A Review of Data Analytic Applications in Road Traffic Safety. Part 1: Descriptive and Predictive Modeling

Abstract

This part of the review aims to reduce the start-up burden of data collection and descriptive analytics for statistical modeling and route optimization of risk associated with motor vehicles. From a data-driven bibliometric analysis, we show that the literature is divided into two disparate research streams: (a) predictive or explanatory models that attempt to understand and quantify crash risk based on different driving conditions, and (b) optimization techniques that focus on minimizing crash risk through route/path-selection and rest-break scheduling. Translation of research outcomes between these two streams is limited. To overcome this issue, we present publicly available high-quality data sources (different study designs, outcome variables, and predictor variables) and descriptive analytic techniques (data summarization, visualization, and dimension reduction) that can be used to achieve safer-routing and provide code to facilitate data collection/exploration by practitioners/researchers. Then, we review the statistical and machine learning models used for crash risk modeling. We show that (near) real-time crash risk is rarely considered, which might explain why the optimization models (reviewed in Part 2) have not capitalized on the research outcomes from the first stream.

Impact on Road Safety and Operation of Rerouting Traffic in Rural Travel Time Information System

“…The rerouting of traffic during peak periods is reported in Figure 6 as it was used in Scenario 3. The results presented in [1] confirm the need for an overall assessment of the safety performance of the system, not only for road sections, but also for intersections. The assessment of safety and traffic performance of road networks is a complex problem due to possible changes in traffic distribution at the intersections.…”

“…The traffic redistribution on the road network not only impacts the environment (fuel consumption and an increase in pollution) but it can affect in a not negligible way the safety of the road users. The common problem in the implementation of this kind of complex system is that the travel time (measured as traffic volume in relation to the infrastructure capacity) is the only factor in the decision about rerouting traffic instead of considering multiple criteria [1]. The present research aims to analyze the effects of the TTIS system on road safety and travel time by verifying the overall safety and traffic operation performance of the road network, including national and regional roads and their intersections where traffic is rerouted.…”

Road Traffic Accidents Injury Data Analytics

“…Mehdizadeh et al [2] presented a comprehensive review on data analytic methods in road safety. Analytics models can be grouped into two categories: predictive or explanatory models that attempt to understand and quantify crash risk and (b) optimization techniques that focus on minimizing crash risk through route/path-selection and rest-break scheduling.…”

Managing Big Data for Addressing Research Questions in a Collaborative Project on Automated Driving Impact Assessment

“…The PFDS protocol is evaluated on several standard prediction tasks and experimental results demonstrate the potential of sharing privacy-preserving datasets to produce accurate predictors. In addition, [12] provides an extensive review of data analytic applications in road traffic safety, with particular attention to crash risk modelling.…”