Spatio-temporal low-rank sparse tensor model and its application in urban anomaly analysis
Date:
In this study, we propose a comprehensive framework for traffic anomaly diagnosis based on tensor theory and GIScience methods, which is divided into three parts: road traffic status acquisition, traffic anomaly detection, and urban anomaly analysis. In terms of traffic anomaly detection, a novel Spatio-Temporal constrained Low-Rank Sparse Tensor (ST-LRST) method is proposed to decompose urban traffic data into normal and anomalous components. For anomaly analysis, we analyze the characteristics of the anomalies detected by ST-LRST, such as duration, impact scope, and impact intensity. Then, combined with crowdsourced geographic information, we conduct a comprehensive analysis of the spatial and temporal anomalous variations in the road network and explain the inducing factors of urban anomalies.