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|

In last 2 years

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Drone Delivery: A Systematic Review on Technology, Efficiency, and Applications WU Jingqiong, DIAN Ran, ZI Taisheng, LI Yunqi Journal of Transportation Systems Engineering and Information Technology    2025, 25 (6): 34-49.   DOI: 10.16097/j.cnki.1009-6744.2025.06.004 Abstract （1949）      PDF （2284KB）（914）    PDF(English version) （466KB）（18）    With the rapid development of e-commerce and a surge in demand for instant delivery, drone delivery, as an innovative solution in the logistics sector, is driving profound transformations in the logistics system. This paper synthesizes findings from 74 relevant articles published between 2015 and 2024, comprehensively examining drone delivery research advancements across key dimensions including critical technologies, economic benefits, environmental sustainability, application potential, and system synergy. The results indicate that drone delivery primarily relies on path planning algorithms, energy management, and multi-drone collaboration as its core technologies. Related optimization research has evolved from single-objective to multi-objective coordination, with algorithms transitioning from classical heuristics to intelligent approaches, effectively reducing solution time and optimizing costs. However, nonlinear effects of payload and wind resistance, along with adaptability to harsh weather conditions, remain bottlenecks. In terms of economic benefits, drone-vehicle collaborative systems can significantly reduce customer waiting time, delivery costs, and labor demands through optimized path planning and resource scheduling. Integration with public transit systems (bus/subway) effectively expands service coverage while reducing energy consumption. Multi-objective optimization models dynamically balance energy consumption, cost, and timeliness to further enhance synergistic benefits. Nevertheless, economic viability remains constrained by payload and range limitations, showing greater advantages in short distance, lightweight deliveries, particularly for emergency cargo deliveries. Environmental benefit analyses demonstrate that the operational phase of drone delivery exhibits significantly lower carbon emissions than traditional transportation methods, though a comprehensive lifecycle assessment encompassing manufacturing, operation, and recycling phases is required. Regarding applications, drone delivery technology demonstrates unique value in medical supply distribution, emergency logistics, and urban "last- mile" delivery, with particular advantages in remote areas and urgent emergency scenarios. However, challenges persist regarding safety risks, technological innovation gaps, limited social acceptance, and imperfect policy regulations. Future research should prioritize battery technology breakthroughs, intelligent path planning optimization, privacy/security safeguards, and cross regional policy coordination to accelerate drone delivery commercialization.

Select

A Review of AI-driven Trajectory Prediction Methods for Autonomous Vehicles TIAN Daxin, XIAO Xiao, ZHOU Jianshan Journal of Transportation Systems Engineering and Information Technology    2025, 25 (5): 1-24.   DOI: 10.16097/j.cnki.1009-6744.2025.05.001 Abstract （2007）      PDF （1838KB）（883）       In autonomous driving systems, trajectory prediction plays an important role in connecting vehicle's perception and decision-making, and enhancing driving safety and overall system robustness. In recent years, with the continuous advancement of artificial intelligence (AI), the AI-driven trajectory prediction methods have seen significant progress in terms of accuracy, adaptability, and the capability to model complex traffic environment. This paper provides a systematic review of mainstream trajectory prediction methods in autonomous driving, with a focus on predictive model frameworks. It first revisits traditional physics-based approaches, and then highlights current research trends, including modeling paradigms based on classical machine learning, deep neural networks, and reinforcement learning. Additionally, recent developments in explainable AI techniques aimed at improving model transparency and safety are discussed. Based on comparative analysis, the paper evaluates the strengths and limitations of various models in interaction modeling, multimodal uncertainty, and generalization capability. Furthermore, it organizes trajectory prediction evaluation metrics and publicly available trajectory prediction datasets according to their characteristics and application scenarios, and summarizes representative real-world deployments from both domestic and international sources. At last, considering the existing research bottlenecks and future development trends, the paper outlines potential directions for future studies, such as enhancing model interpretability, effectively integrating multimodal information, and designing unified frameworks for joint prediction and planning. The purpose of this review is to provide insights and references that can be used in the future research and applications.

