Investigating lane-changing moves of vehicles departing from signalized junction

Abstract

ABSTRACT Discretionary Lane-Changing (DLC) possesses different characteristics under various traffic conditions. Therefore, in order to model DLC moves in the correct manner, they need to be approached separately for various conditions. This study has examined the DLC moves of vehicles, which depart from signalized junction. It is observed that a large number of vehicles move to a neighboring lane in order to travel under better traffic conditions, after the traffic lights turn green. There are many parameters, which motivate the vehicles to change lanes at this stage. This study has focused on discovering these parameters. Data was collected through field work for this purpose. Thereinafter, the impact value of each parameter has been discovered using four separate feature selection methods and has been sorted. Fuzzy Cognitive Maps have been developed with the obtained impact values. The models have been validated using the field data and have been compared with each other.