The increase in vehicle ownership and urban population puts a strain on roads and increases traffic congestion within developed and developing nations. Congestion affects an individual’s time and increases an individual’s fuel consumption and pollution output, undercutting efforts towards smart/ sustainable cities. Outdated statistical congestion predicting methods do not account for the non-linear, dynamic nature of congestion with regards to external factors such as, weather, road incidents, and infrastructure. The adoption of machine and deep learning develops the framework towards adaptable and data-driven congestion predicting methods. This study develops a framework that combines the fundamentals of machine learning algorithms, Queuing Theory, Decision Trees, Random Forests, and Deep Belief Networks (DBN) for robust and interprefig traffic congestion forecasting. The traffic flow micro-dynamics integration with Queuing Theory and the use of historical/ real-time multimodal data such as sensor feeds, GPS trajectories, and incident reports as a basis for forecasting helps in robust congestion prediction. Polynomials of moving and rest queues with defined traffic characteristics fuel flow mechanisms. The designed framework uses the DBN and Queuing Theory for robust traffic forecasting.
Jha et al. (Fri,) studied this question.