Causal Modeling of Traffic Events

jkim_bn_illustrationThis research aims to use big data analytics to enable the prediction of future traffic states to provide Traffic Management Centers (TMCs) with enhanced awareness of network conditions and risks and an ability to proactively respond.

We develop probabilistic graphical models (e.g., Bayesian Networks) and other statistical learning models that learn causal, spatio-temporal dependence relations between network conditions and traffic states from large-scale, multi-source data to predict the future states given various road condition scenarios.


Related Papers: