Abstract
Highway crashes, along with the property damage, personal injuries, and fatalities that they cause, continue to present one of the most significant and critical transportation problems. At the same time, provision of safe travel is one of the main goals of any transportation system. For this reason, both in transportation research and practice much attention has been given to the analysis and modeling of traffic crashes, including the development of models that can be applied to predict crash occurrence and crash severity. In general, such models assess short-term crash risks at a given highway facility, thus providing intelligence that can be used to identify and implement traffic operations strategies for crash mitigation and prevention. This paper presents several crash risk and injury severity assessment models applied at a highway segment level, considering the input data that is typically collected or readily available to most transportation agencies in real-time and at a regional network scale, which would render them readily applicable in practice. The input data included roadway geometry characteristics, traffic flow characteristics, and weather condition data. The paper develops, tests, and compares the performance of models that employ Random effects Bayesian Logistics Regression, Gaussian Naïve Bayes, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine methods. The paper applies random oversampling examples (ROSE) method to deal with the problem of data imbalance associated with the injury severity analysis. The models were trained and tested using a dataset of 10,155 crashes that occurred on two interstate highways in New Jersey over a two-year period. The paper also analyzes the potential improvement in the prediction abilities of the tested models by adding reactive data to the analysis. To that end, traffic crashes were classified in multiple classes based on the driver age and the vehicle age to assess the impact of these attributes on driver injury severity outcomes. The results of this analysis are promising, showing that the simultaneous use of reactive and proactive data can improve the prediction performance of the presented models.
Highlights
The literature review reveals that the existing studies of real-time crash risk prediction are based on the real-time traffic counts and density collected from Automatic Vehicle Identification (AVI) sensors and real-time weather data collected from weather stations
The Bayesian logistic regression differs from the standard logistic regression in the treatment of coefficients—it assumes that the coefficients follow a random distribution, rather than being fixed
The resulting confidence region associated with each estimated parameter is equivalent to the confidence interval in standard regression analysis, but it captures the unobserved variability in the model parameters, which may improve the accuracy of the estimates
Summary
To better understand the causes and factors contributing to highway crashes, and identify the measures for improving highway safety, much of the traffic safety research focuses on developing a better understanding of how, why, when, and where the highway crashes occur The outcomes of such studies can be used to ascertain the likelihood of crash occurrence under the given conditions and take the appropriate actions to reduce the frequency or mitigate the crashes before they occur. The advances in intelligent transportation systems (ITS), especially in the areas of connected vehicle, vehicle telemetry, and remote sensing data collection technologies, have significantly improved the ability to analyze traffic and road performance These technologies have provided opportunities to collect and analyze data in near-real-time and aggregated to relatively short roadway segment level, including the data on prevailing vehicle speeds and travel times, lane occupancy, and road-weather and environmental characteristics. Due to the limitation in data availability, those models could only be applied to specific, well instrumented facilities or local networks, and would not be applicable as support systems for dynamic monitoring of crash risks (in terms of crash likelihood and severity) and regional traffic operations decision making
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.