Traffic state estimation using hierarchical clustering and principal components analysis: a practical approach

Traffic state estimation and prediction are fundamental requirements for automatic control of urban road traffic with both adaptive traffic lights and variable message signs. For that, collecting of actual traffic data is necessary. This paper deals with the combined application of principal components analysis (PCA) and hierarchical cluster analysis (HCA) for the specification of the needed number of stationary road traffic sensors and their preferable locations within a given road network. Both methods are introduced briefly. A practicable procedure for using these methods is derived and it is shown that their combination is effective. First tests based on microscopic simulation data and on real volumes of inductive loops lead to plausible and promising results in application of the proposed procedure.