Interpretable time series neural representation for classification purposes - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Interpretable time series neural representation for classification purposes

Résumé

Deep learning has made significant advances in creating efficient representations of time series data by automatically identifying complex patterns. However, these approaches lack interpretability, as the time series is transformed into a latent vector that is not easily interpretable. On the other hand, Symbolic Aggregate approximation (SAX) methods allow the creation of symbolic representations that can be interpreted but do not capture complex patterns effectively. In this work, we propose a set of requirements for a neural representation of univariate time series to be interpretable. We propose a new unsupervised neural architecture that meets these requirements. The proposed model produces consistent, discrete, interpretable, and visualizable representations. The model is learned independently of any downstream tasks in an unsupervised setting to ensure robustness. As a demonstration of the effectiveness of the proposed model, we propose experiments on classification tasks using UCR archive datasets. The obtained results are extensively compared to other interpretable models and state-ofthe-art neural representation learning models. The experiments show that the proposed model yields, on average better results than other interpretable approaches on multiple datasets. We also present qualitative experiments to asses the interpretability of the approach.
Fichier principal
Vignette du fichier
dsaa23.pdf (2.61 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04284273 , version 1 (14-11-2023)

Identifiants

Citer

Etienne Le Naour, Ghislain Agoua, Nicolas Baskiotis, Vincent Guigue. Interpretable time series neural representation for classification purposes. 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), Oct 2023, Thessaloniki, Greece. ⟨10.1109/DSAA60987.2023.10302534⟩. ⟨hal-04284273⟩
50 Consultations
37 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More