On the Application of Time-Series Foundation Models for Detecting Long-Context Anomalies in Industrial Control Systems
This work explores the application of pre-trained time-series foundation models (FMs) for detecting anomalies in industrial processes and introduces a new time-series forecasting method that filters out suspicious data and uses previously predicted data as input, called Forecast Fallback (FF).
A. Lowe, Clement Fung, Lujo Bauer
· 0 citations