Top Downloaded

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month| Most Downloaded in Recent Year|

Most Downloaded in Recent Month

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Pedestrian Movement Characteristics with Mobile Phone Distractions YAO Ming, WANG Yuhang, CAO Shuchao, MA Luhan Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 364-372.   DOI: 10.16097/j.cnki.1009-6744.2025.02.033 Abstract （41）      PDF （2883KB）（120）       To investigate the impact of smartphone distraction on pedestrian movement trajectories, gait characteristics, and walking speed, this paper designed a controllable experimental scheme, and performed series of walking experiments under normal and three distraction conditions (reading, sending messages, watching videos). Based on image processing technology, high precision pedestrian trajectories were obtained, and the effects of different distractions were analyzed for trajectory, step length, step width, step time and walking speed. The results indicate that distracted behaviors lead to more disordered movement trajectories, with the video group showing the largest deviation distance, which is 33.98% greater than the normal group. Distraction also impairs pedestrian acceleration abilities, reducing walking speed. The video group shows a 26.78% decrease in acceleration, a 44.88% increase in relaxation time, and a 28.24% reduction in walking speed. As for gait characteristics, step length decreases as the level of distraction increases, while step width and stride time show opposite trends. Notably, the messaging group exhibits the shortest step length, the widest step width, and the longest stride time. A linear regression analysis reveals that step length increases with walking speed, while step width and stride time are inversely related to speed.

Select

Cascading Failure and ResilienceAssessment of Urban Traffic Congestion Risk Fields ZHAO Xueting, HU Liwei, ZHOU Jun Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 146-156.   DOI: 10.16097/j.cnki.1009-6744.2025.02.014 Abstract （30）      PDF （3919KB）（117）       This paper applies the information physics system to analyze the cascading failure process of urban traffic congestion risk field and proposes the quantitative method for toughness risk size assessment. A CPS(Cyber Physical Systems) control model is developed with mutual coupling of real traffic road network, traffic congestion prevention, and control type zoning of urban traffic congestion risk field in consideration of the multidimensional coupling characteristics of urban traffic congestion risk. The structural characteristics of the traffic domain is examined through the complex network theory. The CPS characteristic parameters are redefined, the four processes of CPS cascade failure are defined, and the CPS cascade failure model is developed with urban traffic congestion risk field. The risk factor is defined as the intervention point and the risk perturbation mechanism is elaborated through the network topology theory. The CPS connectivity is examined through the normalized quantitative node connectivity, delay time, average operating speed, average congestion length and other toughness indexes. The CPS damage perturbation and toughness are evaluated by different failure-recovery strategies, the indicators of the robustness, damage/recovery rate, and recovery capability. The results from case studies show that: (1) Guiyang city urban traffic congestion risk field CPS real traffic network consists of 170 intersections and 231 edges, and the traffic congestion prevention and control type zoning network consist of 21 traffic command areas and 41 edges. (2) The maximum and minimum degree value of the CPS model is respectively 22 and 1. The degree value obeys the power rate distribution function, has characteristic scale-free network features, and the mediator shows the exponential distribution. The degree value perturbation has the greatest influence on the real traffic network of Guiyang city, and the mediator perturbation has the greatest influence on the type of sub-districts of Guiyang city's traffic congestion prevention and control. (3) When t=2 , the network performance starts to decline under both meso and degree perturbation, and the meso perturbation affects the performance more than the degree perturbation, and both reach the lowest at t=7 . (4) The median recovery effect is better than the degree value recovery, under the median perturbation, the degree value recovery and median recovery effect of Guiyang city's real traffic network is poor, the toughness value is respectively 0.01123 and 0.01252, which is significantly lower than that of the toughness value of the traffic congestion prevention and control type of partitioning (0.1355). The proposed model provides reference for the quantitative evaluation and initiation of the traffic congestion control strategy at different stages.

