Journal of Advanced Transportation最新文献

In the context of increasingly complex and diverse traffic environments, where intelligent and connected vehicles (ICVs) coexist with conventional human-driven vehicles, maintaining reliable navigation under global navigation satellite system (GNSS) outages is crucial for supporting adaptive driving strategies and ensuring operational safety. Low-cost inertial measurement units (IMUs) offer promising solutions due to their low computational load and high self-sufficiency, yet error accumulation remains a persistent challenge, particularly in real-world mixed traffic scenarios. This study introduces a dilated convolutional neural network (DCN)–driven framework to directly estimate vehicle forward velocity and IMU error parameters from raw IMU measurements, addressing the reliance on hardware-based odometry by extending nonholonomic constraints (NHC) into three-dimensional velocity constraints. By dynamically optimizing IMU error parameters through integration with an error model, the proposed method mitigates the adverse effects of inherent noise in low-cost IMUs, enabling robust navigation in GNSS-denied environments. Validation using a GNSS/INS dataset demonstrates that the approach accurately estimates vehicle position while significantly suppressing error accumulation, which is pivotal for maintaining reliable navigation in heterogeneous traffic flows where autonomous and human-driven vehicles coexist. This contributes to the development of robust vehicle autonomy and enhanced safety in mixed-traffic ecosystems, enabling more adaptive and resilient driving strategies.

Traffic accidents are one of the leading causes of death and disability, as well as a significant source of economic losses for society. However, the nonlinear and heterogeneous relationships between environmental factors and traffic accidents are complex and difficult to comprehend. This study constructs an explainable spatial machine learning framework using a geographically weighted support vector machine (GW-SVM) model to address issues of nonlinearity, spatial heterogeneity, and interpretability. Based on a large-scale traffic accident dataset and multisource big data, this study provides both global and local explanations for the nonlinear relationships in California, USA. The study finds that (1) humidity plays a more important role in the relationship between environmental factors and traffic accident severity; (2) all environmental variables, including both natural and socioeconomic variables, exhibit nonlinear and threshold effects on traffic accidents; and (3) compared to the existing models, the GW-SVM model performs better in predicting the severity of traffic accidents on urban roads. The results of this study are significant for reducing traffic accident risks.

Owing to undersea-tunnel constraints concentrating off-ramp maneuvers in confined zones, this study optimizes graded lane-changing strategies to mitigate collision risks. Using the Jiaozhou-Bay Undersea Tunnel case, we propose an innovative exit diversion area graded lane-changing strategy comprising Transition Section I, Transition Section II, gradient section, and auxiliary lane. Six schemes were simulated via UC-WinRoad, with driver physiological stress quantified through Tobii eye-tracking as a novel application of pupil dynamics. Four indicators—lane-change position, lane-change rate, pupil diameter, and speed change—were weighted by the integrated analytic hierarchy process and entropy weight method (AHP–EWM) methodology and evaluated via the set pair analysis with the technique for order preference by similarity to ideal solution (SPA-TOPSIS) theory model. Optimal Scheme E (290-m transition I, 210-m transition II, 120-m gradient, and 140-m auxiliary lane) achieved γ = 0.968, significantly reducing pupil fluctuation by 32% compared with the shortest design (Scheme A) while ensuring smoothest speed control. This demonstrates effective conflict distribution in high-risk undersea environments, providing universally applicable design benchmarks for tunnel safety enhancement.

Urban expressways serve as the main arteries of urban transportation. Congestion and traffic disruptions on expressways can easily lead to the paralysis of the entire regional transportation system. Accurately understanding the patterns of congestion formation and influencing factors on expressways is beneficial for improving traffic efficiency and reducing travel costs. This study takes typical sections of expressway diverging and exit sections as examples, introducing traffic data provided by navigation systems to explore the potential influencing factors and formation processes of urban expressway traffic congestion. This study explores the effects of operating conditions, control facilities, road properties, weather, and other factors on the smoothness of exit sections based on navigation and field survey data. The traffic congestion index is used as an indicator of congestion degree to evaluate the smoothness of typical area of urban expressways exit sections and the overall safety of urban roads. A structural equation model is used to construct a traffic congestion impact model. The results show that traffic facilities (β = 0.462, p < 0.001), road conditions (β = 0.177, p < 0.001), road location (β = 0.129, p < 0.001), spatiotemporal characteristics (time of day: β = 0.295, p < 0.001; day of week: β = −0.105, p < 0.001), environment (β = 0.021, p < 0.001), and driving behavior (β = 0.326, p < 0.001) have a significant impact on traffic congestion. And driving behavior can be used as an intermediate variable to affect the relationship between transportation facilities, road conditions, road location, spatiotemporal characteristics, environment, and traffic congestion. The research contributes to a precise understanding of the formation patterns and influencing factors of urban expressway traffic congestion, laying the groundwork for the adoption of targeted traffic management measures to improve traffic flow efficiency and reduce accident occurrences.

