An interactive threshold-setting procedure for improved multivariate anomaly detection in time series

Anomaly detection in multivariate time series is valuable for many applications. In this context, unsupervised and semi-supervised deep learning methods that estimate how normal a new observation is have shown promising results on benchmark datasets. These methods are dependent on a threshold that d...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2023-01, Vol.11, p.1-1
Hauptverfasser:	Lundstrom, Adam, O'Nils, Mattias, Qureshi, Faisal Z.
Format:	Artikel
Sprache:	eng
Schlagworte:	Anomalies Anomaly detection Anomaly scoring Data models Deep learning Electronic mail Multivariate analysis Multivariate regression Multivariate time series (MVTS) Time series Time series analysis Time-domain analysis Training Training data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!