Select

Effectiveness of New Energy Vehicle Incentive Strategies Considering Urban and Population Heterogeneity WENG Jiancheng, ZHOU Huiyuan, ZHANG Mengyuan, YU Jiangbo Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 2-14.   DOI: 10.16097/j.cnki.1009-6744.2025.01.001 Abstract （307）      PDF （2998KB）（250）       Formulating policies tailored to urban low-carbon development phases and resident characteristics is essential for optimizing incentive structures and promoting green mobility. This study evaluates new energy vehicle (NEV) incentive strategies across four city categories, considering factors such as air quality, NEV penetration, and charging infrastructure maturity. It analyzes social media data using the Latent Dirichlet Allocation (LDA) model and designs user surveys. A Latent Class Ordered Logit Model (LCOL) is employed to assess different urban populations' preferences for vehicle electrification incentives, identifying key impacted groups. The results indicate that immediate incentives, such as driving ban exemptions and significant fiscal subsidies, effectively enhance the purchasing intent of NEVs among less receptive residents. Conversely, more receptive residents respond better to regular, smaller subsidies. Cities with low NEV penetration exhibit a higher probability of purchasing under incentives, highlighting greater potential for improvement. Enhancing charging infrastructure significantly boosts purchasing intentions in infrastructure-deficient cities, with a 1% increase in likelihood for every minute reduction in charging time. However, this effect diminishes in cities with extensive charging networks. In metropolises with vehicle access restrictions, exempting NEVs from these increases purchasing probabilities by 3.5%. These insights guide NEV promotional strategy development in diverse urban settings.

Select

Comparison on Influence of Job-housing and Commuting Status on Travel Mode Choice in Multiple Types of Cities ZHOU Yuyang, ZHAO Congying, LI Jingkun, CHEN Yanyan, LIU Di, WANG Shuling Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 26-35.   DOI: 10.16097/j.cnki.1009-6744.2025.02.003 Abstract （30）      PDF （2873KB）（100）       Establishing a green and efficient travel service system is an important part of China's Green Travel Action Plan. It is necessary to consider the heterogeneity of job-housing status and commuting mode in different levels of cities. Based on 1788 valid questionnaires collected from three types of cities, the SEM-MNL model is constructed to quantitatively analyze the comprehensive impact of job-housing status, commuting attributes and personal economic characteristics on the choice of commuting modes in various types of cities. The findings reveal that the latent variable commuting attribute is the key factor affecting the travel mode, and the restrictive effect is more prominent in ordinary cities than in first-tier and new first-tier cities. Job-housing status indirectly affects commuting mode choice through commuting attributes. The path coefficients of three classes of cities are 0.83, 0.89, and 0.93, respectively. The effects of residential type on commuting distance and mode choice show an opposite trend in first-tier cities and ordinary cities. Highly educated travelers in first-tier cities prefer green travel modes, while in non-first-tier cities, the result is reversed. In new first-tier cities, residents with short commute distances have the highest proportion of renting, nearly half of them choose slow-speed transportation. Adjusting the job-housing distribution to increase the proportion of short-distance commuting can raise the share of green travel mode. As the city level declines, the feedback sensitivity of regulation increases. The research results provide differentiated policy recommendations for job-housing balance and transportation infrastructure planning in multiple types of cities. The results are conducive to promoting the low-carbon travel and contribute to the balance of urban transportation supply and demand and thus sustainable development.

Select

Simulation of Driving Strategies for Multi-lane Bottleneck Road Sections in An Environment with Autonomous Vehicles Penetration ZHANGJianxu, WU Chunxiang Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 69-81.   DOI: 10.16097/j.cnki.1009-6744.2025.02.007 Abstract （30）      PDF （3401KB）（70）       To explore the traffic efficiency and characteristics of multi-lane temporary bottleneck sections in a mixed intelligent connected autonomous vehicle (CAV) penetration environment, this paper designs car-following and lane-changing rules tailored to human-driven vehicles (HV) and CAV based on the continuous cellular automaton model. A car-following model was established based on HV slow start, and a lane-changing model was established considering lane-changing motivation, which can be divided into free lane-changing, inclined lane-changing, and mandatory lane-changing. For CAVs, an active lane-changing with facilitating platoon has been designed. The CAVs in middle lane can cooperate with those in the outer lane for lane-changing, providing lane-changing space for vehicles operating in the inner lane and facilitating the formation of CAV platoons in the outer lane. To verify the impact of this strategy on traffic flow in temporary bottleneck scenarios, a strategy without control experiment was set up to analyze the traffic efficiency of bottleneck sections under different CAV penetration rates and flow levels. The simulation results showed that, compared without strategy, ALC-FP strategy has reduces HV and CAV mandatory lane changing by 75% and 94.45%, respectively; The maximum increase in CAV platoon intensity is 50%, which facilitates the formation of CAV platoons passing through bottleneck sections; The average speed of vehicles passing through bottleneck can be doubled, the average delay of vehicles can be significantly reduced by up to 88.6%.

