Crashes among young and inexperienced drives are a major safety problem in the United States, especially in an area with large rural road networks, such as West Texas. Rural roads present many unique safety concerns that are not fully explored. This study presents a complete machine leaning pipeline to find the patterns of crashes involved with teen drivers no older than 20 on rural roads in West Texas, identify factors that affect injury levels, and build four machine learning predictive models on crash severity. The analysis indicates that the major causes of teen driver crashes in West Texas are teen drivers who failed to control speed or travel at an unsafe speed when they merged from rural roads to highways or approached intersections. They also failed to yield on the undivided roads with four or more lanes, leading to serious injuries. Road class, speed limit, and the first harmful event are the top three factors affecting crash severity. The predictive machine learning model, based on Label Encoder and XGBoost, seems the best option when considering both accuracy and computational cost. The results of this work should be useful to improve rural teen driver traffic safety in West Texas and other rural areas with similar issues.

Lane information is an essential part of high-resolution micro-traffic data (HRMTD). Most of the lane detection algorithms for Light Detection and Ranging (LiDAR) are applied to high-density onboard LiDAR and airborne LiDAR, which cannot be used directly to process low-density roadside LiDAR data. In this article, an algorithm for lane detection applied to low-density roadside LiDAR is proposed, which includes three steps: ground recognition, lane marking point extraction, and pavement lane marking points clustering. Firstly, an improved algorithm for ground recognition is proposed to get normal ground points (NGPs). Then, the lane marking points are extracted from the no lane marking points based on the difference of laser intensity. Finally, we divided the ground within the range of LiDAR scanning into different stripes, and search the maximum linear density of the stripe to extract the lane markings. The average distance error (ADE) of lane detection results is less than 0.1m by fusing and comparing the test results with the aerial photographs. The proposed algorithm is also proved to be robust in multiple test locations and the results can be used to assist high-precision vehicle positioning in vehicle-to-infrastructure (V2I) cooperation application within the intelligent transportation system.

High-density land uses cause high-intensity traffic demand. Metro as an urban mass transit mode is considered as a sustainable strategy to balance the urban high-density land uses development and the high-intensity traffic demand. However, the capacity of the metro cannot always meet the traffic demand during rush hours. It calls for traffic agents to reinforce the operation and management standard to improve the service level. Passenger flow prediction is the foremost and pivotal technology in improving the management standard and service level of metro. It is an important technological means in ensuring sustainable and steady development of urban transportation. This paper uses mathematical and neural network modeling methods to predict metro passenger flow based on the land uses around the metro stations, along with considering the spatial correlation of metro stations within the metro line and the temporal correlation of time series in passenger flow prediction. It aims to provide a feasible solution to predict the passenger flow based on land uses around the metro stations and then potentially improving the understanding of the land uses around the metro station impact on the metro passenger flow, and exploring the potential association between the land uses and the metro passenger flow. Based on the data source from metro line 2 in Qingdao, China, the perdition results show the proposed methods have a good accuracy, with Mean Absolute Percentage Errors (MAPEs) of 11.6%, 3.24%, and 3.86 corresponding to the metro line prediction model with Categorical Regression (CATREG), single metro station prediction model with Artificial Neural Network (ANN), and single metro station prediction model with Long Short-Term Memory (LSTM), respectively.

Mixed traffic composed of human-driven vehicles (HDVs) and CAVs will exist for an extended period before connected and autonomous vehicles (CAVs) are fully employed on the road. There is a consensus that dense fog can cause serious traffic accidents and reduce traffic efficiency. In order to enhance the safety, mobility, and efficiency of highway networks in adverse weather conditions, it is necessary to explore the characteristics of mixed traffic. Therefore, we develop a novel cellular automata model for mixed traffic considering the limited visual distance and exploring the influence of visibility levels and CAV market penetration on traffic efficiency. We design acceleration, deceleration, and randomization rules for different car-following scenes. For lane-changing, considering the interaction of CAVs and surrounding vehicles, we introduce game theory (GT) to lane-changing policies for CAVs. This paper presents the following main findings. In reduced visibility conditions, the introduction of CAVs is beneficial to improve mixed traffic efficiency on metrics such as free-flow speed and traffic capacity (e.g., 100% CAVs could increase the traffic capacity up to around 182% in environments of dense fog). In addition, the critical density increases as the proportion of CAVs increases, which is more pronounced in conditions of dense fog according to the simulation results. In addition, we compared the proposed GT-based lane-changing strategy to the traditional STCA lane-changing strategy. The results showed that the average speed is significantly improved under the proposed lane-changing strategy. The model presented in this paper can evaluate the overall performance and provide a reference for future management and control of mixed traffic flow in fog conditions.

Further detection will increase traffic safety by perceiving unexpected traffic incidents earlier, allowing more time to make decisions and implement these decisions. Therefore, this article attempts to extend the detection range by using a low-channel roadside light detection and range sensor (LiDAR) sensor due to its low price and widespread employment in the future. The proposed method contains two major parts: static background construction and traffic objects detection. For static background construction, successive point cloud frames data were used to cover the most LiDAR scanning horizontal–vertical angle and obtain background information ultimately. Furthermore, the constructed static background was optimized to reduce the missing of the far range points and the occurrence of noise points. For vehicle and road user detection, the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to identify the near-range traffic objects. For far-range traffic objects detection, the trajectories of objects were extracted based on their moving direction and distance, and a fast Fourier transform (FFT) algorithm was used to filter the noise point and identify the vehicle and road user points. The experimental results show that the static background construction with the proposed method is more effective and uses fewer point cloud data. The average maximum detection range can be up to 100, 100, and 85 m for vehicles, cyclists, and pedestrians, respectively. The average precision (AP) and recall are 95.71% and 90.62%, respectively, which are better than the previous studies.