Select

Prediction of Outbound Transportation Volume of Xinjiang Coal Railway by Integrating Sparrow Search with Long Short-Term Memory LI Haijun, ZHANG Xiaoyang , GAO Ruhu , WEI Dehua, CHEN Xiaoming Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 14-23.   DOI: 10.16097/j.cnki.1009-6744.2024.05.002 Abstract （555）      PDF （2275KB）（738）       To enhance the precision of predicting the Xinjiang's coal railway outbound volume transportation, a prediction model integrating the sparrow search algorithm and the long and short-term memory network (SSA-LSTM) is proposed. The model introduces the sparrow search algorithm to optimize the hyper-parameters of the LSTM model in order to improve the model prediction performance. Based on the data of Xinjiang coal rail outbound transportation volume from 2015 to 2022, the gray correlation analysis is employed to comprehensively evaluate the impact of factors, including economic and transportation aspects, ensuring that the selected factors exhibit a strong correlation with the prediction targets. Among the influencing factors, the GDP data is adjusted for Consumer Price Index (CPI) effects, and the refined data are then fed into the model for prediction. Finally, the model is applied to predict the Xinjiang's coal rail outbound transportation volume across short, medium, and long time horizons. The results demonstrate that the SSA-LSTM model outperforms both the BP neural network and the conventional LSTM model, achieving a Mean Absolute Percentage Error (MAPE) of 0.88% and a Root Mean Square Error (RMSE) of 49.9. Furthermore, incorporating CPI processing into the prediction process significantly reduces the prediction error, with MAPE and RMSE decreasing by 75.8% and 56.2%, respectively, compared to non-CPI-processed predictions. This study provides an effective approach for predicting Xinjiang's coal rail outbound transportation volume, offering important data insights that inform the strategic design of coal transportation routes out of Xinjiang.

Select

Research on Energy Consumption and Carbon Emissions in the Whole Life Cycle of Beijing-Xiong'an Intercity Railway CAO Meng, YUAN Zhenzhou, YANG Yang, NIE Yingjie, NA Yanling, SUN Yunchao, CHEN Jinjie Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 37-44.   DOI: 10.16097/j.cnki.1009-6744.2024.05.004 Abstract （1343）      PDF （1339KB）（725）    PDF(English version) （341KB）（43）    As the backbone of green transportation, intercity railways play a supporting role in reducing energy consumption and achieving the goal of "carbon peak and carbon neutrality". This paper analyzes the development trajectory and energy consumption patterns of intercity railways in China, with a particular focus on the entire lifecycle of planning, design, construction, and operation within the context of the "dual carbon" initiative. Utilizing the Beijing-Xiong'an intercity railway as a prototypical case, the paper examines energy consumption and carbon emissions across its lifecycle, incorporating the influence of energy-saving, emission-reduction strategies, and green carbon sink measures. The findings reveal that carbon emissions during the planning and design phases are negligible, whereas the energy consumption during the operation stage dominates, accounting for approximately 74.9% of the total annual lifecycle energy consumption. Additionally, the energy consumption attributed to building materials production (scaled to 100 years) constitutes roughly 22.4% of the total. Notably, the implementation of energy conservation, emission reduction, and green carbon sequestration measures has yielded substantial outcomes, achieving an average annual energy savings of approximately 12%. When compared with similar railway energy consumption indicators globally, the Beijing- Xiong'an intercity railway's unit transportation traction energy consumption of 6.42 tce per million person-kilometer aligns with expectations. Furthermore, its carbon reduction impact is significant in diverting highway passenger traffic, savings approximately 612.67 million yuan in carbon sink transactions and generating substantial societal benefits. This comprehensive analysis offers valuable insights and reference for the establishment of a green and low-carbon intercity railway carbon emission dual control indicator system.

