An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection

Miao, Qiucheng; Xu, Chuanfu; Zhan, Jianming; Zhu, Daiyin; Wu, Chengkun

doi:10.1007/978-981-99-1645-0_42

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 41 ], an anomaly detection method based on forecasting and reconstruction was proposed; the characteristics of short and long time series have been taken into consideration. Miao et al [ 43 ] proposed a time series anomaly detection method based on short-term and long-term mask representation learning. However, Informer [ 44 ] is a variant of Transformer that has favorable performance in long time series forecasting.…”

Section: Related Workmentioning

confidence: 99%

Graph Attention Network and Informer for Multivariate Time Series Anomaly Detection

Zhao,

Peng,

et al. 2024

Sensors

View full text Add to dashboard Cite

Time series anomaly detection is very important to ensure the security of industrial control systems (ICSs). Many algorithms have performed well in anomaly detection. However, the performance of most of these algorithms decreases sharply with the increase in feature dimension. This paper proposes an anomaly detection scheme based on Graph Attention Network (GAT) and Informer. GAT learns sequential characteristics effectively, and Informer performs excellently in long time series prediction. In addition, long-time forecasting loss and short-time forecasting loss are used to detect multivariate time series anomalies. Short-time forecasting is used to predict the next time value, and long-time forecasting is employed to assist the short-time prediction. We conduct a large number of experiments on industrial control system datasets SWaT and WADI. Compared with most advanced methods, we achieve competitive results, especially on higher-dimensional datasets. Moreover, the proposed method can accurately locate anomalies and realize interpretability.

show abstract

Section: Related Workmentioning

confidence: 99%