Paper
2 May 2023 TAGAN: multivariate time series anomaly detection algorithm with attention and generative adversarial network
Xinyu Jia, Wenbo Zhang, Xinzhi Yang
Author Affiliations +
Proceedings Volume 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023); 126421X (2023) https://doi.org/10.1117/12.2674966
Event: Second International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT 2023), 2023, Xishuangbanna, China
Abstract
In this paper, a new anomaly detection architecture, TAGAN, is proposed. By combining the reconstruction approach with the prediction approach, TAGAN is used for anomaly detection over multivariate time series. A new loss function based on Wasserstein distance with gradient penalty is introduced in the reconstruction branch, and attention mechanism is introduced in the prediction branch. The performances of the proposed algorithm are tested over four real-world datasets (MSL, SMAP, SMD, and SWaT). Numerical experiments show that the proposed algorithm performs better than that of six anomaly detection algorithms.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinyu Jia, Wenbo Zhang, and Xinzhi Yang "TAGAN: multivariate time series anomaly detection algorithm with attention and generative adversarial network", Proc. SPIE 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023), 126421X (2 May 2023); https://doi.org/10.1117/12.2674966
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Reconstruction algorithms

Transformers

Adversarial training

Network architectures

Performance modeling

Time series analysis

Back to Top