EUVIMEDEUVIMED entdecken
Crossref

Conditional normalizing flow for multivariate time series anomaly detection

Siwei Guan, Zhiwei He, Shenhui Ma, Mingyu Gao

ISA Transactions · 2023-12 · 143 · 231-243

DOI: 10.1016/j.isatra.2023.09.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2023-12. Verfasst von Siwei Guan und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information, Hangzhou Dianzi University, Hangzhou, Zhejiang Province, China; Zhejiang Provincial Key Lab of Equipment Electronic…. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Key Research and Development Program of Zhejiang Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multivariate time series data is becoming increasingly ubiquitous in various fields such as servers, industrial applications, and healthcare. However, detecting anomalies in such data is challenging due to its complex time-dependent, high-dimensional, and label scarcity. Aiming at this problem, this paper proposes an Attention Factorization Normalizing Flow (AFNF) algorithm for unsupervised multivariate time series anomaly detection. Our hypothesis is that anomalies are in a low-density region of the distribution. To transform the complex density of high-dimensional time series into a simple evaluable conditional density, we propose a time series factorization strategy and parameterize the conditional information generated by factorization in the time and attribute dimensions using an attention mechanism. Moreover, to compensate for the lack of temporal information due to the permutation invariance attention mechanism, a adjacency contrasting approach is proposed to model the local invariance of the time series. To provide long-term location information, a learnable global location encoding is introduced. Conditional normalizing flows are applied to evaluate the conditional probability of the observations. Finally, through extensive experiments on three real data sets, our method yielded the best results and its effectiveness in density estimation and anomaly detection is demonstrated.

Schlagwörter

Stichwörter der Autor:innen

Anomaly detectionAttention mechanismMultivariate time seriesNormalizing flow

Autor:innen und Institutionen

  • School of Electronic Information, Hangzhou Dianzi University, Hangzhou, Zhejiang Province, China; Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, Zhejiang Province, China. Electronic address: guansw@hdu.…
  • School of Electronic Information, Hangzhou Dianzi University, Hangzhou, Zhejiang Province, China; Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, Zhejiang Province, China. Electronic address: zwhe@hdu.ed…
  • School of Electronic Information, Hangzhou Dianzi University, Hangzhou, Zhejiang Province, China; Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, Zhejiang Province, China. Electronic address: mash@hdu.ed…
  • School of Electronic Information, Hangzhou Dianzi University, Hangzhou, Zhejiang Province, China; Zhejiang Provincial Key Lab of Equipment Electronics, Hangzhou, Zhejiang Province, China. Electronic address: mackgao@hdu…

Förderung

  • National Key Research and Development Program of China
  • Key Research and Development Program of Zhejiang Province
  • National Natural Science Foundation of China

Zitieren

APA

Guan, S., He, Z., Ma, S., & Gao, M. (2023). Conditional normalizing flow for multivariate time series anomaly detection. ISA Transactions, 143, 231-243. https://doi.org/10.1016/j.isatra.2023.09.002

Vancouver

Guan S, He Z, Ma S, Gao M. Conditional normalizing flow for multivariate time series anomaly detection. ISA Transactions. 2023;143:231-243. doi:10.1016/j.isatra.2023.09.002

BibTeX
@article{Guan2023,
  author = {Guan, Siwei and He, Zhiwei and Ma, Shenhui and Gao, Mingyu},
  title = {Conditional normalizing flow for multivariate time series anomaly detection},
  journal = {ISA Transactions},
  year = {2023},
  volume = {143},
  pages = {231--243},
  doi = {10.1016/j.isatra.2023.09.002}
}
Kostenlos starten →