Source Analysis and Selection Using Block Term Decomposition in Atrial Fibrillation

Abstract : Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia in clinical practice, and is becoming a major public health concern. To better understand the mechanisms of this arrhythmia an accurate analysis of the atrial activity (AA) signal in electrocardiogram (ECG) recordings is necessary. The block term decomposition (BTD), a tensor factorization technique, has been recently proposed as a tool to extract the AA in ECG signals using a blind source separation (BSS) approach. This paper makes a deep analysis of the sources estimated by BTD, showing that the classical method to select the atrial source among the other sources may not work in some cases, even for the matrix-based methods. In this context, we propose two new automated methods to select the atrial source by considering another novel parameter. Experimental results on ten patients show the validity of the proposed methods.
Type de document :
Communication dans un congrès
Deville, Y., Gannot, S., Mason, R., Plumbley, M.D., Ward, D. 14th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2018), Jul 2018, Guildford, United Kingdom. Springer, pp.46-56, Latent Variable Analysis and Signal Separation. 〈10.1007/978-3-319-93764-9_5〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01949822
Contributeur : Pedro Marinho Ramos de Oliveira <>
Soumis le : lundi 10 décembre 2018 - 14:07:25
Dernière modification le : mercredi 2 janvier 2019 - 02:45:54

Fichier

lva_paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Pedro Marinho R. de Oliveira, Vicente Zarzoso. Source Analysis and Selection Using Block Term Decomposition in Atrial Fibrillation. Deville, Y., Gannot, S., Mason, R., Plumbley, M.D., Ward, D. 14th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2018), Jul 2018, Guildford, United Kingdom. Springer, pp.46-56, Latent Variable Analysis and Signal Separation. 〈10.1007/978-3-319-93764-9_5〉. 〈hal-01949822〉

Partager

Métriques

Consultations de la notice

41

Téléchargements de fichiers

5