Driving risk varies substantially according to many factors related to the driven vehicle, environmental conditions, and drivers. This study explores the contributing historical factors of driving risk with hierarchical clustering analysis and the quasi-Poisson regression model. The dataset of the study was collected from two sources: naturalistic driving experiments and self-reports. The drivers who participated in the naturalistic driving experiment were categorized into four risk groups according to their near-crash frequency with the hierarchical clustering method. Moreover, a quasi-Poisson model was used to identify the essential factors of individual driving risk. The findings of this study indicated that historical driving factors have substantial impacts on individual risk of drivers. These factors include the total number of miles driven, the driver’s age, the number of illegal parking (past three years), the number of over-speeding (past three years) and passing red lights (past three years). The outcome of the study can help transportation officials, educators, and researchers to consider the influencing factors on individual driving risk and can give insights and provide suggestions to improve driving safety.

Recently, autonomous driving becomes a hot topic in research and industry area. Autonomous driving technology needs to perceive the semantic information of road scenes in the all-day and open environment. In this paper, the semantic recognition of traffic scenes is studied using a deep learning network model, and a semantic representation model of road scenes is established. Besides, a semantic recognition algorithm of road scenes based on image data is proposed. Finally, a self-built data set is used to train the proposed model, and verified in the field of the test vehicle. It is found that the proposed method can quickly capture the perceptual road scene and over-performs better than traditional methods and demonstrated great potential to be used in road scene applications.

It is widely recognized that driving anger plays a major role in road safety. Many studies have been carried out in this field, and the significance of incentive factors of driving anger - in terms of driver's personal characteristics (e.g., sex or education) and external environment (e.g., interaction among drivers and obstruction) - has been proven. Questionnaire surveys and simulation experiments are used as the basis for those studies, but such methods make the studies very unrealistic. In this study, 22 licensed drivers were hired to drive along a specified route in Wuhan, China. Physiological data and drivers' reported driving anger and observed driving behavior are used to study the ranking of the contribution of various incentive factors to and their causal relationship with driving anger. Study results show that the following top three factors result in about three quarters of driving anger: (1) red traffic lights, (2) congestion, and (3) offensive hogging behavior of surrounding vehicles. Further, statistical analyses show that the p-values from the Somers-d test applied to red light waiting times and congestion duration, and from the F-test to hogging behavior are very small (< 0.02) and, thus, indicate that they have a significant impact on the level of driving anger. In general, this study contributes to this field by using both self-reported data and in-cabin observations to study the ranking of incentive factors and their causal relationship with driving anger in a typical driving environment in China. Study results can be useful for traffic operation and management agencies in China to improve their level of service in order to effectively reduce road rage.

The $k$-truss is a type of cohesive subgraph where each edge is contained in at least $k-2$ triangles within the subgraph, and it is commonly used in community search and dense subgraph discovery. Although $k$-trusses can be computed in polynomial time, obtaining all $k$-trusses of a dynamic graph that evolves over time through edge insertions and deletions remains computationally expensive. To address this challenge, prior studies proposed truss maintenance approaches that update the affected $k$-trusses when the dynamic graph changes. However, existing approaches only utilize one tool of parallelism or auxiliary indexes due to latent conflicts, which restricts their overall performance. To resolve this limitation, we propose a novel parallel approach with index optimization that effectively resolves the conflicts between parallelism and index maintenance. Specifically, we first establish a novel truss maintenance theory based on auxiliary indexes, which ensures the feasibility and correctness of our maintenance solution. Second, we design two effective edge partitioning strategies to improve the parallelism of the proposed algorithms. Finally, we implement two efficient parallel algorithms that cooperate with auxiliary indexes to reduce maintenance costs. Extensive experiments on real-world graphs demonstrate that our methods outperform all baseline approaches by up to one order of magnitude.