Physics-Informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed By Second-Order Traffic Models

Traffic Prediction using a Deep Learning Paradigm

For many years intelligent transportation systems (ITS) have been collecting and processing huge amounts of data from numerous sensors to generate a ground truth of urban traffic. Such data has set the foundation of traffic theory, planning and simulation to create rule-based systems. It has also been used in many different studies in data-driven short-term traffic flow forecasting with promisi...

A Hybrid Optimization Algorithm for Learning Deep Models

Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...

A Hybrid Optimization Algorithm for Learning Deep Models

Deep learning is one of the subsets of machine learning that is widely used in Artificial Intelligence (AI) field such as natural language processing and machine vision. The learning algorithms require optimization in multiple aspects. Generally, model-based inferences need to solve an optimized problem. In deep learning, the most important problem that can be solved by optimization is neural n...

Resurrection of "Second Order" Models of Traffic Flow

We introduce a new “second order” model of traffic flow. As noted in [C. Daganzo, Requiem for second-order fluid with approximation to traffic flow, Transportation Res. Part B, 29 (1995), pp. 277–286], the previous “second order” models, i.e., models with two equations (mass and “momentum”), lead to nonphysical effects, probably because they try to mimic the gas dynamics equations, with an unre...

Hybrid traffic state estimation and prediction using pattern recognition