Topological Data Analysis of Time-Series as an Input Embedding for Deep Learning Models - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Topological Data Analysis of Time-Series as an Input Embedding for Deep Learning Models

Morgan Byers
  • Fonction : Auteur
  • PersonId : 1406768
Lee B. Hinkle
  • Fonction : Auteur
  • PersonId : 1406769
Vangelis Metsis
  • Fonction : Auteur
  • PersonId : 1105381

Résumé

An appreciable portion of medical data exist in the form of a time-series, e.g. electroencephalogram (EEG) and electrocardiogram (ECG) readings of the biopotentials related to the head and heart. Scarcity of labeled data and class imbalance pose challenges when training deep learning models. Topological data analysis (TDA) is an emerging area of research that can be applied to time-series data. In this paper we show that using TDA as a time-series embedding methodology for input to deep learning models offers advantages compared to direct training of such models on the raw data. In our work TDA acts as a generic, low-level feature extractor that is able to capture common signal patterns and thus improve performance with limited training data. Our experimental results on publicly available human physiological biosignal datasets show an improvement in accuracy, especially for imbalanced classes with only a few training instances compared to the full dataset.
Fichier sous embargo
Fichier sous embargo
0 4 6
Année Mois Jours
Avant la publication
mercredi 1 janvier 2025
Fichier sous embargo
mercredi 1 janvier 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04668670 , version 1 (07-08-2024)

Licence

Identifiants

Citer

Morgan Byers, Lee B. Hinkle, Vangelis Metsis. Topological Data Analysis of Time-Series as an Input Embedding for Deep Learning Models. 18th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2022, Hersonissos, Greece. pp.402-413, ⟨10.1007/978-3-031-08337-2_33⟩. ⟨hal-04668670⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More