Journal of Advanced Transportation最新文献

Maintaining driving workload (DWL) at an appropriate level is crucial for preventing driver-related crashes. However, the unique conditions of plateau environments significantly impact DWL, increasing driving risks. Research on DWL identification, particularly in real-world plateau driving scenarios, remains limited. This study recruited 27 participants for a naturalistic driving experiment on the Qinghai–Tibet Plateau, integrating psychological and physiological factors to assess DWL. Electrocardiogram (ECG) signals were collected using a wearable wireless physiological monitor, whereas driving video was recorded with two driving recorders. Participants reviewed driving scenarios and operations through recorded videos and rated their subjective DWL using the NASA Task Load Index (NASA-TLX). The self-reported NASA-TLX scores were clustered by C-mean fuzzy (FCM). The cluster results served as classification labels, whereas the corresponding ECG signals were used as features. Then, an extreme gradient boosting (XGBoost) model, optimized by the tree-structured Parzen estimator (TPE) algorithm, classified DWL into three levels. Results show that the proposed model achieves 90.53% accuracy, with an F1 score of 0.91. Under real-world plateau driving conditions, integrating ECG features with subjective workload ratings effectively classified DWL, particularly when using heart rate (HR) and the low-to-high frequency (LF/HF) power ratio. Although the medium level of DWL is more challenging to classify than the other two levels, incorporating multiple physiological features significantly improves the model’s performance in identifying it. These findings provide valuable insights into feature selection and model development for DWL assessment, contributing to optimized road design and enhanced driving safety management in plateau regions.

Blind spots represent a critical challenge to maintaining traffic safety. The development and deployment of intelligent and connected vehicle technologies have resulted in significant enhancements to traffic safety. However, blind spots are still a thorny issue, especially on traffic safety at intersections because of the complexity of their reasoning environment. Despite these advancements, blind spots remain a significant challenge for traffic safety, particularly at intersections, where the complex driving environment hinders accurate perception. In this paper, we introduce an innovative architecture that leverages self-optimizing computational (SOC) network resources to improve the accuracy and efficiency of blind spot detection for vehicles at intersections. This approach tackles two critical challenges: excessive data volumes causing significant transmission delays and insufficient data leading to a deficiency in essential features required for accurate vehicle state assessment. Through dynamic allocation of network resources and real-time performance optimization, it significantly enhances perception and thereby improves traffic safety. (1) Grounded in a comprehensive analysis of real-world conditions, this method enhances performance by focusing on critical areas, optimizing information packaging, and efficiently utilizing communication resources; and (2) this method employs dynamic analysis of blind spots to automatically optimize the allocation of computational resources, ensuring efficient and real-time performance adjustments. To evaluate the proposed perceptual architecture, we validated it using the DAIR-V2X dataset, a benchmark for real-world vehicular infrastructure collaboration, achieving an average precision (AP) of 67.20% at a communication rate of 5.09%.

Currently, the optimization of train stop planning of high-speed railways does not adequately account for how ticket adjustment and train departure time affect passenger expectations. To better align supply and demand dynamics and maximize passenger utility, it is essential to optimize train stop planning, ticket pricing strategies, and passenger flow allocation from a system-wide perspective. The paper proposes a synergistic optimization model for train stop planning, ticket pricing, and passenger flow allocation of high-speed railway. The optimization model aims to maximize the operational revenues of the transportation enterprise while minimizing the total travel costs of passengers. The number of train stops, range of ticket price fluctuations, transportation capacity, and price response function are taken into consideration. A double-layer simulated annealing algorithm is designed to solve the model. Finally, a real case based on the Hohhot East–Beijing North high-speed railway in China verifies the correctness and validity of the model. A comparative analysis of the operational benefits of the railroad transportation enterprises and the travel utility of the passengers under the original plan and the synergistic optimization plan is carried out to verify the validity of the model and the algorithm. The results show that the method proposed in this paper can improve the operational efficiency of transportation enterprises by 18.54% and reduce the passenger travel time costs by 12.13% without increasing the number of trains and the number of stops. The optimized plan can reduce train operation costs, meet passenger flow demand, and improve the operational efficiency of transportation enterprises and the travel utility of passengers.

