Amb motiu del tancament d'estiu, la validació de documents es reprendrà a partir del 28 d'agost de 2026. Disculpeu les molèsties.
Con motivo del cierre de verano, la validación de documentos se reanudará a partir del 28 de agosto de 2026. Disculpad las molestias
Due to the summer closure, document validation will resume starting August 28, 2026. We apologize for any inconvenience.

Files

260926.pdf (1.8 MB)

Document type

Article

Version

Published version

Publication date

2023-07-19

Publication license

cc by (c) Aina Ferrà Marcús et al., 2023
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/218042

Importance attribution in neural networks by means of persistence landscapes of time series

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

https://doi.org/10.1007/s00521-023-08731-6

Abstract

This article describes a method to analyze time series with a neural network using a matrix of area-normalized persistence landscapes obtained with topological data analysis. The network’s architecture includes a gating layer that is able to identify the most relevant landscape levels for a classification task, thus working as an importance attribution system. Next, a matching is performed between the selected landscape levels and the corresponding critical points of the original time series. This matching enables reconstruction of a simplified shape of the time series that gives insight into the grounds of the classification decision. As a use case, this technique is tested in the article with input data from a dataset of electrocardiographic signals. The classification accuracy obtained using only a selection of landscape levels from data was 94.00% averaged after five runs of a neural network, while the original signals achieved 98.41% and landscape-reduced signals yielded 97.04%.

Subject

Xarxes neuronals (Informàtica), Anàlisi de sèries temporals, Homologia

Subject (English)

Neural networks (Computer science), Time-series analysis, Homology

Citation

Collections

Articles publicats en revistes (Matemàtiques i Informàtica)

Citation

FERRÀ MARCÚS, Aina, CASACUBERTA, Carles and PUJOL VILA, Oriol. Importance attribution in neural networks by means of persistence landscapes of time series. Neural Computing & Applications. 2023. Vol. 35, num. 20143-20156. ISSN 0941-0643. [consulted: 7 of August of 2026]. Available at: https://hdl.handle.net/2445/218042

Export metadata

JSON - METS

Share record