Adaptive Unsupervised Anomaly Detection for Low-Quality Multivariate Time-Series Data
IEEE Transactions on Knowledge and Data Engineering · 2026-08 · 38 (8) · 4851-4867
DOI: 10.1109/tkde.2026.3700672 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-08. Verfasst von Jiayi Liu und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation.
Abstract (Originalsprache)
How should we perform anomaly detection on multivariate time-series data with missing data, attribute misplacement and concept drift? The majority of existing anomaly detection methods overlook the fact that data are often of low quality. To address this challenge, we propose an adaptive unsupervised anomaly detection method for low-quality multivariate time series data. Our method introduces a self-attention mechanism that integrates masked information and missing length information to enhance the model's capability in handling incomplete data. Furthermore, we design a deep probabilistic adaptive memory network to improve the model's adaptability to attribute misplacement and concept drift. We also discuss the optimal window size for effectively dealing with concept drift. Comparative experiments on multiple real-world datasets demonstrate that our method can effectively detect anomalies in low-quality multivariate time series data. The experimental results further highlight the robustness of our model, proving its ability to maintain high performance in the presence of data quality issues.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Shandong Provincial Natural Science Foundation
Zitieren
APA
Liu, J., Yang, D., Wang, J., Gao, H., & Li, J. (2026). Adaptive Unsupervised Anomaly Detection for Low-Quality Multivariate Time-Series Data. IEEE Transactions on Knowledge and Data Engineering, 38(8), 4851-4867. https://doi.org/10.1109/tkde.2026.3700672
Vancouver
Liu J, Yang D, Wang J, Gao H, Li J. Adaptive Unsupervised Anomaly Detection for Low-Quality Multivariate Time-Series Data. IEEE Transactions on Knowledge and Data Engineering. 2026;38(8):4851-4867. doi:10.1109/tkde.2026.3700672
BibTeX
@article{Liu2026,
author = {Liu, Jiayi and Yang, Donghua and Wang, Jinbao and Gao, Hong and Li, Jianzhong},
title = {Adaptive Unsupervised Anomaly Detection for Low-Quality Multivariate Time-Series Data},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2026},
volume = {38},
number = {8},
pages = {4851--4867},
doi = {10.1109/tkde.2026.3700672}
}
EUVIMED