Journal of Advanced Transportation最新文献

Spatial correlation is a critical factor in establishing accurate traffic accident analysis models, with the choice of measurement method significantly influencing the results. Despite the central role of roads as the primary conduit for traffic flow and a direct exposure variable in accidents, their impact on spatial correlation in accident analysis has not been fully explored. This study introduces an innovative spatial correlation matrix, termed the road matrix, which incorporates shared road lengths between grids to enhance accident prediction accuracy. The model examines the relationship between traffic accidents and various predictor variables, including land use, road networks, and public transportation facilities. Compared to traditional spatial correlation methods such as the rook and queen matrices, the road matrix provides a more precise characterization of spatial dependencies and significantly improves accident frequency estimation. Notably, the application of the road matrix within a conditional autoregressive (CAR) model uncovers additional significant contributors to traffic accidents, such as the number of interchanges and the length of nonexpress arterial roads. These findings offer new insights and practical recommendations for urban planning and traffic safety management. The study provides a valuable reference for future research on traffic accident frequencies and offers guidance for the design of more effective traffic safety measures.

Autonomous valet parking has drawn wide attention these years. The k-stacks layout, known for its ability to increase parking capacity by stacking vehicles more compactly, is of great practicality among all possible layout patterns. Although this layout can increase the capacity of a parking lot, it generates relocations, which let vehicles move additional distances and influence the lot’s peak hour service ability. For the sake of optimizing them all simultaneously, we propose a simulation-based multiple-objective optimization (SMOO) and use NSGA II to solve the problem, obtaining candidate solutions. Then, a nondominated sorting based on cumulative advantages (NSCA) method is put forward to select the most robust solution from all candidates, considering different demand scenarios. K-stacks parking lots optimized by the SMOO can provide 36%–59% more parking spaces than a traditional parking lot while keeping other evaluations fine. In addition, we specify high-demand and low-demand scenarios and discuss the impact of different aspect ratios. It is recommended to use k-stacks layouts when a lot’s length is close to its width.

This paper introduces an action replacement module for reinforcement learning (RL)–based ramp metering to address the issue of ramp queue spillback during the training process. Ramp queue spillback leads to significant impacts on the traffic efficiency of adjacent road networks, making it a critical concern in ramp control. Existing RL approaches often employ ramp states as reward functions to encourage agents to learn strategies that avoid queue overflow. However, due to the trial-and-error nature of RL, these methods frequently generate actions that cause queue spillback during training, posing challenges for real-time online training in real-world applications. To overcome this limitation, the proposed action replacement module utilizes the store-and-forward model to estimate a lower bound for ramp metering rates. By identifying and replacing actions that fail to meet this constraint, the strategy effectively prevents queue spillback. In addition, penalties are imposed on replaced actions to guide the agent in learning effective and practical control policies. The proposed method is evaluated in both single-ramp and multiramp scenarios. Experimental results demonstrate that the agent can learn the queue spillback prevention strategies, and nearly eliminate ramp queue spillback without compromising control performance.

The hit-and-run caused a delay in medical assistance to the victim and posed a significant threat to the safety of drivers in road tunnels. This study investigates the potential factors contributing to drivers’ hit-and-run violations in river-crossing tunnels. This paper built three models (the logit model, the random parameter logit model, and the random parameter logit model with heterogeneity in means) based on a dataset consisting of crashes reported in thirteen river-crossing tunnels in Shanghai, China. Potential contributors from five aspects (offending drivers, vehicle conditions, tunnel characteristics, environmental conditions, and crash information) were explored. Results showed that the random parameter logit model with heterogeneity in means produced the highest fitting accuracy among the three models. Eight important variables (nighttime, single-vehicle, multi-vehicle, two-wheeled vehicle, passenger car, heavy goods vehicle, rear-end, and short tunnel) were found to affect hit-and-run violations significantly. The research has highlighted that nighttime and short tunnel increase the likelihood of hit-and-run and other variables are the opposite. The results of this study could provide useful information for the development of interventions to improve the level of safety in tunnels and reduce the rate of hit-and-run offenses.

Pavement distress is one of the most serious and prevalent diseases in pavement road detection. However, traditional methods for crack detection often suffer from low efficiency and limited accuracy, necessitating improvements in the accuracy of existing crack detection algorithms. Consequently, we propose the shuffle attention for you only look once version eight (SA-YOLOv8) model, which is based on an enhanced framework. Initially, we establish the required dataset and classify images proportionally based on their states. Subsequently, we conduct comparative testing against the results of the original model, analyzing issues such as the oversight of shallow and small cracks, truncation in the recognition of single-instance long cracks, and imprecise detection. We devise an improved detection approach based on YOLOv8. This method incorporates a small target detection layer to optimize the receptive field range, aiming to focus on identifying shallow and small cracks. Simultaneously, the Shuffle Attention mechanism and the transplanted spatial pyramid pooling-fast (SPP-F) reuse structure are introduced in the feature extraction network to enhance the model’s attention to detection targets. This augmentation improves the fusion of features for shallow small targets and overall and partial features of long cracks, thereby alleviating the precision of the model in crack detection. The experimental results demonstrate a stepwise improvement in the model’s mean average precision (mAP) with each enhancement to the original network. Initially, adding a small object detection layer increased the mAP by 3.4 percentage points, raising it to 68.2%. Subsequently, incorporating the spatial attention (SA) module resulted in a more substantial improvement, boosting the mAP by 8.7 percentage points to 73.5%. Finally, the addition of the transplanted SPP-F module further enhanced accuracy, increasing the mAP by 0.7 percentage points from the previous stage, thus achieving a final mAP of 74.2%. Overall, these modifications resulted in a total improvement of 9.4 percentage points in mAP compared to the original model. In conclusion, the proposed SA-YOLOv8s model effectively supports the automated recognition of asphalt road surface cracks, demonstrating applicability in practical scenarios. The recognition performance is notably favorable, demonstrating robustness in complex environments.

