Saved in:
Bibliographic Details
Main Authors: Correia, Lucas, Goos, Jan-Christoph, Klein, Philipp, Bäck, Thomas, Kononova, Anna V.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.06849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909898737975296
author Correia, Lucas
Goos, Jan-Christoph
Klein, Philipp
Bäck, Thomas
Kononova, Anna V.
author_facet Correia, Lucas
Goos, Jan-Christoph
Klein, Philipp
Bäck, Thomas
Kononova, Anna V.
contents As attention to recorded data grows in the realm of automotive testing and manual evaluation reaches its limits, there is a growing need for automatic online anomaly detection. This real-world data is complex in many ways and requires the modelling of testee behaviour. To address this, we propose a temporal variational autoencoder (TeVAE) that can detect anomalies with minimal false positives when trained on unlabelled data. Our approach also avoids the bypass phenomenon and introduces a new method to remap individual windows to a continuous time series. Furthermore, we propose metrics to evaluate the detection delay and root-cause capability of our approach and present results from experiments on a real-world industrial data set. When properly configured, TeVAE flags anomalies only 6% of the time wrongly and detects 65% of anomalies present. It also has the potential to perform well with a smaller training and validation subset but requires a more sophisticated threshold estimation method.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data
Correia, Lucas
Goos, Jan-Christoph
Klein, Philipp
Bäck, Thomas
Kononova, Anna V.
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
As attention to recorded data grows in the realm of automotive testing and manual evaluation reaches its limits, there is a growing need for automatic online anomaly detection. This real-world data is complex in many ways and requires the modelling of testee behaviour. To address this, we propose a temporal variational autoencoder (TeVAE) that can detect anomalies with minimal false positives when trained on unlabelled data. Our approach also avoids the bypass phenomenon and introduces a new method to remap individual windows to a continuous time series. Furthermore, we propose metrics to evaluate the detection delay and root-cause capability of our approach and present results from experiments on a real-world industrial data set. When properly configured, TeVAE flags anomalies only 6% of the time wrongly and detects 65% of anomalies present. It also has the potential to perform well with a smaller training and validation subset but requires a more sophisticated threshold estimation method.
title TeVAE: A Variational Autoencoder Approach for Discrete Online Anomaly Detection in Variable-state Multivariate Time-series Data
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2407.06849