Select

Research Progress and Challenges on Equity in Flight Slot Allocation HU Rong, ZHANG Yutong, DING Jiahao, WANG Yiren, ZHANG Junfeng Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 1-15.   DOI: 10.16097/j.cnki.1009-6744.2025.02.001 Abstract （53）      PDF （1969KB）（69）       To further improve the feasibility of slot allocation results and reduce the unfairness among the participants in slot allocation, much literature has been studied on the fair allocation of flight schedules. By searching relevant databases at home and abroad, this paper systematically sorts out the individual fairness indicators and overall fairness goals in the optimization of existing slot allocations. Firstly, the development process and metrics of the concept of "fairness" are summarized, and the connotation of fairness in slot allocation is analyzed from three perspectives: horizontal/vertical, individual/overall and absolute/ relative. Secondly, the individual fairness index of each participant in the slot allocation are sorted out and compared based on the two dimensions of the number of slot adjustment and slot displacement. Then, from the perspectives of absolute fairness, relative fairness and Gini index, the overall fairness optimization objectives of the slot allocation model are summarized. The results show that the current fairness indicators are mainly constructed based on the principle of proportionality, while the weighted construction method is limited due to the difficulty of data acquisition and strong subjectivity. The research on the fairness goals has been relatively well-developed, and the Gini index has been widely used because of its global characteristics. Based on the content of the literature review, this paper further analyzes the shortcomings of existing studies and provides suggestions for future research. The study concludes that, in-depth research should be carried out in four aspects in the future: quantitative calculation of flight value, expansion of fairness research objects, construction of environmental fairness indicators and evaluation of the impact of dynamic parameters, to help the healthy and sustainable development of the civil aviation industry.

Select

Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 1-.   Abstract （251）      PDF （761KB）（158）

Select

Integrated Optimization of Grain Loading Strategies and Transportation Routes Considering Losses WAN Min, KUANG Haibo, JIA Peng, YU Fangping, MA Qianli, ZHANG Yige, ZHAO Sue Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 15-23.   DOI: 10.16097/j.cnki.1009-6744.2025.01.002 Abstract （177）      PDF （1877KB）（148）       A high-quality grain distribution system is critical to ensure the balance of grain supply and demand and food security. This study considers the perishable nature of grain types and aims to minimize the total costs of transportation, carbon emissions, and loss. An integrated optimization model is proposed to consider different loading methods (bagged-bulk-container) and various transportation modes (road-rail-sea). A case study was performed using the heuristic genetic algorithm in the "grain transport from North to South China" scenario in Northeast China. The results indicate that compared to bagged grain and bulk grain transport, multimodal transport of grain containers by rail, road, and water has clear advantages in terms of lower total cost and reduced loss. The proportion of grain loss cost in container transport, bagged grain transport, and bulk grain transport is 9.86%, 42.29%, and 29.82%, respectively. In the "grain transport from North to South China" process, roads are primarily used for local collection and distribution, while railways and waterways handle long- distance trunk transportation. When the delivery time requirements increase, the proportion of railway transportation would gradually increase, and the proportion of waterway transportation would decrease. When the total delivery time reaches 71.5 hours, the optimal transportation scheme would shift from container multimodal transport via road, rail, and sea to container multimodal transport via road and rail only. In the composition of total costs, the transportation costs and carbon emission costs of the optimal routes for the three loading methods are essentially the same. The study result also serves as a reference for the government regulatory agencies and logistics service providers that reducing grain transportation losses is an effective way to lower the overall logistics transportation costs.