The operating environment in underground mines is complex and fraught with various hazards that pose severe risks to miners’ safety. As an essential auxiliary transportation device in mines, the operational safety and reliability of rubber-tired vehicles are crucial to coal mine production safety and efficiency. Therefore, developing an L4-level autonomous driving system for these vehicles will accelerate the achievement of inherent safety in underground transportation, holding significant theoretical and practical value. This paper mainly studies and improves the control strategy of the chassis of the underground unmanned railless rubber wheeled vehicle and elaborates the MPC controller in detail, including its specific implementation principle, advantages and disadvantages, and the improvement should be carried out in the underground working conditions. Finally, a concrete feasible control scheme is given, and the safety and stability of the scheme are verified by experiments. This research offers theoretical foundations and technical support for the automation and intelligence of rubber-tired vehicles in underground mines and has made important contributions to the application and industrialization of safe autonomous driving in such environments.

Conventional field-testing approaches for license plate recognition (LPR) product evaluation demonstrate substantial methodological limitations that impede both technological advancement and optimal deployment in practical applications. To address these challenges, this study proposes a new evaluation platform for LPR hardware, focusing on two key contributions: (1) A standardized laboratory-based methodology: We develop an innovative evaluation device integrated with a calibration protocol, designed to overcome the inherent variability of field testing while ensuring metrological traceability and repeatability. (2) Comprehensive performance benchmarking: Five commercially dominant LPR hardware products in the Chinese market were rigorously evaluated. The assessment identified their respective strengths and weaknesses while providing valuable insights for future directions for research in the LPR field. Experimental results indicate that the proposed method effectively eliminates systematic errors inherent in traditional field testing. Crucially, the results reveal that reported “recognition rates” are fundamentally database-dependent—recognition rates serve as guiding indicators only when correlated with test images of known attributes. This work not only advances LPR evaluation standards but also establishes a standardized methodology for the robust and fair assessment of LPR technologies across diverse regions.

A two-stage multiobjective optimization model for multipath coordinated control based on the improved AM-Band model is proposed to address issues such as multipath competition and the narrowing of the green-wave bandwidth in the coordinated control of urban road arterial signals. In the first stage, at the intersections along the arterial road, by considering the analysis of path traffic flows and turning demands, the classical AM-Band model is improved, and a green-wave bandwidth maximization model for multipaths is established, aiming to meet the demands of multipath competition to the greatest extent. In the second stage, according to the signal states between upstream and downstream intersections, a reasonable speed guidance range is determined. The vehicle speeds are divided into green light guidance and red light guidance, and a delay minimization model based on optimal speed guidance is established. Furthermore, a multiobjective grasshopper optimization algorithm is used to solve the above models. Finally, four consecutive intersections along Xingguang Road in Xiqing District, Tianjin, are selected for simulation verification. The results of the relevant case studies show that, compared with the Webster scheme and the Yang-M2 scheme, the average vehicle delay of the model in this paper is reduced by 10.75% and 6.53%, respectively, the average number of vehicle stops is reduced by 43.26% and 16.64%, respectively, and the average travel time is reduced by 10.84% and 3.69%, respectively. This indicates that the model in this study can effectively improve the traffic efficiency of the road network under multipath competition.

Many cities are currently working on the development of mobility policies aimed at improving the accessibility of transport infrastructures and the intermodality in the citizen’s daily travel. Some of these policies should focus on obtaining a more sustainable modal split distribution in the access to and egress from multimodal transportation hubs. The first step to face this problem should be to obtain a good estimation of this actual modal split. Although different methods are available in the literature, this paper opens a new research challenge proposing to use models calibrated with data obtained from pedestrian reidentification devices as these models allow the direct reconstruction of pedestrian route flows. However, this topic is still a work in progress as the real data required to validate these models should, at the outset, come from reidentification sensors that are under development, and although there are cameras installed in some stations, they are not sensors that are useful for the postprocessing we are looking for. Indeed, among the few models found in the literature dealing with dynamic pedestrian demand estimation, none of them use data from reidentification sensors to reconstruct the OD-matrix or to establish the pedestrian modal split in the access to and the egress from the station. To fill this gap, this paper sets out to establish the fundamentals of a new dynamic pedestrian estimation model using reidentification data and to propose a genetic algorithm for the determination of the best possible location of PRI sensors in an urban multimodal transportation hub. To do so, a methodology is proposed to use microsimulation tools to obtain realistic data for the development of this model as an alternative to real data until real devices are installed. To demonstrate its applicability, two small fictitious stations and the real case study of Getafe Central station are modeled to explain the method and to generate realistic scenarios that occur daily at train stations to virtually locate pedestrian recognition sensors capable of reidentifying users over several parts of their routes.