Select

Urban Road Traffic Accidents Prediction Based on Image Sequence Analysis HU Zhenghua, ZHOU Jibiao, MAO Xinhua, ZHANG Minjie Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 91-102.   DOI: 10.16097/j.cnki.1009-6744.2024.05.009 Abstract （787）      PDF （3453KB）（705）       To further improve the accuracy of traffic accident prediction in road networks, a short-term traffic accident prediction method based on sequential image analysis is proposed. First, an oversampling technique is applied to interpolate traffic accident data collected from a WeChat mini-program to mitigate the impact of extensive zero values within the data on model training accuracy. These data are then integrated with road network traffic flow and accidentrelated attributes to generate stable time series as input for the model. A Bidirectional ConvLSTM U-Net with densely connected convolutions (BCDU-Net) is constructed. In this model, bidirectional ConvLSTM structures are used to integrate the features from the encoder and decoder layers, comprehensively capturing spatiotemporal correlations in the sequential data. Additionally, densely connected convolutions are employed to concatenate feature maps in the depth dimension, ensuring that each layer can directly access gradients from the loss function. Finally, the performance of the proposed model is evaluated by comparing the predicted results with actual traffic accident data. The results show that, compared to the Fully Connected Long Short-Term Memory (FC-LSTM) model, the Convolutional LSTM (ConvLSTM) model, and the U-Net model, the proposed model achieves reductions in cross-entropy loss of 65.96%, 15.70%, and 3.47%, reductions in root mean square error of 21.48%, 3.13%, and 1.71%, and increases in precision of 75.06%, 11.82%, and 3.08%, respectively. It is demonstrated that the proposed method offers superior performance in predicting urban road traffic accidents.

Select

Review of Modular Transit Vehicles Scheduling Research SONG Cuiying, DING Jie, ZHANG Chunbo Journal of Transportation Systems Engineering and Information Technology    2025, 25 (4): 175-192.   DOI: 10.16097/j.cnki.1009-6744.2025.04.017 Abstract （568）      PDF （1588KB）（697）       Modular Transit Vehicles (MTV) represent an innovative form of public transportation, with the core feature of being able to flexibly combine and split modular units according to passenger demand. This characteristic helps optimize resource utilization, operational efficiency, and passenger comfort within public transportation systems. In recent years, with the development of intelligent transportation technologies, the MTV scheduling strategies have become a research hotspot. Therefore, this study summarizes and analyzes the current research on MTV scheduling and evaluation methods. First, the paper introduces how existing MTV scheduling studies are categorized and the content included in each category. Then, the related research on MTVscheduling is classified and organized, and the performance evaluation indicators of MTV are summarized. The classification is primarily based on the service scope of MTV scheduling in existing studies (single line service scope and line network service scope). It is then further refined according to the locations of stops where modular units can be combined or split and the characteristics of MTV operational lines (fixed/flexible single line scheduling and fixed/flexible line network scheduling). Additionally, specific MTV service modes are covered (fixed-route transit, feeder bus transit, direct bus transit, shuttle bus transit, demand-responsive transit, customized bus). At last, the paper summarizes the limitations in the research content and provides suggestions for potential future research directions: exploring passenger transfer schemes within the vehicle, MTV charging and battery swapping strategies, enriching research scenarios, focusing on MTV infrastructure development, and raising public awareness of MTV.

