Overcoming uncertainty of roadside sensors with smart adaptive traffic congestion analysis system

Real time traffic congestion degree is useful information in assisting decision making of drivers. It can also be a factor for calculating other traffic information. The congestion degree can be usually calculated on the basis of sensors installed along roads. It is possible that the sensory data can be lost due to potentially unreliable communication or faulty sensors, leading to lost of important traffic data. In this paper, we propose both adaptive traffic congestion analysis system architecture as well as a novel traffic congestion estimation algorithm that can compensate missing sensory data. An ability to provide traffic condition of road segments at all time is feasible. Unlike other existing methods, our approach aims not to rely on only traffic data from sensors, but utilize discoverable external context instead. The promising experiment result and analysis are reported in this paper. In addition, the context attribute correlation analysis is also discussed.