Abstract
Road traffic crashes are a public health issue due to their terrible impact on individuals, communities, and countries. Studies affirmed that vehicle speed is a major contributor to crash likelihood and severity. At the same time, they identified Automated Speed Enforcement (ASE) systems, namely speed cameras, as a highly effective measure to reduce excessive and inappropriate speed, and thus improving road safety. However, identifying optimum sites for fixed speed camera placement stays an open issue in the literature, although it is a key factor that guarantees the efficiency of such ASE systems. This paper describes a predictive framework of speed camera locations using a classification algorithm that can predict, for each section of a given road network, its pertinence as a speed camera location. First, we identify a set of features as predictors of the classification algorithm, that we have argued their goodness through correlation tests. Second, for training our algorithm, data from road controlled sections, corresponding to existing speed cameras, is exploited. Each section class reflects the contribution level of the ASE system (good, neutral, or bad) to road safety. Third, as a proofof-concept, the framework has been implemented and deployed on the Moroccan road network. The results showed that Random Forest classifier is the best performing model attaining an accuracy of 95% and a precision of 88%. Further, a tool was developed to visualize updated classification results on a Moroccan road network map to support authorities in their decision making process.
Highlights
According to the World Health Organization (2018), 1.35 million road traffic deaths occur every year producing a terrible impact on individuals, communities, and countries
The objective of this paper is to address this gap by defining a predictive framework of speed camera locations
To tackle the literature gap of a data-driven methodology that deals with the site selection issue for speed cameras, we propose in the present work a machine learning approach using a classification algorithm
Summary
According to the World Health Organization (2018), 1.35 million road traffic deaths occur every year producing a terrible impact on individuals, communities, and countries. ASE systems are an important element in speed management and can be a very effective countermeasure to prevent speeding-related crashes In this context, international research based on many ASE programs clearly argues that speed cameras help change driver behavior and have a positive road safety impact (Hess, 2004; De Pauw, Daniels, Brijs, Hermans & Wets, 2014; Pilkington & Kinra, 2005; KANG, 2002). The framework can designate, each section of the road network, as good, neutral, or bad speed camera site To achieve this goal, we define a Priority function as a composition of two main variables: i.) the effect of the ASE system on speed limit violation; and ii.) the effect of the ASE system on collisions of a controlled section.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
