T‐VAE: Transformer‐Based Variational AutoEncoder for Perceiving Anomalies in Multivariate Time Series Data

ABSTRACT Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expert systems Jg. 42; H. 7
Hauptverfasser: Li, Chang, Kiat, Yeo Chai, Jing, Jiwu, Long, Chun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford Blackwell Publishing Ltd 01.07.2025
Schlagworte:
Ablation
anomaly perception
Multivariate analysis
Perception
Representations
Sensitivity analysis
Time series
time series data
transformer
variational auto‐encoder
Volatility
ISSN:0266-4720, 1468-0394
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:ABSTRACT Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among high‐dimensional samples and features, can be complex and nonlinear. Additionally, the time series data often exhibit high volatility and are interspersed with noise data. These factors make anomaly perception in multivariate time series challenging. Despite the recent development of deep learning methods, only a few are able to address all of these challenges. In this paper, we propose a Transformer‐based Variational AutoEncoder (T‐VAE) for anomaly perception in multivariate time series data. The T‐VAE consists of two sub‐networks, the Representation Network and the Memory Network, and achieves end‐to‐end jointly optimisation. The Representation Network leverages self‐attention mechanisms and residual network structures to capture sequence information and metaphorical patterns from multivariate time series data. The Memory Network employs a Variational AutoEncoder to learn the distribution of normal data. It employs Maximum Mean Discrepancy to approximate the distribution of high‐volatility and noisy data to the distribution of the normal data. We evaluate T‐VAE on five datasets, showing superior performance and validating its effectiveness and robustness through comprehensive ablation studies and sensitivity analyses.
Bibliographie:Funding
This work is supported by the National Key Research and Development Program of China (Grant No: 2023YFC3304704), and the Youth Innovation Promotion Association of the Chinese Academy of Sciences (Grant No: 2023181).
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0266-4720
1468-0394
DOI:10.1111/exsy.70078