نوع مقاله : مقاله پژوهشی
نویسنده
استادیار، گروه مهندسی عمران، دانشکده مهندسی، دانشگاه گلستان،گرگان، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسنده [English]
The purpose of this paper was to identify and investigate the possibility of obtaining turning volumes from existing signal control devices and investigate their accuracy. A large majority of signalized intersections operate under inductive loops. A macroscopic study was performed on two intersections. The detector accuracy was interpreted in terms of Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). Results showed that counts were not reliable. However, by using Genetic Programming (GP) and Adaptive Neuro-Fuzzy Inference System (ANFIS), detector counts were modified and again MAPE was calculated. The proposed method for modifying detector counts did not guarantee reliable counts in all situations. Therefore, an alternative method is proposed to obtain turning movement counts only from signal information without using detector counts. To produce the required data, a simulation was performed in VISSIM with different input volumes. Green time interval and volume during each phase was extracted form VISSIM output and models were made based on these variables. This method generates accurate counts for some cases. Even when detector counts could be modified, or turning movements could be estimated based on traffic signal information, turning movement counts could not be estimated in shared lanes. This paper also proposed three methods to estimate turning movement proportions in shared lanes.
کلیدواژهها [English]
)