A Method for Detecting Spatio-temporal Correlation Anomalies of WSN Nodes Based on Topological Information Enhancement and Time-frequency Feature Extraction

2026-01-17

AI Summary

This work addresses the limitations of existing anomaly detection methods in wireless sensor networks, which often fail to effectively model spatiotemporal dependencies and are typically confined to either time- or frequency-domain features, resulting in high computational costs. To overcome these challenges, the authors propose TE-MSTAD, a novel approach that integrates graph neural networks with the RWKV linear attention mechanism within a dual-branch architecture to jointly learn time-frequency features and dynamic topological structures. The method further incorporates a cross-modal feature extraction module and a learnable adjacency matrix to transcend the constraints of single-domain representations. Evaluated on both public and real-world datasets, TE-MSTAD achieves F1 scores of 92.52% and 93.28%, respectively, significantly outperforming state-of-the-art methods and demonstrating superior detection performance and generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Existing anomaly detection methods for Wireless Sensor Networks (WSNs) generally suffer from insufficient ex-traction of spatio-temporal correlation features, reliance on either time-domain or frequency-domain information alone, and high computational overhead. To address these limitations, this paper proposes a topology-enhanced spatio-temporal feature fusion anomaly detection method, TE-MSTAD. First, building upon the RWKV model with linear attention mechanisms, a Cross-modal Feature Extraction (CFE) module is introduced to fully extract spatial correlation features among multiple nodes while reducing computational resource consumption. Second, a strategy is designed to construct an adjacency matrix by jointly learning spatial correlation from time-frequency domain features. Different graph neural networks are integrated to enhance spatial correlation feature extraction, thereby fully capturing spatial relationships among multiple nodes. Finally, a dual-branch network TE-MSTAD is designed for time-frequency domain feature fusion, overcoming the limitations of relying solely on the time or frequency domain to improve WSN anomaly detection performance. Testing on both public and real-world datasets demonstrates that the TE-MSTAD model achieves F1 scores of 92.52% and 93.28%, respectively, exhibiting superior detection performance and generalization capabilities compared to existing methods.

Problem

• Wireless Sensor Networks
• anomaly detection
• spatio-temporal correlation
• time-frequency features
• computational overhead

Innovation

• spatio-temporal correlation
• time-frequency feature fusion
• topology-enhanced GNN
• cross-modal feature extraction
• anomaly detection