Publikationen_1920x250_Detail
In: IN4PL 2020, IN4PL 2021: Innovative Intelligent Industrial Production and Logistics, Springer

On Kernel Search Based Gaussian Process Anomaly Detection

Jan Hüwel , Andreas Besginow , Fabian Berns , Markus Lange-Hegermann und Christian Beecks,
Jul 2023

Anomaly detection becomes more important with increasing automation. Especially for time series data, prevalent in industry, there are numerous methods that have been well researched. In this work we provide a proof of concept for a novel approach using the interpretability of Gaussian processes. To detect an abnormal section, the data is split into equally sized segments which are then interpreted individually using separate kernel searches. The resulting kernels can then be compared and clustered by one of multiple presented methods. The segments that contain an anomaly end up in their own cluster.

To test all possible configurations of our proposed approach, we applied them to a subset of the SIGKDD 2021 anomaly dataset mutliple times and evaluated the results. Almost all configurations were able to succeed, although not yet reliably reproducible. The results of our performance evaluation indicate that kernel searches are in principle applicable to anomaly detection in univariate time series data.

Literatur Beschaffung: IN4PL 2020, IN4PL 2021: Innovative Intelligent Industrial Production and Logistics, Springer
@article{2652,
author= {Hüwel, Jan and Besginow, Andreas and Berns, Fabian and Lange-Hegermann, Markus and Beecks, Christian},
title= {On Kernel Search Based Gaussian Process Anomaly Detection},
journal= {Innovative Intelligent Industrial Production and Logistics},
year= {2023},
volume= {Communications in Computer and Information Science},
number= {},
pages= {1 -- 23},
month= {Jul},
note= {},
}