Topological Analysis for Detecting Anomalies (TADA) in Time Series - IRT SystemX Access content directly
Preprints, Working Papers, ... Year : 2024

Topological Analysis for Detecting Anomalies (TADA) in Time Series

Frédéric Chazal
Clément Levrard
  • Function : Author
  • PersonId : 1318418
Martin Royer

Abstract

This paper introduces new methodology based on the field of Topological Data Analysis for detecting anomalies in multivariate time series, that aims to detect global changes in the dependency structure between channels. The proposed approach is lean enough to handle large scale datasets, and extensive numerical experiments back the intuition that it is more suitable for detecting global changes of correlation structures than existing methods. Some theoretical guarantees for quantization algorithms based on dependent time sequences are also provided.
Fichier principal
Vignette du fichier
abats.pdf (1.63 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04604083 , version 1 (07-06-2024)

Identifiers

  • HAL Id : hal-04604083 , version 1

Cite

Frédéric Chazal, Clément Levrard, Martin Royer. Topological Analysis for Detecting Anomalies (TADA) in Time Series. 2024. ⟨hal-04604083⟩
48 View
62 Download

Share

Gmail Mastodon Facebook X LinkedIn More