Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

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.

Analysis of Factors Associated with Traffic Injury Severity on Urban Roads in Different Lighting Conditions

“…Using the CART model, results showed that influential factors were mostly similar between daylight crashes and crashes that happened on lighted streets at night. However, dark streets at night were able to involve some other factors in the severity of twovehicle crashes [19].…”

Understanding the Factors Affecting Urban Vehicle-to-Vehicle Crash Severity with Focus on Drivers' Route Familiarity

“…As it remained only 15 fatal crashes after eliminating unknown records, fatal and injury crashes were integrated. Therefore, the dependent variable is a binary variable with the value of 1 if the crash severity is fatal or injury; and 0 if the crash severity is no injury [3]. The dataset includes 1403 injury/fatal and 4786 no injury vehicle-to-vehicle crashes.…”

“…The five categories of contributing factors to traffic collisions are human, vehicle, road, environment, and traffic [2,3]. Research has shown that human factors play a significant role in about 90% of crashes [4].…”

Accident Hotspot Detection of Exclusive Bus Transit Lanes (Case Study: City of Rasht)

“…It should be noted that according to the World Health Organization (WHO), 1.2 million individuals are amongst the annual casualties of traffic accidents, and approximately 20-50 million are found injured each year globally. Furthermore, approximately 17,000 individuals lose their lives in Iran annually due to traffic accidents; plus, the obtained results from the city of Rasht during a period of four years showed a total of 122 fatal and approximately 9,000 injured crash records [2,3]. Contrary to the accidents, which are usually presumed to be random events, the spatial distribution of traffic accidents in the road network is not random, and areas with high traffic accident frequency are essentially called blackspots or hotspots.…”