Detection of Atrial Fibrillation from ECG using BTD Tensor Decomposition

Authors

DOI:

https://doi.org/10.14209/jcis.2025.3

Keywords:

Atrial Fibrillation, Tensor Decomposition, Electrocardiogram, Automatic Detection, Machine Learning

Abstract

Atrial fibrillation (AF) is a common cardiac arrhythmia associated with various cardiovascular diseases and has a significant impact on mortality around the world. This work focuses on the detection of AF using data collected from cardiac monitoring through the Electrocardiogram (ECG), proposing new attributes for the prediction of AF. In particular, the present work proposes novel convergence and optimization indicators derived from Block-term Decomposition (BTD), applied to five RRI ECG segments, combined with RRI intervals (RRI) to improve the detection of AF. These features were used with tree-based machine learning algorithms to classify signals as Atrial Fibrillation (AF) or Normal Sinus Rhythm (NSR). The study also discusses data acquisition from three different ECG databases: Atrial Fibrillation Database (AFDB), Long-term Atrial Fibrillation Database (LTAFDB), and Normal Sinus Rhythm Database (NSRDB).

Downloads

Download data is not yet available.

Author Biographies

Renan Henrique Cardoso, Universidade Federal do Ceara (UFC)

Renan H. Cardoso received the B.Sc. degree in Computer Engineering from the Universidade Federal do Ceará (UFC), Brazil, in 2021. Since then, he has worked as a software engineer. In 2024, he completed his M.Sc. degree at UFC. His research interests include machine learning, tensor decompositions, and biomedical engineering.

Carlos Alexandre Rolim Fernandes, Universidade Federal do Ceara (UFC)

C. Alexandre R. Fernandes received the B.Sc. degree in Electrical Engineering from the Universidade
Federal do Ceara (UFC), Fortaleza, Brazil, in 2003, M.Sc. degrees from the UFC and University of Nice
Sophia-Antipolis (UNSA), Nice, France, in 2005, and the double Ph.D. degree in signal processing from the UFC and UNSA, in 2009. He was a Teaching Assistant with the UNSA/FR (2008-2009) and Postdoctoral Fellow with the UFC (2009-2010). In 2010, he joined the UFC as a Full Professor with the Department of Computer Engineering. His research interests include machine learning, signal processing, tensor  decompositions, biomedical engineering etc.

Pedro Marinho Ramos de Oliveira, Université Côte d'Azur

Pedro M. R. de Oliveira was born in Fortaleza, Brazil, in 1993. He received a B.Sc. degree in Computer Engineering from the Universidade Federal do Ceara (UFC), Brazil, in 2016, and an M.Sc. degree in Teleinformatics Engineering, also from UFC, in 2017. He received a Ph.D. degree in signal processing from the Universit ́e Cˆote d’Azur, France, in 2020, where he also worked as a Teaching Assistant. From Summer 2014 to Spring 2015, he was an Exchange Student at the Illinois Institute of Technology, U.S.A. During Summer 2015, he was an Intern Researcher at the George Washington University, U.S.A. From 2020, he works in the industry on the healthcare sector. His research interests include artificial inteligence, signal processing, tensor decompositions, applied mathematics, and biomedical engineering.

Downloads

Published

2025-05-28

How to Cite

Cardoso, R. H., Fernandes, C. A. R., & Oliveira, P. M. R. de. (2025). Detection of Atrial Fibrillation from ECG using BTD Tensor Decomposition. Journal of Communication and Information Systems, 40(1), 20–30. https://doi.org/10.14209/jcis.2025.3

Issue

Section

Regular Papers
Received 2024-05-27
Accepted 2025-05-20
Published 2025-05-28

Most read articles by the same author(s)