Select

Strategic Approaches for Optimizing Queue Size in Connected and Autonomous Vehicle Platooning SUN Xu, MA Tianxing, WANG Tianshi, WANG Jianyu, LU Huapu Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 48-57.   DOI: 10.16097/j.cnki.1009-6744.2025.02.005 Abstract （36）      PDF （2665KB）（60）       This study aims to comprehensively explore the effect of queue size for effective mixed traffic flow in Connected and Autonomous Vehicles (CAVs). The study is segregated based on queue size, considering intra-platoon gap organization as well as inter-platoon relative positioning. A two-stage platooning strategy for CAVs is proposed and studied. A three-lane highway operation model is built based on cellular automata with parameters like CAV penetration rate and maximum queue size. The performance of the proposed strategy is compared with free-flow mixed traffic and another two-stage CAV platooning model. Comparison is made with respect to important traffic parameters like traffic flow capacity, density, lane changing frequency, driving speed, and CAVs' safety profile. The outcome demonstrates that, as compared with free-flow mixed traffic, two-stage platooning strategy increases traffic capacity around 16.78% in various CAV penetration rate conditions. In scenarios with moderate CAV penetration levels, the strategy contributes significantly in terms of safety, reducing cumulative collision risk time by 45.45%. Moreover, the platooning strategy demonstrates a critical scale where the optimal platoon size is limited to 6 vehicles at the one-stage and 14 vehicles at the two-stage.

Select

Traffic State Recognition Based on Vehicle Dynamic Behavior Characteristics LI Xiying, LU Meiyan, HE Zhaocheng, SU Shuyan, PANG Shumin Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 44-55.   DOI: 10.16097/j.cnki.1009-6744.2025.01.005 Abstract （194）      PDF （2497KB）（145）       Traffic state recognition research is of great significance for the prevention and mitigation of traffic congestion. It provides decision support for traffic management and also effectively enhances the operational efficiency of roads. Traditional traffic state identification methods typically take into account one single macroscopic characteristic parameter, while overlooking the impact of vehicle lane-changing behaviors and the consequent mutual interference among vehicles. This leads to a relatively coarse granularity in the state division space and insufficient refinement in state identification, thereby hindering in-depth analysis of traffic congestion causes. In response to this, this study proposes a traffic state identification method based on vehicle dynamic behavior characteristics from an Unmanned Aerial Vehicle (UAV) perspective. Firstly, the method combines a vehicle detection algorithm (YOLOv8-OBB) based on rotated bounding boxes and a vehicle tracking algorithm (BoTSORT) to detect and track vehicles, addressing redundant background pixels and overlapping vehicle bounding boxes within horizontal bounding boxes, extract more accurate vehicle trajectory data such as vehicle spatial direction angle and four-point rotation coordinates, and calculate microscopic traffic flow parameters. Secondly, by utilizing the obtained vehicle driving direction angles and rotated position information, this study proposes vehicle dynamic behavior characteristics parameters: lane change interference rate and vehicle direction fluctuation index. Combined with macroscopic average speed and traffic density parameters, a multi-dimensional state feature space is constructed and applied to traffic state identification in actual road scenes. The ultimate experimental results demonstrate that the method achieved an mAP@0.5 of 0.987 in the rotated vehicle detection, with stable and continuous vehicle trajectory data output. In traffic state recognition, by introducing the lane change interference rate based on the average speed and traffic density as macroscopic feature parameters, the state recognition precision reached 0.983. Moreover, incorporating the direction fluctuation index, the state recognition precision reached 0.987. Additionally, according to the state characteristic space representation, the traffic state enables accurate classification into four states: smooth state, steady state, crowded state, and blocked state. This allows for quantitative analysis of the impact of vehicle dynamic behavior on traffic state, and provides novel theoretical insights for traffic state recognition from a UAV perspective, offering advanced fine-grained perception capabilities for intelligent transportation systems