Aiming to address the issues of missed detection and low accuracy in detecting small, dense traffic cones in complex traffic scenarios, this study proposes an improved traffic small target detection method based on YOLOv11, referred to as WHF-YOLOv11. In terms of network structure, large receptive field wavelet convolution is introduced into the YOLOv11 network (WTConv). By decomposing and reconstructing the image at different scales, the model can capture the local and global features of the image more accurately, so as to effectively extract the key details such as texture and edge. At the level of feature map extraction, the hierarchical multiscale feature fusion network (HiFuse) was introduced into the neck network. By utilizing a three-branch HiFuse, the local perception capabilities of CNNs and the global modeling strengths of transformers were combined to enhance the image classification accuracy. In terms of loss function, Focaler-IoU is used as the bounding box loss function to improve the detection ability of small target difficult cases. The experimental results show that for the traffic cone dataset obtained on the Roboflow platform, compared to the benchmark model YOLOv11 n, the improved model improves the accuracy rate P and recall rate R by 2.8% and 1.7%, respectively, and mAP50 and mAP50∼95 by 1.6% and 3.3%, which verifies the effectiveness of the model and provides technical support for the intelligent detection of small targets in traffic scenes.

The COVID-19 pandemic has profoundly disrupted global aviation, raising new challenges for passenger satisfaction and service quality in airport terminals. While the SERVQUAL model has long been used to measure expectation–perception gaps, it has been critiqued for treating all service attributes as if they contribute symmetrically to satisfaction. Also, most studies on airport service quality and passenger satisfaction were conducted prepandemic, leaving a gap in understanding COVID-19’s impact. This study addresses how the pandemic reshaped passenger expectations and satisfaction, providing a comprehensive analysis of airport service quality during COVID-19 and the unique challenges it introduced. In this regard, the performance of an airport passenger terminal service level and the factors affecting user satisfaction during the COVID-19 pandemic were evaluated using SERVQUAL and Kano analyses at Imam Khomeini International Airport (IKIA). To validate the model and the estimated parameters, Kolmogorov–Smirnov, Wilcoxon, Friedman ranking, and Spearman correlation coefficient tests were applied. The SERVQUAL findings showed a notable quality gap between the expected and received passenger services, with responsiveness and reliability factors exerting the greatest influence on satisfaction. The Kano analysis further highlighted that while some service features were mandatory, others acted as attractive and functional factors that could significantly enhance the passenger experience. The Kolmogorov–Smirnov test showed that the research data do not follow a normal distribution; thus, nonparametric tests were applied. Wilcoxon’s nonparametric test confirmed that the gap between respondents’ expectations and perceptions across all dimensions was not influenced by other factors. In addition, the Friedman test revealed that the average perception scores were high, showing a significant difference in the rankings, with the highest influence of assurance and tangibility variables. By combining these approaches, this study provides a postpandemic dual-method framework that quantifies service quality gaps and prioritizes attributes by their impact on satisfaction and dissatisfaction. The findings guide airports in identifying improvement priorities, adapting to evolving passenger needs, and building resilience for future health crises.

In the Connected and Autonomous Vehicle (CAV) environment, road space utilization can be more flexible. This study aims to maximize the allocation of road space for socioeconomic activities without compromising traffic demands. By exploiting the potential of CAVs to improve transportation systems, this paper explores network-level optimization of road space utilization, formulates the problem as a mixed-integer nonlinear programming model, and solves it with a tailored Tabu Search heuristic. We apply the model to a subnetwork of the Wangjing area in Beijing to demonstrate its practicality and effectiveness. The results reveal that initial lane configurations profoundly influence the activity lane planning. Notably, activity lanes are inclined to be arranged in adjacent segments within the network, providing greater socioeconomic benefits due to spatial agglomeration effects. This approach holds significant implications for effectively managing urban traffic flows and maximizing the utility of public spaces.