Using Artificial Neural Networks for ECG Signals Denoising
The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG) signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learnin...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Editura Universităţii "Petru Maior"
2010-12-01
|
Series: | Scientific Bulletin of the ''Petru Maior" University of Tîrgu Mureș |
Subjects: | |
Online Access: | http://scientificbulletin.upm.ro/papers/2011/01/Using-Artificial-Neural-Networks-for-ECG-Signals-Denoising3.pdf |
id |
doaj-e7464bb84397409299a6c24b119f743d |
---|---|
record_format |
Article |
spelling |
doaj-e7464bb84397409299a6c24b119f743d2020-11-25T02:48:13ZengEditura Universităţii "Petru Maior"Scientific Bulletin of the ''Petru Maior" University of Tîrgu Mureș1841-92672285-438X2010-12-017 (XXIV)23034Using Artificial Neural Networks for ECG Signals DenoisingZoltán Germán-SallóKatalin GyörgyThe authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG) signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1)th sample from n previous samples To train and adjust the network weights, the backpropagation (BP) algorithm was used. In this paper, prediction of ECG signals (as time series) using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated) in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.http://scientificbulletin.upm.ro/papers/2011/01/Using-Artificial-Neural-Networks-for-ECG-Signals-Denoising3.pdfartificial neural networkECG signalpredictionbackpropagationprediction error |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zoltán Germán-Salló Katalin György |
spellingShingle |
Zoltán Germán-Salló Katalin György Using Artificial Neural Networks for ECG Signals Denoising Scientific Bulletin of the ''Petru Maior" University of Tîrgu Mureș artificial neural network ECG signal prediction backpropagation prediction error |
author_facet |
Zoltán Germán-Salló Katalin György |
author_sort |
Zoltán Germán-Salló |
title |
Using Artificial Neural Networks for ECG Signals Denoising |
title_short |
Using Artificial Neural Networks for ECG Signals Denoising |
title_full |
Using Artificial Neural Networks for ECG Signals Denoising |
title_fullStr |
Using Artificial Neural Networks for ECG Signals Denoising |
title_full_unstemmed |
Using Artificial Neural Networks for ECG Signals Denoising |
title_sort |
using artificial neural networks for ecg signals denoising |
publisher |
Editura Universităţii "Petru Maior" |
series |
Scientific Bulletin of the ''Petru Maior" University of Tîrgu Mureș |
issn |
1841-9267 2285-438X |
publishDate |
2010-12-01 |
description |
The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG) signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1)th sample from n previous samples To train and adjust the network weights, the backpropagation (BP) algorithm was used. In this paper, prediction of ECG signals (as time series) using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated) in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals. |
topic |
artificial neural network ECG signal prediction backpropagation prediction error |
url |
http://scientificbulletin.upm.ro/papers/2011/01/Using-Artificial-Neural-Networks-for-ECG-Signals-Denoising3.pdf |
work_keys_str_mv |
AT zoltangermansallo usingartificialneuralnetworksforecgsignalsdenoising AT katalingyorgy usingartificialneuralnetworksforecgsignalsdenoising |
_version_ |
1724749215337283584 |