Traffic dynamics estimation by using raw floating car data

摘要: Massive datasets of Floating Car Data (FCD) are collected and thereafter processed to estimate predict traffic conditions. In the framework short-term forecasting, machine learning techniques have become very popular. However, big available today contain for most part easily predictable data, that data observed during recurrent Integration different with engineering notions must contribute obtain new transportation-oriented data-driven methods. this paper we address dynamics estimation by using individual FCD in order develop an integrative able recognize select suitable method forecasting. Taking into account spatial distributions positions retrieve a spatial-based criterion integration models.