Open access
Jul 2026
U-GRU for Short-Term Urban Traffic Speed Forecasting with Ordered-Node Feature Transformation and Channel–Temporal Recalibration
This study proposes U-GRU, a staged forecasting model that integrates node-wise gated recurrent temporal encoding, a one-dimensional U-Net-based ordered-node feature transformation module, external-feature alignment and channel–temporal recalibration for short-term traffic speed forecasting.
Chuanbin Shao, Jiejin Qi, Guijie Zhang
· Applied Sciences · 0 citations