Learning from user's behaviour of some well-known congested traffic networks
By: Isolda Cardoso, Lucas Venturato, Jorgelina Walpen
Potential Business Impact:
Predicts traffic jams to help cars move faster.
We consider the problem of predicting users' behavior of a congested traffic network under an equilibrium condition, the traffic assignment problem. We propose a two-stage machine learning approach which couples a neural network with a fixed point algorithm, and we evaluate its performance along several classical congested traffic networks.
Similar Papers
Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment
Machine Learning (CS)
Predicts traffic jams faster for city planning.
Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling
Machine Learning (CS)
Predicts traffic jams from road work faster.
From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem
Machine Learning (CS)
Speeds up traffic planning by predicting road use.