Modelling of Traffic Flow of Long and Short Trucks on a Signalized Road Intersection Using Artificial Neural Network Model

Abstract

The increasing socio-economic development and the increase in private car ownership in developing and developed countries have added to traffic congestion problems at signalized road intersections. Over the years, researchers have come up with conventional models to predict traffic flow to solve the problem of traffic congestion. However, there are still existing traffic issues, especially those caused by long and short trucks, such as traffic-related accidents caused by long and short trucks at road intersections. This research focused on modelling the traffic flow of long and short trucks at road intersections that are signalized by utilizing datasets from the South Africa traffic flow networks. These traffic data were obtained through video cameras and inductive loop detectors. Eight hundred and fifty traffic datasets were identified, and they were divided into and testing which are 70% and 30% for the evaluation performance of the ANN model. The results (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.99806) show that the ANN model is suitable for modelling long and short trucks at these intersections. This research adds to the growing body of knowledge on traffic flow prediction and showcases insights into the traffic flow parameters that are useful in modelling the traffic flow of these trucks.