Data-driven modeling for crowd dynamics

Predicting the behaviors of pedestrian crowds is of critical importance for a variety of real-world problems. Data driven modeling, which aims to learn the mathematical models from observed data, is a promising tool to construct models that can make accurate predictions of such systems. In this project, we will develop data-driven modeling approachs with the state-of-the-art machine learning techniques, for constructing continuous-time models of crowd dynamics. We will tackle several challenging issues in such problems, which are primarily associated with the dimensionality of the underlying crowd system. In particular we plan to incoperate mechanism-based prior knowledge into the modeling process. The proposed methods will be applied to a range of real-world problems involving crowd dynamics.