Select

Collaborative Optimization of Suburban Railway and Metro Train Operation Plans Under Interconnection Operational Mode PENG Qiyuan, LIU Siyuan, JIANG Shan, FENG Tao, CHEN Yao, ZHANG Yongxiang Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 36-47.   DOI: 10.16097/j.cnki.1009-6744.2025.02.004 Abstract （34）      PDF （2588KB）（53）       The train operation plan plays a crucial role in improving the operational efficiency of regional multi-standard rail under the interconnection operational mode. This study develops an integrated optimization model for the suburban railway and metro train operation plans and passenger flow assignment under the interconnection operational mode to minimize the total of passenger travel cost and the enterprise operational cost. The model simultaneously optimizes the train service routes on the entire line, the frequency, composition types, and stopping plan of trains on each service route, where practical constraints such as carrying capacity, train capacity, rolling stock resources, and the number of train services are considered. An improved adaptive large-scale neighborhood search algorithm is designed and its effectiveness is verified through instances with different passenger demand levels. The results show that: 1) The improved algorithm can provide a satisfactory solution, resulting in an average decrease of 3.6% in the objective function with an average computational time of 234 seconds compared to the two-stage approach;2) Compared to the independent operational mode, the interconnection operational mode reduces the enterprise operational cost by 11.3%, full-line and cross-line passenger travel costs respectively by 3.9% and 10.7%, the transfer times of cross-line passengers by 18.7%, and the number of rolling stocks used by 14.4%. 3) Compared to the all-stop pattern, the passenger travel cost is reduced by 4.2% on average after adopting the flexible-stop pattern for the suburban railway local and cross-line trains. The proposed method provides an auxiliary decision support tool for generating the suburban railway and metro train operational plans under the interconnection operational mode.

Select

Game Mechanism and Guiding Strategy of Intelligent Connected Transit Signal Priority WEI Liying, FENG Mei, WU Runze Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 95-107.   DOI: 10.16097/j.cnki.1009-6744.2025.02.009 Abstract （38）      PDF （2006KB）（51）       The ongoing development of intelligent connected technology provides crucial support for achieving transit signal priority (TSP) and assisting the development of the intelligent connected public transit towards "precision public transit" and "safe public transit". This paper starts from the conflict game relationship between different phases, and constructs a TSP guiding strategy based on chicken game in the intelligent connected environment. Firstly, the chicken game theory is used to analyze the game behavior of priority and non-priority phases of public transit, establishing a game model with weighted delay as the benefit matrix. Then, adopting the active priority and speed guidance, a TSP guiding strategy and optimization process based on the proposed game model is proposed by considering factors such as punctuality, limitation of minimum green time, priority and non priority phase delay of priority transit. Finally, to validate the strategy, a case study is conducted using an actual intersection in Beijing, employing SUMO for simulation. The results show that the TSP guiding strategy can effectively improve the traffic efficiency of priority phases and reduce the negative impact on non-priority phases compared to the initial timing; under the condition of 50% penetration rate, compared to the implementation of strategy, 20% of priority buses have been optimized significantly for punctuality, and the traffic efficiency indicators such as average queue length, average parking times and delay are reduced by at least 33.27%. Additionally, fuel consumption and CO2 emissions are reduced by at least 12.20%, and the negative influence of non-priority phase indicators is less than 8%.

Select

APeriodic Parking Reservation and Allocation Model Considering Comprehensive Benefits SONG Xianmin, LIU Bo, LI Haitao, ZHAN Tianshu, LI Shihao, ZHANG Yunxiang Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 24-35.   DOI: 10.16097/j.cnki.1009-6744.2025.01.003 Abstract （147）      PDF （3008KB）（114）       This paper proposes a parking reservation allocation optimization method based on the relationship between the direct revenue of the service platform and its service level in the parking allocation process, as well as the diversity of users' travel characteristics. To maximize the platform's operational service revenue, an optimized function is established with the operator's maximum revenue and the minimum comprehensive benefit of user travel costs as the objective. A periodic optimal parking reservation and allocation model (POPA) is developed in consideration of the time-effectiveness of parking allocation. An adaptive heating simulated annealing-particle swarm optimization algorithm is designed to solve large-scale parking allocation problems. The experimental results show that, considering the time-effectiveness and platform revenue of multiple factors, the optimal reservation period length for the reservation platform is 1 hour. The improved algorithm improves the solution effect by 6.14%. Sensitivity analysis proves that the introduction of punishment factors can improve the platform's user request acceptance rate by 2.25% to 18.17% without affecting the user's time cost and parking lot utilization rate. The proposed model has a 38.11% higher actual revenue than the user optimal model and a 15.31% lower average user travel cost than the platform optimal model. The expanded numerical test proves the applicability and effectiveness of the proposed model in large-scale complex scenarios.

