Search

In this study, 4 classification algorithms were employed to characterize the influence of road determinants on roadway crash severity with actual crash data. The crash data were obtained from crash records in Texas, USA, from January 2020 to April 2021. The prediction model of crash severity utilized 12 road-related features—including shoulder types, shoulder width, and curb types—as well as 10 other features—such as weather and illumination conditions—as input features. Three crash severity levels—"Minor Damage," "Moderate Damage," and "Severe Damage"—were used as output features. Decision tree, support vector machines, and multi-layer perceptron were employed to compare their prediction performance with the XGBoost model. The results show that the XGBoost model yields the best performance among the 4 algorithms. The overall accuracy, average precision, average recall, and average F1 score of the XGBoost model were 82.65%, 0.83, 0.82, and 0.82, respectively. Besides, SHapley Additive exPlanations (SHAP) and partial dependence plots were used to interpret the model results. Among the road-related features, the most influential one is the median width. Greater crash severity is related to paved right shoulder and curb. These findings are helpful for the design and planning of road safety. [ABSTRACT FROM AUTHOR]

Aggressive driving significantly impacts traffic safety, and heavy‐duty vehicle drivers are more liable for causing serious crashes. This paper analyzes drivers' aggressive driving behavior from the vehicle type perspective and identifies the influencing factors of aggressive driving behavior through artificial neural network (ANN) and Shapley additive explanations (SHAPs). Using Kaggle's open‐source aggressive driving data, we establish an ANN model to identify driving styles, where road conditions, environmental conditions, and vehicle parameters are independent variables and driving style is a dependent variable. The following measurements, including accuracy, recall, precision, and F1 score, are used to evaluate the model's performance, and the neural network got 85.33%, 82.32%, 84.16%, and 0.8308, respectively. To illustrate the influence of independent variables, the SHAP algorithm is used to analyze the model's feature importance. It was found that illumination and weather conditions influenced the model's performance along with the vehicle length. The number of lanes relates to driving style, and there were more aggressive driving behaviors on two‐lane roads than on single‐lane roads. Besides, heavy‐duty vehicle drivers were more likely to drive aggressively in wet road conditions and indulge in aggressive driving behaviors at night. Particularly, drivers of heavy‐duty vehicles were more likely to drive aggressively, provided that the vehicle in front was also a heavy‐duty vehicle. These findings inform heavy‐duty vehicle drivers to reduce aggressive driving behavior. The information is suitable for inclusion in driver education programs, thus improving traffic safety. [ABSTRACT FROM AUTHOR]