DeepHYDRA: Resource-Efficient Time-Series Anomaly Detection in Dynamically-Configured Systems

1 code implementation • 13 May 2024 • Franz Kevin Stehle, Wainer Vandelli, Giuseppe Avolio, Felix Zahn, Holger Fröning

A downside of such methods is that they require a static input size, or lose data through cropping, sampling, or other dimensionality reduction methods, making deployment on systems with variability on monitored data channels, such as computing clusters difficult.

Anomaly Detection Dimensionality Reduction +3