An adaptive approach to enhanced traffic signal optimization by using soft-computing techniques

This paper presents an application of diverse soft-computing techniques to adaptive traffic light controls. The proposed methodology consists of two main phases: off-line and on-line. First, clustering techniques and optimization methods are used at the off-line stage to discover the prototypes which characterize the traffic mobility patterns at an intersection. After this process an optimum timing plan is decided for each mobility pattern detected. In the on-line phase, a prediction model is then constructed on the basis of the prototypes found. Fuzzy Logic based techniques are used to formally represent the prototypes in the prediction model and these prototypes are parametrically defined through frameworks. During the on-line phase an intelligent transportation system, by using the prediction model, matches the current traffic conditions to the mobility patterns detected at the off-line stage in order to identify the most suitable one to be used. The use of these techniques supposes a substantial contribution to the significance of the prediction model, making it robust in the face of anomalous mobility patterns, and efficient from the point of view of real-time computation.