The paper analyses the effects of modifying traffic light regulations at urban road junctions, focussing on the ratio between green time and cycle time, as a function of vehicular traffic variables (flows, density and speed) on the links. The analyses are conducted in an urban setting using a before-and-after approach, employing traffic data detected by loop detectors and traffic light control parameters (the ratio between green time and cycle time) that were actually implemented. The data pertain to a central street in the city of Santander (Spain), collected during several significant weeks in different periods corresponding to varying demands for mobility. In the context of existing studies on the flow–density diagram, a function is estimated that considers the ratio between green time and cycle time as the independent variable and link capacity as the dependent variable. The analysis at the link level may be extended in the future to the network level by incorporating the network fundamental diagram into the traffic signal setting design problem.

Port collecting and distributing network (PCDN) carries both freight traffic flow associated with the port and urban traffic flow, serving as the only channel between the port and the hinterland. The congestion caused by increasing freight traffic seriously disrupts urban traffic and leads to environmental issues such as increased carbon emissions. To address this issue, this study proposes a multiobjective optimization approach for the route selection of freight traffic flow within the PCDN, considering the balance among efficiency, environmental performance, and disruption to urban traffic. First, the generation mechanism and characteristics of freight traffic flow in the PCDN are analyzed, followed by the development of a mathematical model based on the static traffic flow distribution theory and the multiobjective optimization theory. Then, a solution framework with NSGA-III as the core is developed, and an improved Dial algorithm is utilized to allocate traffic flow. Finally, taking a large-scale container port as the case study, the solution framework is implemented to address the multiobjective optimization model and obtain the optimal route for freight traffic. The results show that there are significant negative correlations between distributing efficiency and disruption to urban traffic, as well as between distributing efficiency and carbon emissions. Decision-makers can choose the optimal route according to different preferences or adopt the compromise solution by referencing the Pareto front obtained by the solution framework. The proposed method provides theoretical support for designing the PCDN scientifically.

This paper develops a mathematical optimization approach for link-level air traffic flow management. First, a pure integer programming model is established for the problem on a link level. The model seeks to minimize the weighted summation of ground delay and airborne delay, and offers a more precise modeling for the capacity and traffic dynamics at the merge, diverge, and intersection nodes. The optimization problem is computationally NP-hard, and a modified genetic algorithm is then presented to solve it. Besides a new chromosome coding rule for converting binary decision into time series vectors, the algorithm uses a taboo mutation operator and an adaptive mutation probability selection operator. Finally, the effectiveness and superiority of the model and algorithm are demonstrated through a real-world case study in Dalian, China, and some managerial insights are presented.

Nonrecurrent congestion (NRC) events caused by incidents bring unexpected delays and affect normal traffic operations. Imprecise NRC event detection methods can trigger false alarms and repetitive incident alerts for the same congestion event. The speed watershed from the historical profile based on DBSCAN can provide a reference for identifying NRC. This paper proposes a DBSCAN-based dynamic NRC tracking (DyNRTrac) algorithm to detect and track NRC events. By comparing real-time spatial–temporal patterns of the speed contour diagram against the historical speed contour diagram along a corridor, this method effectively distinguishes NRC events from regular traffic patterns. The proposed algorithm applies the Rauch–Tung–Striebel smoother for speed noise reduction and establishes a historical congestion profile for each recurrent congestion event within a corridor by each day of the week and season. A new event-profile–based 3D speed volume comparison method is proposed to detect NRC events that do not significantly overlap with recurrent congestions in the historical profile. Finally, a bilevel congestion confirmation process is introduced for NRC persistency checking and filtering. The proposed algorithm was evaluated by using field travel time data and with the New Jersey Department of Transportation OpenReach incident database. Overall, the proposed model shows up to 88.3% detection rate for NRC that can match the incident in the database, and it shows superior detection rates on NRC events at a similar false alarm rate level when compared with three prior models over the same datasets. Furthermore, a detailed spatial–temporal map analysis is provided to show the capability of the proposed method in distinguishing NRC and RC and identifying nonaccidental NRC events, providing its potential for traffic operation management systems to assist traffic operators to be alerted about NRC events.

The transportation system is a complex dynamic giant system which integrates and intertwines the elements of people, vehicles, roads, and the environment. The city-level traffic flow forecasting can effectively reflect the flow changes of the traffic system and provide practical guidance for the formulation of traffic rules. Recent city-level traffic flow forecasting works rely on accurate prior knowledge of graphs (i.e., the spatial relationships between roads), which hinders their effectiveness and application in the real world. We propose a novel framework for urban traffic flow forecasting, which simultaneously infers and utilizes the relationship between time series. In our model, the graph structure learning module dynamically captures the correlation and causation between the different time series and infers a potentially fully connected graph. At the same time, the temporal convolution network captures the temporal correlation between a single time series. The graph neural network uses the graph for forecasting. Our model no longer relies on accurate graph priors and achieves better forecasting results than previous work. Experiments on two public datasets verify that the proposed model is very competitive.