A Lightweight Recurrent Architecture for Robust Urban Traffic Forecasting With Missing Data
· One min read
Link : https://ieeexplore.ieee.org/document/11162586
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 anomalies, missing values, and unstable model performance. To address these challenges, this paper proposes a lightweight and robust recurrent neural network architecture