Regional rapid rail transit is an emerging rail transit system in China in recent years, with the same level of service frequency and longer station spacing as metro. The traditional fixed train composition mode has weak adaptability to its unbalanced transport demand in time and space, leading to high rolling stock traveling kilometers and operation costs. As a novel operation strategy, the flexible train composition mode can make up for this shortcoming, but the matched rolling stock circulation planning is a complex optimization problem. This paper proposes an operation mechanism of the rolling stock circulation plan under flexible train composition mode with multiple coupling/decoupling operation sites for regional rapid rail transit, where trains can change compositions at both terminal and intermediate stations. A mixed-integer nonlinear programming (MINLP) model is constructed for rolling stock circulation planning based on the proposed mechanism. The optimization objective is to minimize the total operation costs of train services, depot entry/exit processes, and coupling/decoupling activities at terminal and intermediate stations. The model is then reformulated to an equivalent mixed-integer linear programming (MILP) model, which can be solved by the CPLEX solver. A numerical experiment based on the real-world data from a regional rapid rail transit line in China is designed to verify the effectiveness of the model and solution approaches. The results show that the obtained rolling stock circulation plan effectively reduces the rolling stock traveling kilometers and operation costs with the pregiven timetable. The methods in this paper provide dispatchers with more options to better match the transport demand of regional rapid rail transit.

To enhance the rationality of lane-changing decisions and the adaptability of trajectory planning, this study incorporates short-term driving styles to construct a multiobjective optimized lane-changing trajectory planning model based on naturalistic driving data. First, lane-changing behavior rules were defined to extract lane-changing and lane-keeping data. Essential factors influencing lane-changing behavior were identified using the eXtreme Gradient Boosting (XGBoost) model. Based on the essential factors, drivers were classified into three categories (conservative, moderate, and aggressive) using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, which revealed the behavioral difference during lane-changing. Subsequently, an attention-enhanced long short-term memory (LSTM) network was employed to predict surrounding vehicle trajectories, generating dynamically updated environmental parameters. Further considering comfort and safety benefits during lane-changing, a multiobjective trajectory planning model was developed. Reinforcement learning algorithms iteratively optimized the trajectories to derive the optimal trajectory. Finally, the behavioral characteristics of planned trajectories for the three categories of drivers and the deviations between planned and actual trajectories were compared. Results indicate that planned trajectories exhibit shorter lane-changing length and higher efficiency compared with actual trajectories. Planned trajectory can smooth microlevel behavior and improve safety and comfort during lane-changing. For different types of drivers, conservative drivers show the longest lane-changing length but smallest headway space distances, which reflects drivers’ caution during lane-changing. Aggressive drivers mostly focus on speed improvement. The findings can be applied to vehicle trajectory planning in connected environments, which can enhance the lane-changing efficiency while ensuing safety.

High-speed railway (HSR) station area is the key focus of urban construction, and the development of HSR station area has significant regional differences. This study adopts the association rule mining model and ordinary least squares (OLS) regression method to explore the relationships among the development level of the station-setting cities, the development level of the HSR station area, and the urban vitality of the HSR station area. It further investigates how each factor influences the urban vitality in the HSR station area. Findings reveal a prominent multicenter clustering pattern in the urban vitality of the HSR station area. The association rule mining analysis reveals a clear and complex link between the urban vitality in the station area and the influencing factors of the development level of the station-setting cities and the development level of the HSR station area. OLS regression analysis results indicate that the proportion of the tertiary industry in GDP and the intensity of intracity travel are significantly positively correlated with urban vitality in the HSR station area, directly contributing to the growth of the urban vitality. The study’s innovation mainly lies in utilizing multisource data to analyze the spatial pattern characteristics and influencing mechanism of the urban comprehensive vitality in the HSR station area from multiple perspectives, as well as applying association rule mining to explore the correlations between urban vitality in the HSR station area and its determinants. From the perspective of urban vitality, gaining deeper insight into the overall development status of the HSR station area and identifying the factors that affect the urban vitality of the HSR station area can support efforts to enhance the vitality of the broader urban environment.