Select

Collaborative Lane Change Method for Autonomous Vehicles Based on Dynamic Trajectory Planning LIU Miaomiao, LIU Xiaochen, ZHU Mingyue, WEI Zeping, DENG Hui, YAO Mingkun, WU Silin, LI Ang, SHI Zan, GONG Xiaoyu Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 65-78.   DOI: 10.16097/j.cnki.1009-6744.2024.05.007 Abstract （1117）      PDF （2891KB）（693）       Traditional multi-vehicle coordination lacks effective utilization of information about target platoons and lane-changing vehicles. To address the impact of dynamic information changes on the lane-changing process, this paper proposes a collaborative lane-changing control method for autonomous vehicles based on dynamic trajectory planning. First, focusing on the scenario of a single vehicle merging into vehicle platoons in autonomous driving environments, a collaborative lane change control framework based on real-time dynamic information is proposed. Considering the cooperation between the lane-changing vehicle and the target platoon vehicles, and the impact of the lane-changing behavior on the target platoon, longitudinal collaborative control models are established for both non-lane changing and lane-changing periods. Second, after the lane-changing vehicle sends a lane-change request and satisfies the lane-change triggering conditions, a dynamic lane-change trajectory planning method using a sinusoidal curve is employed to derive a safe and reliable trajectory. Vertical coordination goals are considered. And based on the dynamic planning of longitudinal speed changes, a sine-curve-based dynamic lane change trajectory planning approach is introduced to derive safe and reliable trajectories. Then, a model predictive control-based trajectory tracking control algorithm is used to achieve real-time trajectory tracking. Finally, by constructing a joint simulation platform of Prescan and Simulink, several sets of simulation experiments under different speed conditions are designed. And traditional control algorithms based on vehicle tracking strategies are compared with the proposed control strategy by analyzing three key indicators: lane change trigger time, train stabilization time, and speed fluctuation amplitude. This comprehensive analysis validates the effectiveness and feasibility of the proposed control strategy. Simulation results show that, compared with traditional methods, the average stable time of the platoon is reduced by 34%, and the speed fluctuation amplitude of the platoon remains stable. In addition, safe and efficient lane changes can be achieved under different relative speed conditions.

Select

Path Optimization for Vertical Take-off and Landing Aircraft in Dynamic Urban Airspaces for Urban Air Mobility ZHOU Hang, ZHAO Fengyang, HU Xiaobing Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 295-308.   DOI: 10.16097/j.cnki.1009-6744.2024.05.027 Abstract （828）      PDF （4788KB）（668）       To address the current challenges of achieving optimality and computational efficiency in dynamic airspace route optimization for urban air mobility, as well as the inadequacy in addressing mixed urban and suburban operational scenarios, an innovative approach to constructing a combined urban-suburban network is initially proposed to support both urban and suburban operations seamlessly. Based on the flight dynamics model of electric vertical takeoff and landing (eVTOL) aircraft, an accurate eVTOL power consumption model is developed to optimize flight paths. A Dynamically Weighted Routing Network (RSA-DWRN) algorithm for dynamic airspace is introduced by leveraging the Ripple Spreading Algorithm. With a combined urban-suburban network framework that incorporates time-varying airflow patterns and obstacle zones, the optimization performance of the RSA-DWRN's is compared against the traditional DPO-A* algorithm across five scenarios through 600 experiments, considering path power consumption, flight time, computation time, and matching degree as key metrics. Simulation results show that RSA-DWRN algorithm performs best under the four indexes, especially as the complexity of dynamic airspace environmental factors increases. In scenarios with moving obstacles, the DPO- A* algorithm fails to predict their trajectories and requires frequent updates to the network state, significantly increasing the computational cost of path planning. In contrast, the RSA-DWRN algorithm co-evolves with changes in the dynamic environment, finally obtaining optimal solutions that simultaneously ensure optimization results and computational efficiency.

Select

Energy Saving and Emission Reduction Potential of Road Traffic in Coastal Urban Agglomerations Under Background of Carbon Peak ZHANG Lanyi , XU Yinuo, WANG Shuo, XIE Zhengyi, WENG Dawei, WANG Zhenhao, HU Xisheng, ZHENG Pingting Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 45-55.   DOI: 10.16097/j.cnki.1009-6744.2024.05.005 Abstract （530）      PDF （2617KB）（633）       In alignment with China's strategic "dual-carbon" goals, this paper aims to investigate the potential for energy saving and emission reduction in the road transportation system of coastal urban agglomerations. Taking the coastal urban agglomerations in Fujian Province as an example, a long-range energy alternatives planning system model (LEAP) has been constructed, three primary scenarios and four secondary sub-scenarios have been developed. The emission reduction potential and trend of regional road traffic were studied by adjusting the parameters of vehicle ownership and fuel economy. The study indicates that among all scenarios, the Modified Policy Scenario (MPS) demonstrates the most superior energy saving and emission reduction effects, with the greatest potential for energy conservation and emission reduction. Compared to the Business as Usual (BAU) scenario, the energy saving of the MPS is expected to be improved by 59.3% , by 2035. Under the MPS scenario, the trends in greenhouse gas and pollutant emissions both show a significant decline, with remarkable emission reduction effects. Looking specifically at the energy- saving and emission reduction potential of different vehicle types, under the MPS scenario, small- duty gasoline passenger vehicle (SGPV), heavy-duty diesel freight vehicle (HDFV), and light-duty gasoline freight vehicle (LGFV) have the greatest potential for energy conservation; carbon emissions from 8 types of vehicles can peak by 2025; and pollutant emissions can be effectively controlled, with the greatest potential for pollutant emission reduction found in HDFV. The research confirms that advancing the implementation of comprehensive policies, accelerating the phase-out of traditional fuel vehicles, and optimizing the structure of road vehicles will have a positive impact on the realization of the green and low-carbon goals. Through model simulation, it is anticipated that the road traffic system of the coastal urban agglomerations in Fujian Province will achieve significant energy-saving and emission-reduction effects before 2030.

