Graph Structure Learning-Based Multivariate Time Series Anomaly Detection in Internet of Things for Human-Centric Consumer Applications
IEEE Transactions on Consumer Electronics · 2024-08 · 70 (3) · 5419-5431
DOI: 10.1109/tce.2024.3409391 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2024-08. Verfasst von Shiming He und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Innovation Program of Hunan Province, Scientific Research Fund of Hunan Provincial Transportation Department.
Abstract (Originalsprache)
As the Internet of Things system becomes more popular and ubiquitous, it has also gradually entered the consumer electronics field. For example, smart home systems have numerous sensors that monitor the environment and interact with the Internet to provide smart services. A large amount of multivariate time series data generated using sensors can provide services for consumers and identify faulty systems through multivariate time series anomaly detection (MTSAD), which is crucial for maintaining system stability. However, representing the complex relationships among multivariate time series is challenging. Recently, graph neural networks and graph structure learning, which can excellently learn complex time series relationships, have been applied to multivariate time series. However, existing research on graph structure learning only constructs k-Nearest Neighbor (kNN) graphs based on the pair-wise similarity between time series. This generates a quadratic cost and only considers partial relationships among sensors. Accordingly, we propose a lightweight graph structure learning-based multivariate time series anomaly detection (GSLAD), which exploits full graph parameterization to learn the graph structure without pair-wise similarity to overcome the quadratic cost and the limited neighbor relationship. GSLAD exploits diffusion convolutional recurrent neural network (DCRNN) to extract temporal and spatial features. The results from the extensive simulations performed on four public real-world datasets demonstrate that the F1 score improved by an average of 5% with less training time compared to existing state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
- Science and Technology Innovation Program of Hunan Province
- Scientific Research Fund of Hunan Provincial Transportation Department
- Open Fund of Key Laboratory of Safety Control of Bridge Engineering, Ministry of Education
- Open Research Fund of the Hunan Provincial Key Laboratory of Network Investigational Technology
- Researchers Supporting Project, King Saud University, Riyadh, Saudi Arabia
Zitieren
APA
He, S., Li, G., Yi, T., Alfarraj, O., Tolba, A., Sangaiah, A. K., & Sherratt, R. S. (2024). Graph Structure Learning-Based Multivariate Time Series Anomaly Detection in Internet of Things for Human-Centric Consumer Applications. IEEE Transactions on Consumer Electronics, 70(3), 5419-5431. https://doi.org/10.1109/tce.2024.3409391
Vancouver
He S, Li G, Yi T, Alfarraj O, Tolba A, Sangaiah AK, et al. Graph Structure Learning-Based Multivariate Time Series Anomaly Detection in Internet of Things for Human-Centric Consumer Applications. IEEE Transactions on Consumer Electronics. 2024;70(3):5419-5431. doi:10.1109/tce.2024.3409391
BibTeX
@article{He2024,
author = {He, Shiming and Li, Genxin and Yi, Tongzhijian and Alfarraj, Osama and Tolba, Amr and Sangaiah, Arun Kumar and Sherratt, R. Simon},
title = {Graph Structure Learning-Based Multivariate Time Series Anomaly Detection in Internet of Things for Human-Centric Consumer Applications},
journal = {IEEE Transactions on Consumer Electronics},
year = {2024},
volume = {70},
number = {3},
pages = {5419--5431},
doi = {10.1109/tce.2024.3409391}
}
EUVIMED