Search papers, labs, and topics across Lattice.
This paper introduces a Multi-View Coupled Tensor Decomposition (MVCTD) model designed for online traffic prediction using imperfect multi-view observations such as speed, flow, and occupancy. By leveraging coupled tensor decomposition and group sparse regularization, the model effectively captures shared spatial structures and specific temporal dynamics while mitigating the impact of traffic anomalies on forecasts. Experimental results on real-world datasets show that MVCTD delivers accurate predictions with efficient runtime, even in scenarios with significant data missingness, highlighting its potential for intelligent transportation systems.
Traffic prediction accuracy can be maintained even under severe data missingness using a novel multi-view approach that adapts in real-time.
Accurate online traffic prediction is essential for intelligent transportation systems, where forecasting must be performed continuously under imperfect sensing conditions. Missing observations and anomalous disturbances make this task challenging, particularly when prediction relies on a single traffic view. This paper proposes a Multi-View Coupled Tensor Decomposition (MVCTD) model for online traffic prediction from imperfect multi-view observations, such as speed, flow, and occupancy. The proposed model uses coupled tensor decomposition to build a structured latent forecasting space, in which shared spatial structures across traffic views and view-specific temporal dynamics are jointly modeled. A group sparse regularization is further introduced to capture correlated abnormal responses induced by real traffic anomalies and thus reduce their influence on forecasts. For streaming deployment, MVCTD performs iterative refinement only on the current latent tensor, while the remaining model variables are updated by lightweight closed-form steps based on summarized historical information, thereby avoiding repeated optimization over the full historical sequence. Experiments on real-world traffic datasets demonstrate that MVCTD achieves accurate forecasts with favorable runtime under severe missingness, confirming its suitability for online traffic prediction.