It has been almost 2 decades since the opening of the rail freight market in the EU came into force. The individual Member States have put different liberalization measures into practice, and the situation on the market still varies from country to country. Efforts to create a single European rail market therefore still seem to be unfulfilled, while, at the same time, the call for a shift of freight transport from road to rail in the context of the European Commission’s decarbonization targets is growing stronger. This paper provides a detailed overview of the rail freight market liberalization process and new market entrants in the EU Member States. A trend analysis of the time series was carried out, taking into account the current status of liberalization measures and the development of transport services since 2007. The resulting model uses cluster analysis as the main approach for grouping the countries based on the similarities in the rail freight market, taking into account the performance indicators, the number of licensed railway undertakings in the market and their evolution, and, last but not least, the change in the modal share of rail transport during the period considered.

As an indispensable component of the modern high-quality national comprehensive three-dimensional transport network, air and high-speed rail intermodal transportation (Air–HSR) plays a pivotal role in advancing “transportation integration.” The transfer process in Air–HSR represents a critical touchpoint of service experience, and the investigation into passengers’ preferences for transfer service attributes is instrumental in providing civil aviation enterprises with a more personalized foundation for product development. First, six resource-matching attributes of Air–HSR are extracted by introducing the resource-matching theory (RMT) and drawing on the consumer behavior analytical methods. Subsequently, incorporating the perceived risk theory (PRT) and perceived value theory (PVT), a quantitative framework for passengers’ preferences for service attributes of Air–HSR transfer (RPP-F) is proposed from the dual perspectives of perceived risk (PR) and perceived value (PV). Then, an analysis model (PR–PV–SEM) is constructed with PR and PV as mediating latent variables to examine passengers’ preferences for service attributes of Air–HSR transfer, and the preferences are analyzed through the lens of latent variables. Finally, based on measurement data of passengers’ diverse preferences, passengers’ heterogeneous preferences are analyzed and interpreted through the lenses of latent variables and socioeconomic attributes via multisampling approaches, and the internal preference structures of different attribute groups are deeply explored. The model results demonstrate that the PR–PV–SEM with PR and PV as mediating latent variables exhibits excellent model fit with its explanatory power for passengers’ adoption intention reaching 73%. This finding reveals the mediating mechanism between objective services and subjective willingness via PR and PV and provides a novel perspective for subsequent analysis of travel service preferences.

The present road traffic safety situation faces significant challenges. Examining the influences of diverse contributing factors on road traffic crashes is of crucial importance. However, different factors may have different influences as the change of location and time and the neglect of potential heterogeneity while modelling the frequency of traffic crashes may lead to biases in parameter estimation and incorrect inference. To address the unobserved spatiotemporal heterogeneity and accurately explore the correlations between contributing factors and fatal traffic crashes, a fixed effects panel model with structural breaks is applied to identify the influences of crucial factors on fatal traffic crashes from a macroscopic level. A multisource dataset, including fatal crash numbers, socioeconomic factors, laws and regulations and climate factors is collected from the United States spanning 45 years (from 1977 to 2021). The climate change events (i.e., El Niño–Southern Oscillation phenomena) are examined for their influences on fatal traffic crashes. The experimental results illustrate that high temperatures and frequent meteorological disasters have increasing impacts on fatal crash numbers. High precipitation shows a decreasing one from a macroscope level because of the lagged effect of precipitation on crashes across days. Particularly, the climate change events (including EP E1 Niño, CP E1 Niño and La Niña) represent an adverse impact on road traffic safety. Additionally, the states with similar meteorological characteristics are categorized as high temperature, high precipitation and frequent meteorological disaster subsets for separate analysis. Under these subsets, rural trip proportion becomes a more pronounced factor that affects fatal road traffic crashes, and helmet laws are more efficient in reducing fatal crash frequency. The research findings reveal an increasingly complex road traffic safety environment in the context of global warming, offering valuable perspectives for enhancing road traffic safety.