IEEE

A Lightweight Recurrent Architecture for Robust Urban Traffic Forecasting With Missing Data

Abstract: Real-time traffic flow prediction plays a vital role in alleviating urban congestion and improving transportation efficiency. However, urban traffic data are often subject to sensor ...
IEEE

V-DCRNN: Virtual Network-Based Diffusion Convolutional Recurrent Neural Network for Estimating Unobserved Traffic Data

Abstract: Several studies have analyzed traffic patterns using Vehicle Detector (VD) and Global Positioning System (GPS) data. VD records the speed of vehicles passing through detectors, GPS data ...