Anomaly Detection in High-Dimensional Time Series Data with Scaled Bregman Divergence
Algorithms · 24.01.2025 · 18 (2) · 62
DOI: 10.3390/a18020062 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 24.01.2025. Verfasst von Yunge Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Statistics, Saint Louis University, St. Louis, MO 63103, USA. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, National Institute of General Medical Sciences of the National Institutes of Health, President’s Research Funds.
Abstract (Originalsprache)
The purpose of anomaly detection is to identify special data points or patterns that significantly deviate from the expected or typical behavior of the majority of the data, and it has a wide range of applications across various domains. Most existing statistical and machine learning-based anomaly detection algorithms face challenges when applied to high-dimensional data. For instance, the unconstrained least-squares importance fitting (uLSIF) method, a state-of-the-art anomaly detection approach, encounters the unboundedness problem under certain conditions. In this study, we propose a scaled Bregman divergence-based anomaly detection algorithm using both least absolute deviation and least-squares loss for parameter learning. This new algorithm effectively addresses the unboundedness problem, making it particularly suitable for high-dimensional data. The proposed technique was evaluated on both synthetic and real-world high-dimensional time series datasets, demonstrating its effectiveness in detecting anomalies. Its performance was also compared to other density ratio estimation-based anomaly detection methods.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics and Statistics, Saint Louis University, St. Louis, MO 63103, USA.
- Department of Mathematics and Statistics, University at Albany SUNY, Albany, NY 12222, USA.
- Mathematics Department, Culver-Stockton College, Canton, MO 63435, USA.
ORCID-Profile: Yunge Wang, Lingling Zhang, Tong Si, Haijun Gong
Förderung
- NIGMS NIH HHS
- National Institute of General Medical Sciences of the National Institutes of Health
- President’s Research Funds
Zitieren
APA
Wang, Y., Zhang, L., Si, T., Bishop, G., & Gong, H. (2025). Anomaly Detection in High-Dimensional Time Series Data with Scaled Bregman Divergence. Algorithms, 18(2), 62. https://doi.org/10.3390/a18020062
Vancouver
Wang Y, Zhang L, Si T, Bishop G, Gong H. Anomaly Detection in High-Dimensional Time Series Data with Scaled Bregman Divergence. Algorithms. 2025;18(2):62. doi:10.3390/a18020062
BibTeX
@article{Wang2025,
author = {Wang, Yunge and Zhang, Lingling and Si, Tong and Bishop, Graham and Gong, Haijun},
title = {Anomaly Detection in High-Dimensional Time Series Data with Scaled Bregman Divergence},
journal = {Algorithms},
year = {2025},
volume = {18},
number = {2},
pages = {62},
doi = {10.3390/a18020062}
}
EUVIMED