From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
Researchers have developed a new framework called the Spatial-Temporal Refinement Predictor (STRP) to address the challenge of predicting fine-grained traffic data from coarser sampled information. STRP utilizes Tree Convolution for spatial dependencies and Inverse Dilated Convolution for temporal extrapolation. Experiments on six datasets demonstrated that STRP significantly improves accuracy and efficiency over existing methods, offering a practical solution for managing temporal granularity mismatches in traffic data systems. AI
IMPACT Offers a practical approach to improving traffic prediction accuracy and efficiency by bridging temporal granularity gaps in data.