loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

MA-VAE: Multi-Head Attention-Based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-Series Applied to Automotive Endurance Powertrain Testing

Topics: Applications: Image Processing and Artificial Vision, Pattern Recognition, Decision Making, Industrial and Real World Applications, Financial Applications, Neural Prostheses and Medical Applications, Neural Based Data Mining and Complex Information Process; Deep Learning; Recurrent Neural Networks

Authors: Lucas Correia 1 ; 2 ; Jan-Christoph Goos 1 ; Philipp Klein 1 ; Thomas Bäck 2 and Anna Kononova 2

Affiliations: 1 Mercedes-Benz AG, Stuttgart, Germany ; 2 Leiden University, Leiden, The Netherlands

Keyword(s): Anomaly Detection, Multivariate, Time Series, Automotive, Test Bench, Variational Autoencoder, Bypass Phenomenon.

Abstract: A clear need for automatic anomaly detection applied to automotive testing has emerged as more and more attention is paid to the data recorded and manual evaluation by humans reaches its capacity. Such real-world data is massive, diverse, multivariate and temporal in nature, therefore requiring modelling of the testee behaviour. We propose a variational autoencoder with multi-head attention (MA-VAE), which, when trained on unlabelled data, not only provides very few false positives but also manages to detect the majority of the anomalies presented. In addition to that, the approach offers a novel way to avoid the bypass phenomenon, an undesirable behaviour investigated in literature. Lastly, the approach also introduces a new method to remap individual windows to a continuous time series. The results are presented in the context of a real-world in-dustrial data set and several experiments are undertaken to further investigate certain aspects of the proposed model. When configured pro perly, it is 9% of the time wrong when an anomaly is flagged and discovers 67% of the anomalies present. Also, MA-VAE has the potential to perform well with only a fraction of the training and validation subset, however, to extract it, a more sophisticated threshold estimation method is required. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.137.211.49

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Correia, L. ; Goos, J. ; Klein, P. ; Bäck, T. and Kononova, A. (2023). MA-VAE: Multi-Head Attention-Based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-Series Applied to Automotive Endurance Powertrain Testing. In Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA; ISBN 978-989-758-674-3; ISSN 2184-3236, SciTePress, pages 407-418. DOI: 10.5220/0012163100003595

@conference{ncta23,
author={Lucas Correia and Jan{-}Christoph Goos and Philipp Klein and Thomas Bäck and Anna Kononova},
title={MA-VAE: Multi-Head Attention-Based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-Series Applied to Automotive Endurance Powertrain Testing},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA},
year={2023},
pages={407-418},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012163100003595},
isbn={978-989-758-674-3},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - NCTA
TI - MA-VAE: Multi-Head Attention-Based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-Series Applied to Automotive Endurance Powertrain Testing
SN - 978-989-758-674-3
IS - 2184-3236
AU - Correia, L.
AU - Goos, J.
AU - Klein, P.
AU - Bäck, T.
AU - Kononova, A.
PY - 2023
SP - 407
EP - 418
DO - 10.5220/0012163100003595
PB - SciTePress