Smart City Gnosys

Smart city article details

Title	A Novel Anomaly Detection Method For Multivariate Time Series Based On Spatial-Temporal Graph Learning
ID_Doc	3214
Authors	Zhang J.; Wang X.; Yang Y.; Miao H.; Yang S.
Year	2025
Published	Journal of King Saud University - Computer and Information Sciences, 37, 1
DOI	http://dx.doi.org/10.1007/s44443-025-00024-3
Abstract	Anomaly detection for multivariate time series is crucial in real-world applications, including industrial equipment monitoring and predictive maintenance, financial risk management, smart city and traffic management, as well as environmental monitoring. However, the multivariate time series data exhibit high dimensionality, complex spatiotemporal dependencies, and nonlinear interactions between variables, making anomaly detection in such data a significant challenge. Most existing methods struggle to effectively capture these complex nonlinear relationships or explicitly model the spatiotemporal dependencies in multivariate time series. To address these limitations, we propose a novel approach for multivariate time series anomaly detection, called long short-term memory, temporal convolution and graph convolution (LTG), which is based on spatial-temporal graph learning. LTG uses Correlation Learning (CL) layer to acquire pairwise correlations, generating a graph adjacency matrix. This matrix is then fed into a Spatiotemporal Graph Neural Network (STGNN), composed of a Long Short-Term Memory (LSTM) Network, a Temporal Convolution Network (TCN), and a Graph Convolution Network (GCN), to capture the rich temporal and spatial dependencies in multivariate time series and accurately model these relationships. Finally, a PCA-based anomaly scorer is employed to output anomaly scores. Experimental results show that on the WADI and SMD datasets, LTG outperforms the state-of-the-art multivariate anomaly detection framework correlation-aware spatial-temporal graph learning (CST-GL) in both overall detection and early detection performance. Notably, on the WADI dataset, LTG’s average early detection performance across 6 different delay-constrained time points exceeds CST-GL by 10.64 percentage points. © The Author(s) 2025.
Author Keywords	Anomaly detection; Cyber-physical systems; Multivariate time series; Spatial-temporal graph learning

Similar Articles

Id	Similarity	Authors	Title	Published
13349	0.901	Zhang X.; Zhang J.; Wang C.; Lin F.; Li Z.	Canet: Convolutional Attention-Based Network For Multivariate Time Series Anomaly Detection	2022 7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022 (2022)
22095	0.86	Hao J.; Chen P.; Chen J.; Li X.	Effectively Detecting And Diagnosing Distributed Multivariate Time Series Anomalies Via Unsupervised Federated Hypernetwork	Information Processing and Management, 62, 4 (2025)
6743	0.86	Zhu H.; Liu S.; Jiang F.	Adversarial Training Of Lstm-Ed Based Anomaly Detection For Complex Time-Series In Cyber-Physical-Social Systems	Pattern Recognition Letters, 164 (2022)
20803	0.856	Wang S.; Chen Y.; Xu H.; Hu J.; Zeng P.; Hu Z.	Dngnn: Efficient Deep Noisy Graph Neural Network For Spatio-Temporal Series Forecasting	2025 2nd International Conference on Algorithms, Software Engineering and Network Security, ASENS 2025 (2025)
35807	0.856	Huang L.; Huang J.; Li H.; Cui J.	Lstgcn: Inductive Spatial Temporal Imputation Using Long Short-Term Dependencies	ACM Transactions on Knowledge Discovery from Data, 18, 9 (2024)
1384	0.853	He J.; Dong M.; Bi S.; Zhao W.; Liao X.	A Deep Neural Network For Anomaly Detection And Forecasting For Multivariate Time Series In Smart City	9th IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, CYBER 2019 (2019)
59799	0.85	Toor A.A.; Lin J.-C.; Gran E.G.	Uocad2: An Unsupervised Online Contextual Anomaly Detection Approach Using Optimized Hyperparameters Of Rnns For Multivariate Time Series	Internet of Things (The Netherlands), 33 (2025)