In Gervasi, O., Murgante, B., Hendrix, E., M., T., Taniar, D., & Apduhan, B., O., editors, Computational Science and Its Applications -- ICCSA 2022, pages 247-259, 2022. Springer International Publishing.
![ECG-Based Heartbeat Classification for Arrhythmia Detection Using Artificial Neural Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex 4 downloads
Website abstract bibtex 4 downloads Cardiovascular disease (CVD) has quickly grown in prevalence over the previous decade, becoming the major cause of human morbidity on a global scale. Due to the massive number of ECG data, manual analysis is regarded as a time-consuming, costly and prone to human error task. In the other hand, computational systems based on biomedical signal processing and machine learning techniques might be suited for supporting arrhythmia diagnostic processes, while solving some of those issues. In general, such systems involve five stages: acquisition, preprocessing, segmentation, characterization, and classification. Yet numerous fundamental aspects remain unresolved, including sensitivity to signal fluctuation, accuracy, computing cost, generalizability, and interpretability. In this context, the present study offers a comparative analysis of ECG signal classification using two artificial neural networks created by different machine learning frameworks. The neural nets were built into a pipeline that aims to strike an appropriate balance among signal robustness, variability, and accuracy. The proposed approach reaches up to 99\% of overall accuracy for each register while keeping the computational cost low.
@inproceedings{
title = {ECG-Based Heartbeat Classification for Arrhythmia Detection Using Artificial Neural Networks},
type = {inproceedings},
year = {2022},
pages = {247-259},
websites = {https://link.springer.com/chapter/10.1007/978-3-031-10450-3_20},
publisher = {Springer International Publishing},
city = {Cham},
id = {0598d3e7-7f9d-3aaa-b28c-31d7bc140797},
created = {2022-07-16T03:44:55.045Z},
file_attached = {false},
profile_id = {aba9653c-d139-3f95-aad8-969c487ed2f3},
group_id = {17c612fe-279d-38a6-ac90-9228b535bc5e},
last_modified = {2022-07-16T03:44:55.045Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {10.1007/978-3-031-10450-3_20},
source_type = {inproceedings},
private_publication = {false},
abstract = {Cardiovascular disease (CVD) has quickly grown in prevalence over the previous decade, becoming the major cause of human morbidity on a global scale. Due to the massive number of ECG data, manual analysis is regarded as a time-consuming, costly and prone to human error task. In the other hand, computational systems based on biomedical signal processing and machine learning techniques might be suited for supporting arrhythmia diagnostic processes, while solving some of those issues. In general, such systems involve five stages: acquisition, preprocessing, segmentation, characterization, and classification. Yet numerous fundamental aspects remain unresolved, including sensitivity to signal fluctuation, accuracy, computing cost, generalizability, and interpretability. In this context, the present study offers a comparative analysis of ECG signal classification using two artificial neural networks created by different machine learning frameworks. The neural nets were built into a pipeline that aims to strike an appropriate balance among signal robustness, variability, and accuracy. The proposed approach reaches up to 99\% of overall accuracy for each register while keeping the computational cost low.},
bibtype = {inproceedings},
author = {Cepeda, Eduardo and Sánchez-Pozo, Nadia N and Peluffo-Ordóñez, Diego H and González-Vergara, Juan and Almeida-Galárraga, Diego},
editor = {Gervasi, Osvaldo and Murgante, Beniamino and Hendrix, Eligius M T and Taniar, David and Apduhan, Bernady O},
booktitle = {Computational Science and Its Applications -- ICCSA 2022}
}Downloads: 4