Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain

Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and inter...

Full description

Saved in:
Bibliographic Details
Main Authors: Pratixita Bhattacharjee, Piotr Augustyniak
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/19/8772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283684203069440
author Pratixita Bhattacharjee
Piotr Augustyniak
author_facet Pratixita Bhattacharjee
Piotr Augustyniak
author_sort Pratixita Bhattacharjee
collection DOAJ
description Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals.
format Article
id doaj-art-a7e7f6dbfc3d4747b29a1c73623ae786
institution OA Journals
issn 2076-3417
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a7e7f6dbfc3d4747b29a1c73623ae7862025-08-20T01:47:44ZengMDPI AGApplied Sciences2076-34172024-09-011419877210.3390/app14198772Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling DomainPratixita Bhattacharjee0Piotr Augustyniak1Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30-059 Kraków, PolandFaculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Krakow, 30-059 Kraków, PolandElectrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals.https://www.mdpi.com/2076-3417/14/19/8772electrocardiogram (ECG)non-uniform samplingneural networkstransformer modeltemporal convolutional network (TCN)signal fidelity
spellingShingle Pratixita Bhattacharjee
Piotr Augustyniak
Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
Applied Sciences
electrocardiogram (ECG)
non-uniform sampling
neural networks
transformer model
temporal convolutional network (TCN)
signal fidelity
title Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
title_full Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
title_fullStr Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
title_full_unstemmed Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
title_short Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain
title_sort comparative evaluation of neural network models for optimizing ecg signal in non uniform sampling domain
topic electrocardiogram (ECG)
non-uniform sampling
neural networks
transformer model
temporal convolutional network (TCN)
signal fidelity
url https://www.mdpi.com/2076-3417/14/19/8772
work_keys_str_mv AT pratixitabhattacharjee comparativeevaluationofneuralnetworkmodelsforoptimizingecgsignalinnonuniformsamplingdomain
AT piotraugustyniak comparativeevaluationofneuralnetworkmodelsforoptimizingecgsignalinnonuniformsamplingdomain