Automata Based Multivariate Time Series Analysis for Anomaly Detection over Sliding Time Windows

We describe an optimal linear time complexity method for extracting patterns from sliding windows of multivariate time series that depends only on the length of the time series. The method is implemented as an open-source Java library and is used to detect anomalies in multivariate time series.

Mots clés

multivariate time series transducers sliding windows anomaly detection

Domaines

Informatique [cs]

Fichier principal

engproc-39-00065.pdf (2.33 Mo)

Origine	Fichiers éditeurs autorisés sur une archive ouverte
Licence	Paternité

Nicolas Beldiceanu : Connectez-vous pour contacter le contributeur

https://hal.science/hal-04460520

Soumis le : jeudi 15 février 2024-18:04:02

Dernière modification le : mardi 17 septembre 2024-15:58:04

Archivage à long terme le : jeudi 16 mai 2024-20:06:28

Dates et versions

hal-04460520 , version 1 (15-02-2024)

Licence

Paternité

Identifiants

HAL Id : hal-04460520 , version 1
DOI : 10.3390/engproc2023039065

Citer

Arnold Hien, Nicolas Beldiceanu, Claude-Guy Quimper, Null- I Restrepo. Automata Based Multivariate Time Series Analysis for Anomaly Detection over Sliding Time Windows. 9th International Conference on Time Series and Forecasting, Jul 2023, Gran Canaria, Spain. ⟨10.3390/engproc2023039065⟩. ⟨hal-04460520⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CNRS INRIA EC-NANTES UNAM LS2N LS2N-TASC IMT-ATLANTIQUE LS2N-MODELIS NANTES-UNIVERSITE INSTITUT-MINES-TELECOM

31 Consultations

22 Téléchargements