Journal of Advanced Transportation最新文献

In order to accurately predict the lane-changing trajectory of the vehicle and improve the driving safety of the vehicle, a lane-changing trajectory prediction model based on the combination of convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) neural network is proposed by comprehensively considering the historical driving behavior, the spatial characteristics of surrounding vehicles and the bidirectional time sequence information of the vehicle trajectory. Firstly, the vehicle trajectory data are filtered and smoothed, and it is divided into three categories: left lane change, right lane change, and straight driving, and a lane change trajectory sample set is constructed. Secondly, CNN-BiLSTM model is constructed to identify the sample set of lane-changing trajectory. Considering the interaction between vehicles in the driving process, the information of predicted vehicle, and surrounding vehicles is taken as the input of the model. The extracted feature vector is input to the BiLSTM layer for prediction after the CNN layer feature extraction, and the horizontal and vertical coordinates of the target vehicle at the next time are output. Thirdly, the trajectory data of the US-101 dataset in NGSIM is selected to verify the performance of the CNN-BiLSTM model, and at the same time, it is compared with models such as CNN-LSTM, long short-term memory (LSTM), BiLSTM, and CNN-GRU-Att. Finally, the verification result shows that the overall fitting degree of the vehicle lane change trajectory prediction of the proposed model reaches 99.50%, and the mean square error and mean absolute error are 0.0003076 and 0.01417, which are improved compared with other models. In the meanwhile, the research on multistep trajectory prediction in different prediction time domains is carried out. It was found that the longer the prediction time domain is, the lower the prediction performance of the model decreases, but the prediction accuracy still reached more than 96%, and it was able to accurately predict the lane change trajectory.

Accurately predicting origin-destination (OD) passenger flows serves as the basis for implementing efficient plans, including line planning and timetabling. However, due to the complexity and variety of OD passenger flows types, general prediction models have difficulty in capturing the features of different OD passenger flows, which in turn leads to poor prediction performance. To address this issue, we propose an integrated framework that combines clustering and prediction methods. First, an unsupervised deep learning model is devised to automatically cluster OD flow types by capturing shape characteristics. Second, three types of features are created to enhance training efficiency, including static features, time-dependent observed features, and time-dependent known features. Based on the clustering of OD passenger flow, a weighted adaptive passenger flow prediction model is developed. The study employs a temporal fusion transformers model to enable multitype OD passenger flow prediction. In the numerical experiments, the model was applied to the urban rail transit in South China, and the model clustered 15,168 OD pairs into 4 types for prediction. The findings show that this approach enhanced the prediction accuracy by 2.0%–9.6% compared to the LSTM model and by 1.6%–4.3% compared to the Graph WaveNet. Moreover, the model can accurately assess the various features for diverse types of OD flows.

Connected vehicles (CVs) leverage the vehicle-to-everything (V2X) function to interact with various mobility systems. In China, regulations mandate that CVs must possess automatic recording capabilities as stipulated by the “Management Specification for Road Tests of Intelligent CVs.” Yet, public perception of these functionalities and their impact on the acceptance of V2X technology remains unclear. This study explores the acceptance of V2X in China by augmenting the Unified Theory of Acceptance and Use of Technology (UTAUT) framework. Utilizing a survey of 567 Chinese drivers, we employed structural equation modeling (SEM) and Multiple Indicators Multiple Causes (MIMIC) analysis to dissect the factors influencing the behavioral intention (BI) to use V2X. Our findings reveal that social influence (SI), facilitating conditions (FC), and effort expectancy (EE) significantly predict the intention to adopt V2X. Interestingly, while trust (T) does not exert a direct influence, its overall effect on BI surpasses those of the previously mentioned factors. Moreover, the MIMIC models highlight that individuals’ understanding of V2X significantly shapes their acceptance attitudes. These insights underscore the importance of enhancing T, particularly in the data security aspects of V2X, to bolster its acceptance in China. By addressing these concerns, stakeholders can pave the way for wider adoption of this pivotal technology.

