, Abd. Aziz, Nur Syazarin Natasha, Bani, Nurul Aini, Ahmad, Noor Azurati, Mohd. Sam, Suriani, Azizan, Azizul
Format:	Article
Published:	Inst Advanced Science Extension 2019
Subjects:	T Technology (General)
Online Access:	http://eprints.utm.my/id/eprint/89414/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.89414
record_format	eprints
spelling	my.utm.894142021-02-09T08:26:51Z http://eprints.utm.my/id/eprint/89414/ Detection of arrhythmia from the analysis of ECG signal using artificial neural networks Panatik, Kamarul Zaman Kamardin, Kamilia Amir Sjarif, Nilam Nur Abd. Aziz, Nur Syazarin Natasha Bani, Nurul Aini Ahmad, Noor Azurati Mohd. Sam, Suriani Azizan, Azizul T Technology (General) Arrhythmia is a heart rhythm problem that could indicate a symptom of heart disease that often contributes to the increase in hospitalization in many developed countries. The patient of heart disease requires continuous monitoring and close attention to their vital sign such as the heart rate. There are many attempts to automate the detection of Arrhythmia from the Electrocardiogram (ECG) readings of patient. Nevertheless, the accuracy of some of these methods isnot satisfactory and prone to biased result due to inter-patient variations of ECG dataset.The purpose of this research addresses the arrhythmia classification problem from the ECG signal using Artificial Neural Network (ANN). First, we perform feature extraction on the ECG data which are the four features from RR intervals. The features are then transformed into a feature vector. Then we modelled sixteen different models of ANN where four different algorithms were used such as Bayesian Regularization (BR), Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), and Resilient Backpropagation (RP). The sixteen models are built withadifferent number of neurons in the hidden layer. We used the dataset from Massachusetts Institutes of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia Database for evaluating our models which are simulated in MATLAB. The results of the simulation were analyzedand the best model was compared with the previous work. The analysis of our research indicates that the ANN usingBayesian regularization withtwenty number of neurons in the hidden layer is the optimal model compared to other models with an overall accuracy of 83.1%. The Normal class Sensitivity was 97.4%, Specificity of 66.7% and Positive Predictive Value of 77.1%. The SVEB Sensitivity was 60% with Specificity of 86.9% and Positive Predictive Value of 42.9%. The VEB Sensitivity was 66.7% with Specificity of 88.7% and Positive Predictive Value of 66.7%. The comparison with other worksindicatesthat our model outperforms the previous work in terms of sensitivity and overall accuracy. Inst Advanced Science Extension 2019-04 Article PeerReviewed Panatik, Kamarul Zaman and Kamardin, Kamilia and Amir Sjarif, Nilam Nur and Abd. Aziz, Nur Syazarin Natasha and Bani, Nurul Aini and Ahmad, Noor Azurati and Mohd. Sam, Suriani and Azizan, Azizul (2019) Detection of arrhythmia from the analysis of ECG signal using artificial neural networks. International Journal Of Advanced And Applied Sciences (Ijaas), 6 (4). pp. 101-109. ISSN 2313-626X
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	T Technology (General)
spellingShingle	T Technology (General) Panatik, Kamarul Zaman Kamardin, Kamilia Amir Sjarif, Nilam Nur Abd. Aziz, Nur Syazarin Natasha Bani, Nurul Aini Ahmad, Noor Azurati Mohd. Sam, Suriani Azizan, Azizul Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
description	Arrhythmia is a heart rhythm problem that could indicate a symptom of heart disease that often contributes to the increase in hospitalization in many developed countries. The patient of heart disease requires continuous monitoring and close attention to their vital sign such as the heart rate. There are many attempts to automate the detection of Arrhythmia from the Electrocardiogram (ECG) readings of patient. Nevertheless, the accuracy of some of these methods isnot satisfactory and prone to biased result due to inter-patient variations of ECG dataset.The purpose of this research addresses the arrhythmia classification problem from the ECG signal using Artificial Neural Network (ANN). First, we perform feature extraction on the ECG data which are the four features from RR intervals. The features are then transformed into a feature vector. Then we modelled sixteen different models of ANN where four different algorithms were used such as Bayesian Regularization (BR), Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), and Resilient Backpropagation (RP). The sixteen models are built withadifferent number of neurons in the hidden layer. We used the dataset from Massachusetts Institutes of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia Database for evaluating our models which are simulated in MATLAB. The results of the simulation were analyzedand the best model was compared with the previous work. The analysis of our research indicates that the ANN usingBayesian regularization withtwenty number of neurons in the hidden layer is the optimal model compared to other models with an overall accuracy of 83.1%. The Normal class Sensitivity was 97.4%, Specificity of 66.7% and Positive Predictive Value of 77.1%. The SVEB Sensitivity was 60% with Specificity of 86.9% and Positive Predictive Value of 42.9%. The VEB Sensitivity was 66.7% with Specificity of 88.7% and Positive Predictive Value of 66.7%. The comparison with other worksindicatesthat our model outperforms the previous work in terms of sensitivity and overall accuracy.
format	Article
author	Panatik, Kamarul Zaman Kamardin, Kamilia Amir Sjarif, Nilam Nur Abd. Aziz, Nur Syazarin Natasha Bani, Nurul Aini Ahmad, Noor Azurati Mohd. Sam, Suriani Azizan, Azizul
author_facet	Panatik, Kamarul Zaman Kamardin, Kamilia Amir Sjarif, Nilam Nur Abd. Aziz, Nur Syazarin Natasha Bani, Nurul Aini Ahmad, Noor Azurati Mohd. Sam, Suriani Azizan, Azizul
author_sort	Panatik, Kamarul Zaman
title	Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
title_short	Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
title_full	Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
title_fullStr	Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
title_full_unstemmed	Detection of arrhythmia from the analysis of ECG signal using artificial neural networks
title_sort	detection of arrhythmia from the analysis of ecg signal using artificial neural networks
publisher	Inst Advanced Science Extension
publishDate	2019
url	http://eprints.utm.my/id/eprint/89414/
_version_	1692991780207722496
score	13.211869

Detection of arrhythmia from the analysis of ECG signal using artificial neural networks

Similar Items