We are dedicated to designing transferable and self-adaptive models capable of handling dynamic changes and addressing data insufficiency challenges in short-term traffic prediction. Our research explores both model-based and sample-based transfer strategies to uncover the underlying principles of transferable features, ensuring robust and efficient adaptation across diverse traffic environments. By leveraging these strategies, we aim to enhance the generalizability of traffic prediction models, enabling them to operate effectively in complex, volatile, and data-scarce scenarios.
TSE Lab is part of a key program project that was awarded by the Chinese Minstry of Science and Technology with a total funding of ¥20m RMB to investigate the technologies and theories for cooperative transportation management and control systems (grant no. 2018YFB1600500).
The project is led by Beijing University of Aeronautics and Astronautics. A consortium includes Tsinghua University, Tongji University, Jilin University and Zhejiang University who will work together aim to advance our understandings on potential impacts of connected autonomous vehicles (CAVs) on our society and develop models and theories to optimize the transportation system with different levels of market penetration of CAVs.
The project is led by Dr Simon Hu to develop methods of real-time traffic and air quality management and decision support systems for urban traffic operation. We propose an urban traffic decision support system which will rely on statistical learning and cloud computing to process massive, multi-source, and heterogeneous traffic and pollutant data. Such system will be able to generate nonlinear but computationally efficient real-time relationships between multiresolution urban road traffic states and environmental measures of effectiveness to support proactive traffic control (e.