Behavioral Modeling of Drivers near Speed Control Cameras: A Dual Perspective from Micro and Macro Data

Abstract

The present study investigates the efficacy of speed cameras in managing vehicle speeds and their influence on various driver demographics within the operational context of the cameras. The research, conducted as a case study in Iran, comprises both macroscopic and detailed analyses, quantifying vehicle speeds at different spatial points relative to the speed camera location—upstream, adjacent to, and downstream of the camera—using a manual laser speedometer. Furthermore, the study examines diverse driver behavior metrics, including vehicle type, speeds at different locations, lane changes, braking actions, and measures such as obscuring license plates. Statistical analyses show that speed cameras effectively reduce speeds across different user groups and lead to increased braking and lane-changing behaviors, particularly among light vehicle categories. Moreover, the study reveals distinct behavioral patterns between indigenous and non-indigenous drivers. In addition, a multi-layer perceptron neural network model successfully approximates user speed selection behaviors within the operational range of speed cameras. Overall, this research provides valuable insights into the effectiveness of speed cameras and their impact on diverse driver demographics, contributing to a deeper understanding of advanced speed control mechanisms.