To meet the evolving demands of land use and transport interaction (LUTI) assessment within China’s national territory spatial planning (NTSP) system, this paper introduces the level of development (LoD) and the level of matching (LoM) evaluation models, based on the traffic facility and land use factors. The LoD model, founded on the modified node-place model, provides a comprehensive assessment of the traffic facility and land use development scales. Conversely, the LoM model, grounded in data envelopment analysis methods, evaluates the relative relationship between transport services and the travel demand generated by land use. The integrated use of LoD and LoM can both reflect the development scale and matching status between traffic services and travel activities, which are crucial contents in the planning works, especially within the NTSP framework. The proposed models are tested in the city of Guangzhou, and the LoD values exhibit peaks in central urban zones, suburban towns, and areas adjacent to railway transit, with a decline observed in rural farmland and ecological regions. In contrast, the LoM distribution performs a distinct pattern, highlighting numerous underperforming areas with congestion or idle problems in urban centers, alongside well-coordinated regions showcasing a balance between traffic facilities and land uses in rural regions. Furthermore, the LoM scores revealed frequent instances of facility crowding in urban regions and intensive occurrences of facility idleness in rural areas. By marking regions with low LoD scores, the LoD model finds suitable application in determining the urban development border, essential for restricting land development and preserving farmland and ecological areas. Meanwhile, LoM aids in improving urban renewal efforts by assessing and optimizing the balance between intensive land uses and limited traffic facilities. Validated against the existing metrics, the combined use of LoD and LoM efficiently captures the most details of the LUTI process at the lowest computational cost.

Transit signal priority (TSP) is a traffic control strategy aiming at prioritising public transit vehicles at signalised intersections. The emergence of connected vehicles (CVs) provides the opportunity to enhance TSP operation, mitigating challenges such as the negative impact on nontransit users and the management of conflicting priority requests. Furthermore, traffic control policies produce environmental impacts, whilst TSP strategies are typically evaluated based on common traffic flow indicators, such as average vehicle speed, delay and/or the number of stops. In light of the recent progress made in CV technology, we propose and assess two user-based TSP strategies. The first approach aims to minimise total user delay at a signalised intersection, whilst the second considers both reducing bus schedule delay and total user delay. We also measure the environmental effects of these TSP strategies. A microscopic simulation environment is used to compare the proposed methods’ performance against a conventional TSP ring-and-barrier controller in a case study involving two adjacent signalised intersections in Helsinki, Finland. The findings indicate that implementing the proposed strategies effectively enhances TSP performance whilst also lowering adverse environmental impacts.

Accurately understanding the travel demand of urban rail transit (URT) systems is crucial for effective operational management. Despite the recognition that the diversity in human activity patterns results in different travel demands, few studies have thoroughly investigated the heterogeneity among passengers and its impact on URT ridership. This study utilizes smart card data collected from the Beijing Subway to categorize passengers into four groups: tourist passengers, flexible commuters, regular commuters, and life-oriented passengers, based on their spatiotemporal travel patterns. Furthermore, a Multiscale Geographically Weighted Regression (MGWR) model is employed to examine the relationship between station-level ridership of URT and its determinants, including the built environment and station properties, for each passenger group. The results indicate that the influence of these determinants on station-level ridership varies across passenger groups and spatial scales. For instance, regular commuters exhibit lower sensitivity to accessibility on workdays, whereas those unfamiliar with the URT network are more concerned about the bus accessibility in pedestrian- or bicycle-unfriendly areas. Notably, for tourist and life-oriented passengers, the stations significantly affected by population density are concentrated in areas with a higher proportion of elderly individuals. Conversely, for flexible and regular commuters, these stations are predominantly situated in areas associated with internet technology and scientific research. These findings are valuable for policymakers in designing strategies tailored to different passenger groups to balance trip demand and capacity, thereby improving URT services and promoting a sustainable urban environment.

Accurate prediction of bus arrival time is essential to achieve efficient bus dispatch and improve bus trip sharing rate. This article proposes using the improved whale optimization algorithm–long short-term memory (IWOA–LSTM) model to predict bus arrival times and improving the whale algorithm by optimizing the hyperparameters of the LSTM model, so that the advantages and disadvantages of the whale algorithm and the LSTM model can complement each other, thus enhancing the robustness of the model. Initially, the bus arrival process and its associated influencing factors are analyzed, with certain factors being quantified to serve as input features for the prediction model. After processing the GPS data of the No. 220 bus in Nanchang, Jiangxi, China, the proposed prediction model is analyzed and validated using an example and compared with other prediction models. The results show that the IWOA–LSTM prediction model has the best-fitting effect between the predicted values and actual values in all time periods. Its MAPE, RMSE, and MAE have been reduced by at least 9.47%, 12.77%, and 8.93%, respectively, and the overall R² has been improved by at least 10.65%. These results indicate that the model has the best predictive performance.