Select

Energy-saving Driving Optimization for Connected Electric Buses Considering Station Arrival Strategies NAN Sirui, YU Qian, LI Tiezhu, SHANG Zandi, CHEN Haibo Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 82-94.   DOI: 10.16097/j.cnki.1009-6744.2025.02.008 Abstract （33）      PDF （2723KB）（50）       Considering the high energy consumption of bus operation especially when stopping at bus stations and signalized intersections, this paper proposes an energy-saving driving optimization method based on stop approach strategies. The SUMO platform is used to build intelligent connected vehicle simulation scenarios. A composite reward function is developed, and the driving efficiency, safety, and energy consumption are factored in. Stop arrival strategies and predefined traffic rules are incorporated as constraints into the Soft Actor-Critic (SAC) deep reinforcement learning framework to optimize vehicle trajectories when bus stops at the stations and approaches signalized intersections. The proposed SAC-ruled algorithm is tested under different scenarios, using real-world driving data and the conventional SAC-based optimization method as baseline methods. Results show that the proposed energy-saving driving optimization method shows a 35.97% reduction in vehicle energy consumption and a 21.67% improvement in travel time compared to the baseline methods. In lane-changing scenarios, energy consumption is reduced by up to 41.40%, with a 16.94% improvement in travel time. The proposed method demonstrates great adaptability to traffic flow fluctuations, as validated by sensitivity analysis. This method can be integrated into energy-saving assistance systems, encouraging drivers to adopt energy-saving behaviors.

Select

Regional Traffic Signal Control Methods Considering Lane Remaining Capacity DAI Liang, HUANG Zibin, ZHANG Zhonghao, LI Chenfu Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 108-118.   DOI: 10.16097/j.cnki.1009-6744.2025.02.010 Abstract （42）      PDF （2036KB）（48）       Intersection is the bottleneck of the overall traffic capacity of urban road networks, are the focal points of traffic organization, channelization, and management within the networks. Deep reinforcement learning is widely used in the field of traffic signal control at intersections, as it interacts with the environment to find target strategies, which aligns well with the complex and dynamic characteristics of traffic environments. This paper proposes a regional traffic signal coordination control method that considers lane capacity. By modeling the cooperation relationship between upstream and downstream intersections and introducing downstream lane capacity information into the maximum pressure method to design the reward function, a distributed regional traffic signal coordination control method is proposed based on multi-agent reinforcement learning algorithm. Performance verification is carried out using real road networks and traffic flow datasets from Jinan and Hangzhou. Compared with existing regional traffic signal control methods, the proposed method reduces the average travel time by 6.05%, the average delay time by 18.39%, the average queue length by 21.86%, and increases the throughput by 0.24%.

