• Publications
  • Influence
Online Freeway Traffic Estimation with Real Floating Car Data
The main challenges originating from the sparseness and delay in collecting FCD are addressed and a procedure using the GASM is proposed that allows estimating traffic velocities continuously and outperforms naïve approaches in almost all considered setups. Expand
A phase-based smoothing method for accurate traffic speed estimation with floating car data
The quantitative and qualitative results show that the proposed Phase-Based Smoothing Method reconstructs the congestion pattern more accurately than the other two and is therefore more accurate even if the input data density is low. Expand
Combinatorial Reinforcement Learning of Linear Assignment Problems
It is shown that reinforcement learning can solve small symmetric bipartite maximum matching problems close to linear programming quality, but on the other hand is outperformed for large-scale asymmetric problems by linear programming-based and nearest neighbor-based algorithms subject to the constraint of achieving conflict-free solutions. Expand
Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approach
A dedicated Deep Neural Network architecture that reconstructs space-time traffic speeds on freeways given sparse data using a large dataset of sparse speed data, in particular from probe vehicles is presented. Expand