Estimating likelihood of future crashes for crash-prone drivers

At-fault crash-prone drivers are usually future incidents or crashes. In Louisiana, considered as the high risk group for possible 34% of crashes are repeatedly committed by the at-fault crash-prone drivers who represent only 5% of the total licensed drivers in the state. This research has conducted an exploratory data analysis based on the driver faultiness and proneness. The objective of this study is to develop a crash prediction model to esti- mate the likelihood of future crashes for the at-fault drivers. The logistic regression method is used by employing eight years＇ traffic crash data （2004-2011） in Louisiana. Crash predictors such as the driver＇s crash involvement, crash and road characteristics, human factors, collision type, and environmental factors are considered in the model. The at-fault and not-at-fault status of the crashes are used as the response variable. The developed model has identified a few important variables, and is used to correctly classify at-fault crashes up to 62.40% with a specificity of 77.25%. This model can identify as many as 62.40% of the crash incidence of at-fault drivers in the upcoming year. Traffic agencies can use the model for monitoring the performance of an at-fault crash-prone drivers and making roadway improvements meant to reduce crash proneness. From the findings, it is recommended that crash-prone drivers should be targeted for special safety programs regularly through education and regulations.

Influence of geometric design characteristics on safety under heterogeneous traffic flow

This paper focuses on analysing the influence of geometric design characteristics on traffic safety using bi-directional data on a divided roadway operated under heterogeneous traffic conditions in India. The study was carried out on a four lane divided inter-city highway in plain and rolling terrain. Statistical modelling approach by Poisson regression and Negative binomial regression were used to assess the safety performance as occurrence of crashes are random events and to identify the influence of the geometric design variables on the crash frequency. Negative binomial regression model was found to be more suitable to identify the variables contributing to road crashes. The study enabled better understanding of the factors related to road geometrics that influence road crash frequency. The study also established that operating speed has a significant contribution to the total number of crashes. Negative binomial models are found to be appropriate to predict road crashes on divided roadways under heterogeneous traffic conditions.

An optimization model for improving highway safety

This paper developed a traffic safety management system （TSMS） for improving safety on county paved roads in Wyoming. TSMS is a strategic and systematic process to improve safety of roadway network. When funding is limited, it is important to identify the best combination of safety improvement projects to provide the most benefits to society in terms of crash reduction. The factors included in the proposed optimization model are annual safety budget, roadway inventory, roadway functional classification, historical crashes, safety improvement countermeasures, cost and crash reduction factors （CRFs） associated with safety improvement countermeasures, and average daily traffics （ADTs）. This paper demonstrated how the proposed model can identify the best combination of safety improvement projects to maximize the safety benefits in terms of reducing overall crash frequency. Although the proposed methodology was implemented on the county paved road network of Wyoming, it could be easily modified for potential implementation on the Wyoming state highway system. Other states can also benefit by implementing a similar program within their jurisdictions.

Investigating the influence of segmentation in estimating safety performance functions for roadway sections

Safety performance functions（SPFs） are crucial to science-based road safety management.Success in developing and applying SPFs, apart data quality and availability, depends fundamentally on two key factors： the validity of the statistical inferences for the available data and on how well the data can be organized into distinct homogeneous entities. The latter aspect plays a key role in the identification and treatment of road sections or corridors with problems related to safety. Indeed, the segmentation of a road network could be especially critical in the development of SPFs that could be used in safety management for roadway types, such as motorways（freeways in North America）, which have a large number of variables that could result in very short segments if these are desired to be homogeneous. This consequence, from an analytical point of view, can be a problem when the location of crashes is not precise and when there is an overabundance of segments with zero crashes. Lengthening the segments for developing and applying SPFs can mitigate this problem, but at a sacrifice of homogeneity. This paper seeks to address this dilemma by investigating four approaches for segmentation for motorways, using sample data from Italy. The best results were obtained for the segmentation based on two curves and two tangents within a segment and with fixed length segments. The segmentation characterized by a constant value of all original variables inside each segment was the poorest approach by all measures.