ESTIMATION OF DELAY AND VEHICLE STOPS AT SIGNALIZED INTERSECTIONS USING ARTIFICIAL NEURAL NETWORK

Delay and number of vehicle stops are important indicators that define the level of service of a signalized intersection. Therefore, they are usually considered for optimizing the traffic signal timing. In this study, ANNs are employed to model delay and the number of stops estimation at signalized intersections. Intersection approach volumes, cycle length and left turn lane existence were utilized as input variables since they could easily be obtained from field surveys. On the other hand, the average delay and the number of stops per vehicle were used as the output variables for the ANNs models. Four-leg intersections were examined in this study. Approach volumes including turning volumes are randomly generated for each lane of these intersections, then the traffic simulation program was run 196 times with each generated data. Finally, average delay and the number of stops per vehicle were obtained from the simulations as outputs. In this study, various network architectures were analyzed to get the best architecture that provides the best performance. The results show that the ANNs model has potential to estimate delays and number of vehicle stops.