Inferring the most popular route based on ant colony optimization with trajectory data

Abstract

The development of big data technologies makes it possible to derive valuable information from the history trajectory data. An algorithm is proposed to discover the most popular route from the given source to the given destination in this paper. The region is latticed into regular grids and then the history trajectories are discretized according to the aforementioned grids. Afterwards, the most popular route is determinated by the ant colony optimization method, where the actions of the ants are inspired by the statistics of the history trajectories which lead to the destination or at least near the destination. The grid size and the ant colony parameters are adjustable to fulfil the requirements of the solution precision and the computation complexity. The experiments are performed on the real vehicle trajectory dataset and the results meet our common sense of the popular routes.