This study aimed to determine different influencing factors associated with the injury outcomes of heavy vehicle and automobile drivers at highway–rail grade crossings (HRGCs). A mixed logit model was adopted using the Federal Railroad Administration (FRA) dataset (n = 194,385 for 2011–2020). The results show that drivers’ injury severities at HRGCs are enormously different between automobile and truck/truck–trailer drivers. It was found that vehicle speed and train speed significantly affect the injury severity in automobile and truck drivers. Driver characteristics such as gender and driver actions significantly impact the injury severity in automobile drivers, while HRGC attributes such as open space, rural areas, and type of warning device become significant factors in truck models. This study gives us a better understanding of the differences in the types of determinants between automobiles and trucks and their implications on differentiated policies for car and truck drivers.

To explore the nonlinear influence of a multi-scale built environment on residents’ car ownership behavior, combined with the data set of residents’ individual information and travel-related data from the China Labor Force Dynamic Survey report, eight variables are selected to describe the built environment from multiple scales. The gradient-boosting iterative decision tree model including individual family attributes and neighborhood-scale and city-scale built-environment attributes is constructed. The results show that the individual family attributes have the greatest cumulative impact on car ownership behavior (46.3%). The built environment based on neighborhood scale and city scale also has a significant impact on residents’ car ownership behavior, these being 33.94% and 19.76%, respectively. The distance to the city center at the neighborhood scale is positive correlated with car ownership. The number of buses per 10,000 people and road area per capita in the city scale are also positive correlated with car ownership. Therefore, in order to slow down the increase in car ownership, the built environment can be optimized and adjusted at neighborhood scale and city scale.

This paper analyzes the effects and potential causes of different variables on drivers’ mandatory merging decision behavior by constructing temporal and spatial dimensional merging risk indicators. This study employs the grouped latent class logit model (GLCM) and the grouped random parameter logit model with heterogeneity in means and variances (GRPMV) to analyze group heterogeneity and individual heterogeneity, respectively, and compared their goodness-of-fit and classification performance with other heterogeneity models. GLCM allows for the identification of latent classes among drivers, capturing unobserved heterogeneity by grouping drivers into distinct behavioral categories. Meanwhile, GRPMV provides a nuanced analysis of individual heterogeneity by accounting for variations in both means and variances of the parameters. The results suggest that merging risk has an important impact on the modeling of merging decision behavior, which can significantly improve the fitting performance of the model and effectively reveal unobserved group heterogeneity. In GRPMV, merging risk in the time dimension has the greatest impact on drivers’ merging decision behavior. In GLCM, individuals in different latent classes exhibit varying sensitivity to the presence of merging risk in merging situations. The parameter estimation results show the driving behavior characteristics of “conservative” and “aggressive” drivers. The results provide a theoretical basis for establishing a more comprehensive collision risk response identification function for autonomous vehicles in weaving areas and contribute to the enhancement of real-time decision-making processes in complex traffic scenarios.

Targeted contingency measures have proven highly effective at reducing the duration and harm caused by incidents. This study utilized the Classification and Regression Trees (CART) data mining technique to predict and quantify the duration of incidents. To achieve this, multisensor data collected from the Hangzhou freeway in China spanning from 2019 to 2021 was utilized to construct a regression tree with eight levels and 14 leaf nodes. By extracting 14 rules from the tree and establishing contingency measures based on these rules, accurate incident assessment and effective implementation of post-incident emergency plans were achieved. In addition, to more accurately apply the research findings to actual incidents, the CART method was compared with XGBoost, Random Forest (RF), and AFT (accelerated failure time) models. The results indicated that the prediction accuracy of the CART model is better than the other three models. Furthermore, the CART method has strong interpretability. Interactions between explanatory variables, up to seven, are captured in the CART method, rather than merely analyzing the effect of individual variables on the incident duration, aligning more closely with actual incidents. This study has important practical implications for advancing the engineering application of machine learning methods and the analysis of sensor data.

The region disposition prediction is important to the fleet management of shipping company to make effective decisions. To obtain the future marine environment, support vector machine (SVM) is used due to the advantage of prediction performance based on small samples. Since the incorrectly recorded data would affect the prediction performance of SVM obviously, K-nearest neighbors (KNN) is adopted to filter the input data in data processing. The prediction model based on KNN and SVM is validated by the data. The Baltic Freight Index (BPI index) of four routes and the decision-making of different companies was considered in prediction processing to improve the accuracy of our model. In the example calculation, results show that the proposed prediction model can increase the rental income of fleet effectively, and it would help the shipping company to make decisions of fleet management.