The cascading reliability problem of international railway freight network is becoming noticeable due to the limitation of node transportation capacity with increases in the transport volume of the international railway freight trains. We discuss this problem in this study, thereby focusing on the failure process of the international railway freight network. As the first step, we consider three factors of node degree, node betweenness, and edge betweenness based on the complex network theory, and establish the node model using coupled map lattice method. Next, we select three indicators to evaluate the reliability characteristics of the network and evaluate the robustness of the network with the maximum effective graph and the network efficiency. Finally, we apply the model to the China Railway Express freight network and consider two situations: cascading failures and noncascading failures that are corresponding to two strategies: redistributing cargoes and disbanding cargoes. The results show that the cascading reliability of the China Railway Express freight network is not high. The indicators decrease less than 10% under noncascading failure, while more than 40% under cascading failure, so the network is more reliable under noncascading failure. Our research provides a new way to test the cascading reliability of the international railway freight network and provide different strategies for improving reliability.

Hazardous materials pose significant dangers during transportation due to their flammable and explosive properties. The consequences of accidents involving such materials are often severe and irreparable. A well-designed hazardous materials transportation network can mitigate these risks. However, designing such a network presents two major challenges: quantifying the risk associated with hazardous materials transportation and addressing the hierarchical relationship between government and companies. To address these challenges, we enhance the accuracy of accident probability estimates and the comprehensiveness of accident consequence assessments, incorporating the uncertainty of accident outcomes. We propose a comprehensive risk assessment model and develop a bilevel programming model to reflect the hierarchical relationship. In this model, the government at the upper level aims to minimize the total risk, while companies at the lower level seek to minimize their total costs. The model is transformed using chance-constrained programming and solved using heuristic algorithms. We apply the model to the highway network in Anhui province, China, to verify its validity. The results demonstrate that the model effectively manages the hierarchical relationship between government and companies, reduces the risk of hazardous materials transportation, and enhances the stability and safety of the transportation network.

The primary objective of this paper is to minimize the overall travel costs for passengers while simultaneously maximizing the operational revenue for the transportation company. This is achieved through the optimization and adjustment of various factors, such as the intervals between regular bus and subway services, the duration of vehicle stops at each station, and the pricing structure for subway and shared bicycle usage. By enhancing the efficiency of passenger travel, we have successfully bolstered the company’s operational profits. In contrast to prior research, this paper comprehensively considers the dual uncertainties associated with both bus operations and shared bicycle operations within a cooperative system. By establishing a coordinated dual-level optimization model for regular bus, subway, and bike-sharing networks under dual uncertainty conditions, we employed convex combination techniques to unify the dual uncertain variables into a single objective, which was then incorporated into a chance-constrained bilevel programming model. Ultimately, we utilized KKT conditions to transform the model from a bilevel to a single level for resolution. This paper centers its research on the collaborative system comprising the Nanchang Metro Line 1, Bus Route 520, Bus Route 211, and the adjacent region hosting a cluster of shared bicycles. By leveraging Python programming, optimization models, empirical data on traffic flow and stoppage times, and OD data, we conducted an optimization analysis to solve the problem at hand. According to the optimization results, passenger waiting time, passenger transfer time, and passenger on board time are effectively reduced by 6.81%, 18.29%, and 23.92%. At a confidence level of 95%, the resulting time level results in a 12.44% reduction in total travel time. The average subway fare increased by 18.12%, the average shared bicycle fare decreased by 19.12%, and the total cost of travel expenses increased by 16.68%. The final total cost of travel was reduced by 4.06%, and the business operating income was increased by 13.10%. The comprehensive optimization results have effectively fulfilled the objectives of the bilevel optimization model, thereby confirming the rationality and practicality of the optimization approach. The research outcomes hold significant practical implications for facilitating the efficient and cooperative development of urban transportation networks, ultimately enhancing the convenience of residents’ travel experiences.