A Multivariate Time Series Anomaly Detection Model Based on Spatio-Temporal Dual Features

This paper proposes a novel unsupervised model for multivariate time series anomaly detection (TSAD), targeting the challenges of sparse and unlabeled abnormal data, as well as high dimensionality in IoT applications. The core of our model is to extract spatiotemporal dual features through a coheren...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 International Conference on Networking and Network Applications (NaNA) S. 416 - 421
Hauptverfasser: Wang, Fangwei, Yan, Man, Li, Qingru, Wang, Changguang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.08.2023
Schlagworte:
Anomaly detection
Computational modeling
Data models
Deep convolutional autoencoder
Feature extraction
Stability analysis
Time series
Time series analysis
Transformer
Transformer cores
Transformers
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper proposes a novel unsupervised model for multivariate time series anomaly detection (TSAD), targeting the challenges of sparse and unlabeled abnormal data, as well as high dimensionality in IoT applications. The core of our model is to extract spatiotemporal dual features through a coherent architecture that captures both temporal dependencies and spatial correlations among multiple variables. Specifically, a deep autoencoder is employed to capture the spatial features of multivariate time series data, while a multi-scale sparse Transformer network is used to extract the temporal features. An anomaly detection module based on the dynamic threshold POT method is used for detect anomalies, and extensive experiments are conducted on publicly available datasets. The result on the SMAP dataset show that our proposed model improves the precision and F1 score by 11.3% and 5.48% respectively compared with the latest baseline method. On the NAB dataset, the F1 score is increased by 0.47%. On the SWaT dataset, the precision is improved by 0.62%.
DOI:10.1109/NaNA60121.2023.00075