SpinFlow parametrizes traffic phases with a latent spin vector and competitive-equilibrium mapping, then uses physics-regularized EM to invert the field from trajectories and localize transitions via a new PED metric.
A review of hybrid physics-based machine learning approaches in traffic state estimation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.soc-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SpinFlow: A Physics-Informed Spin Field Framework for Traffic Phase Inference and Transition Detection
SpinFlow parametrizes traffic phases with a latent spin vector and competitive-equilibrium mapping, then uses physics-regularized EM to invert the field from trajectories and localize transitions via a new PED metric.