Select

Key Node Identification of Rail Transit Network Based on Gravity Influence Model ZUO Zhongyi, LIU Zeyu, YANG Guangchuan Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 102-112.   DOI: 10.16097/j.cnki.1009-6744.2025.01.011 Abstract （107）      PDF （2643KB）（255）       The identification of key nodes in a rail transit network is critical to evaluate the network robustness and develop risk resistant plans and therefore ensure efficient operation of the transit network. This paper considers the mutual influence between nodes in the rail transit network and selects the Degree Centrality (DC), Betweenness Centrality (BC) and Closeness Centrality (CC) as comprehensive measurement indicators of node importance. The real rail transit network is converted as the corresponding topological network. The key nodes of the rail transit network are identified through the gravitational influence model, and the differences in network performance under different influencing factors are analyzed to obtain the optimal gravitational influence radius and attack strategy. The study assesses the robustness of the rail transit network from a gravitational perspective, and proposes relevant improvement recommendations. The results indicate that the importance of nodes is composed of the gravitational attraction generated by the target node and other nodes. When the gravitational influence model has a gravitational radius R=8 and a dynamic attack strategy is selected, the relative size decrease rate of the largest connected subgraph is respectively 13.25% and 10.39% higher than that when R=7 and R=9. The relative size decrease rate of network passenger flow efficiency is respectively 5.12% and 6.71% higher than that when R=7 and R=9 . Compared with the FGM, GC, KSGC, CI recognition models, the gravitational influence model has obvious advantages in identifying key nodes in rail transit networks. In addition, after attacking the top 30 nodes, the relative size of the largest connected subgraph in Beijing's subway network decreases by 91.68%, and the relative size of network passenger flow efficiency decreases by 86.17%. The results show that the gravitational influence model is applicable and effective in Beijing's subway network. The proposed method provides a new perspective for analyzing network robustness and provides an effective basis for decision makers to create network risk prevention plans.

Select

Expressway Traffic Flow Prediction Method for Holidays Based on Diffusion Model LIN Peiqun, CHEN Zemu, ZHOU Chuhao Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 169-179.   DOI: 10.16097/j.cnki.1009-6744.2025.02.016 Abstract （37）      PDF （1859KB）（46）       Traffic management authorities require accurate traffic demand forecasts to implement effective traffic control strategies. However, the high uncertainty and suddenness of holiday traffic flows present significant challenges in generating precise pre holiday predictions. This research introduces a diffusion framework for predicting holiday traffic flow, grounded in diffusion probabilistic model theory, and further develops a Conditional Diffusion Model with Multi-feature Extraction (CDMME). The proposed CDMME integrates spatio-temporal characteristics of traffic flow, holiday attributes and meteorological factors to predict long-term traffic flow for holidays. Experiments are conducted using 15-minute and one-hour traffic flow data from 28 busy expressway segments in Guangdong Province, focusing on holidays such as New Year's Day, the Dragon Boat Festival and the Mid-Autumn Festival for model training and validation. The experimental results indicate that, for 15-minute and hourly total flow predictions, compared to the random forest (RF) model, the CDMME reduces the Weighted Mean Absolute Percentage Error (WMAPE) by 12.98% and 34.88%, respectively, while the Mean Absolute Error (MAE) increases by 1.47% for 15-minute prediction and decreases by 23.54% for hourly prediction. In comparison to the long short-term memory (LSTM) model, the CDMME reduces the WMAPE by 16.10% and 32.39% , respectively, and the MAE by 9.42% and 27.55% respectively. Additionally, when comparing hourly total traffic prediction with 15-minute total traffic prediction, hourly passenger traffic prediction and hourly truck traffic prediction, the WMAPE decreased by 29.57%, 12.23% and 30.42%, respectively, indicating that it has superiority in tasks with larger magnitude. Visualization result demonstrates that the CDMME effectively captures traffic peaks. Furthermore, the CDMME achieves peak average accuracy with a one-day advance forecast, with the accuracy of hourly total traffic prediction reaching 87.27%.

Select

Optimization of Recovery Strategy for China's Crude Oil Import Maritime Network from a Resilience Perspective SU Wan, LV Jing, ZHANG Lingye Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 36-43.   DOI: 10.16097/j.cnki.1009-6744.2025.01.004 Abstract （135）      PDF （1755KB）（107）       China's high dependence on imported crude oil, coupled with the escalating risks of disruptions in the maritime transportation network, necessitates urgent attention to optimizing recovery strategies and enhancing resilience. Based on actual transportation data, a model of China's crude oil import maritime network has been developed. A resilience assessment method using resilience curves and network efficiency indicators, has been proposed. An optimization model for recovery strategies is established with the objective of maximizing resilience and then applied to five simulated disruption scenarios. The results reveal that the optimal recovery strategy significantly accelerates network recovery across all scenarios, reducing resilience loss by up to 79.14% compared to traditional strategies. The model identifies crucial nodes that significantly impact the network under various scenarios, emphasizing the importance of prioritized recovery to enhance overall efficiency. Furthermore, relaxing detour cost constraints decreases resilience loss and alters the optimal node recovery sequence. The findings provide a foundational basis for decision-making in emergency recovery and resilience enhancement of China's crude oil import maritime network.

