Real-time traffic prediction is the process of combing information from empirical data with a dynamic traffic prediction model to provide a robust and complete description of traffic states in time and space (e.g. transitions from free-flow to congestion) in the short-term. In recent years rapid advances in information technology have led to various data collection systems which enrich the sources of empirical data for use in transport systems. In practice, traffic data are collected from loop detectors, probe vehicles, cell-phones, Bluetooth, video cameras, remote sensing and public transport smartcards. It has been argued that using data from multiple sources will generally result in better accuracy, increased robustness and confidence, as one data collection method can collect information where others are unavailable; reduced ambiguity, enhanced spatial and temporal coverage as new data sources can work when or where another sensor cannot. Our research aims at developing a new method to build up a real-time traffic prediction model for arterial corridors using data from multiple sources, particularly from loop detectors and partial observation from Bluetooth and GPS devices.
Back to Workshop II: Traffic Estimation