Select

Optimization of Operation Plans for Full-length and Short-turn Routings of Urban Rail Transit Based on Flexible Train Composition LIU Bin, ZHAO Jinhui, TIAN Zhiqiang, MA Chaofan, LIANG Hui, LI Hebi Journal of Transportation Systems Engineering and Information Technology    2025, 25 (6): 143-152.   DOI: 10.16097/j.cnki.1009-6744.2025.06.013 Abstract （913）      PDF （2072KB）（632）    PDF(English version) （623KB）（184）    To address capacity redundancy or shortages caused by uneven passenger flow distribution in urban rail transit, this study optimizes train operation plan under flexible train composition during peak hours to achieve precise demand-capacity alignment, enhance cost control, and improve resource utilization efficiency. Focusing on asymmetric passenger flow patterns, this study develops a bi-objective nonlinear integer programming model with the goals of minimizing operator costs and maximizing average load factor and the constraints such as standing-passenger density limits. A hierarchical three-stage algorithm and Technique for Order Preference by Similarity to Ideal Solution are designed for solution prioritization. The model and algorithm are validated through case studies of an operational metro line. Results demonstrate that flexible train composition outperforms fixed-composition strategies (single routing and combined large/small routing). During peak hours, the operating costs decreased by 25.67% compared with the single routing method, and 7.34% compared to the combined large/small routing method. The average load factor improvements are respectively 29.55% and 26.02% compared to the single routing and combined large/small routing. Sensitivity analysis indicates that allowing a moderate increase in standing-passenger density for small routing can further reduce operational costs, though requires a balance between passenger comfort and safety. When the standing-passenger density increases from 7 to 9 persons ⋅ m -2, the flexible train composition reduces costs by 15.38%, decreases the load factor ratio 14.83%, and lower the required number of train sets by 15.79%. The flexible train composition effectively adapts to spatiotemporal passenger flow fluctuations, and could achieve synergistic optimization of dynamic capacity allocation and cost control.

Select

Intermodal Transportation Network Design Optimization Considering Demand Uncertainty Under "Dual Carbon" Background HUANG Rui, ZHAO Xu, WANG Jingyun Journal of Transportation Systems Engineering and Information Technology    2025, 25 (6): 1-12.   DOI: 10.16097/j.cnki.1009-6744.2025.06.001 Abstract （1130）      PDF （2693KB）（601）    PDF(English version) （1131KB）（14）    A central challenge in modern intermodal transportation planning is the simultaneous consideration of "Dual Carbon" goals and growing fluctuations in freight demand. To address this challenge, this study presents an optimization model for intermodal transport network design. First, a bi-level bi-objective optimization model is developed, with the strategy planner serving as the upper-level leader and shippers as the lower-level followers. The upper level jointly determines the capacity expansion investment, low-carbon investment, and subsidy policies, with the objective of maximizing total revenue while minimizing total carbon emissions. The lower layer solves the network cargo flow allocation under user equilibrium based on generalized transportation costs. Then, the theory of real options is introduced, and geometric Brownian motion is used to describe the stochastic process of transportation demand fluctuations. This enables the quantification of the option value of delayed optimization to determine the optimal timing for strategy implementation. Based on the model characteristics, a nested Frank Wolfe multi-objective evolutionary algorithm based on decomposition (MOEA/D) is designed to solve the deterministic model, combined with a least squares Monte Carlo simulation algorithm to get the optimal implementation timing. Empirical analysis along the Western Land-Sea New Corridor shows that the proposed method simultaneously balances the economic, low-carbon, and operational efficiency optimization goals, which results in a 16.58% decrease in unit transportation costs, a 27.11% decrease in total carbon emissions, and a robust 5.41% increase in total revenue. Under demand uncertainty, delaying the implementation of optimization strategies can generate additional option value. In the case study, delaying to the third period can increase expected revenue by 4.70% and reduce total carbon emissions by 5.03%.