Select

Risk Identification Method for Abnormal Driving Behavior Based on Interpretable Ensemble Learning Model DENG Yuanchang, JIANG Yunxuan, TAO Shengqin Journal of Transportation Systems Engineering and Information Technology    2025, 25 (2): 180-189.   DOI: 10.16097/j.cnki.1009-6744.2025.02.017 Abstract （32）      PDF （2329KB）（44）       In order to accurately identify the risk of abnormal driving behavior and overcome the limitations of poor interpretability of existing models, this study collected vehicle motion data through natural driving test. Five types of abnormal driving behaviors were investigated: speeding, rapid shifting, sharp turning, short distance following, and dangerous lane changing. The risk coefficients of these behaviors were quantified using a threshold method, and the risk levels were classified using the CRITIC (Criteria Importance Through Inter-criteria Correlation) weight method and quantile method. A Stacking based ensemble learning identification model was constructed to identify the abnormal driving behaviors. The model combined training results from different learners. GBDT (Gradient Boosting Decision Tree), AdaBoost, and XGBoost that have the best comprehensive performance, selected as the primary learner combination, and logistic regression was used as the secondary learner. The SHAP (Shapley Additive exPlanation) algorithm was then used to analyze the influence of feature variables on the recognition results of the optimal Stacking model. Results indicate that the optimal Stacking model has an identification accuracy of 92.68%, achieving high precision in identifying abnormal driving behavior risks. Vehicle speed and time-to-collision of lane changing were identified as key features significantly impacting model recognition. Specifically, vehicle speed exceeding 95 km·h -1 and time-to-collision of lane changing less than 2.8 s both increase behavioral risk, and the risk level is higher when the vehicle speed exceeds 150 km·h -1. This study provides a feasible framework for identifying and interpreting the risks of abnormal driving behavior, which is expected to provide technical support for improving traffic safety levels.

Select

Lane-based Speed Regulation of Bottlenecks Under Mixed Flow Environment CAO Danni, WANG Tao, YANG Songpo, QU Yunchao, WU Jianjun Journal of Transportation Systems Engineering and Information Technology    2025, 25 (1): 76-85.   DOI: 10.16097/j.cnki.1009-6744.2025.01.008 Abstract （114）      PDF （2184KB）（230）       To address the congestion and secondary accidents on highways involving both Connected and Automated Vehicles and Human-driven Vehicles after abnormal incidents occur, this paper focuses on a single lane and proposes a lane-based speed regulation method. This study utilizes the controllability of Connected and Automated Vehicles by controlling the passing speed to indirectly guide the driving behavior of Human-driven Vehicles. The area near the bottleneck is divided into a speed limit area and a coordination area. In the speed limit area, the Connected and Automated Vehicles speed limit values for different lanes are determined based on real-time traffic flow at the bottleneck, and the number of vehicles flowing into the coordination area is controlled to alleviate the formation and propagation of congestion waves. In the coordination area, the Connected and Automated Vehicles movement on the incident lane is controlled to ensure that vehicles could pass through the bottleneck area safely and efficiently. A set of simulation experiments are conducted, and the effectiveness of the proposed method is verified from two aspects: efficiency and safety. The simulation results show that compared to an uncontrolled baseline scenario, the average traveling time of vehicles can be increased by 2.4% and the improvement rate of TET (Time Exposed time-to-collision) can reach 14% in a 50% Connected and Automated Vehicles market penetration rates environment. And in a 90% market penetration rates environment, the average travel time can be increased by 18.5%, and the TET improvement rate rises to 51%. This paper could provide strategic recommendations and methods to control the traffic flow when an incident happens under the mixed flow environment.