Select

Optimization of Multimodal Transport Routes Between Northeast Asia and Europe Considering Time Uncertainty WANG Qingbin, LIANG Yinghao, ZHENG Jianfeng Journal of Transportation Systems Engineering and Information Technology    2026, 26 (2): 1-10.   DOI: 10.16097/j.cnki.1009-6744.2026.02.001 Abstract （628）      PDF （1735KB）（597）       East Asia and Europe maintain close economic and trade ties, and the rapid development of the China-Europe freight train has provided a new land-based transportation option for the two regions beyond maritime shipping. The multimodal transport network between the two regions has developed rapidly, with an increasing diversity of route options. Addressing the issues of uncertainty in transit times and railway border crossing dwell times within the East Asia-Europe multimodal transport network, this paper constructs a multi-objective path optimization model with the objectives of minimizing total cost, total time, and total carbon emissions. Trapezoidal fuzzy numbers are used to characterize the uncertainty in transit time and railway border crossing dwell time, and fuzzy opportunity constraint programming is employed to defuzzify the model. A non- dominated sorting genetic algorithm (NSGA-II) suitable for this problem is designed, and the model is validated with a container transport example from Busan to Hamburg. The results show that the optimized route schemes effectively balance cost, time, and carbon emissions. Further sensitivity analysis of sea freight rates shows that when sea freight rates rise above a specific threshold, the preference of multimodal transport operators for sea-rail intermodal transport significantly increases. Additionally, as the time confidence level increases, the optimal route shifts from sea-rail intermodal transport to all-sea transport. This study provides a reference for cross border logistics companies in addressing uncertainty in multimodal transport route decision-making.

Select

Dynamic Spatiotemporal Priority Control of Connected Vehicles Public Transport System LI Zhe, GOU Yangyang, LI Zhenyao, LI Ao, CEN Wei, GAO Jianping Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 56-64.   DOI: 10.16097/j.cnki.1009-6744.2024.05.006 Abstract （749）      PDF （2303KB）（593）       To improve the utilization efficiency of bus lanes and reduce vehicle delays at intersections of continuous bus lanes, this paper investigates dynamic spatiotemporal priority control of connected public transport systems from spatial and temporal dimensions and analyzes the applicable traffic flow conditions. In the spatial dimension, intermittent bus entrance lanes are introduced and vehicle operation control strategies are formulated for four dynamic intervals, including clearance distance. In the temporal dimension, based on deep reinforcement learning, signal timing is dynamically adjusted through time extension of the green light and time interruption of the red light. A simulation verification platform is constructed using SUMO and Python, and comparative simulation experiments and three saturation scenarios are designed for four control schemes concluding the original scheme, spatial priority scheme, temporal scheme, and spatiotemporal collaborative priority scheme. The results show that at saturation levels of 0.2, 0.5, and 0.8, the spatiotemporal collaborative priority scheme reduces the average delay compared to the original scheme by respectively 40.96% , 39.93% , and 28.20% . At low saturation, the spatial priority effect is obvious; at medium saturation, the temporal effect is obvious. Using intermittent bus entrance lanes may lead to a slight increase in bus delays, but the average delay at the entire intersection is significantly reduced. The proposed dynamic spatiotemporal priority control method for connected vehicle bus systems can effectively improve intersection traffic efficiency while ensuring bus priority.

Select

Location-inventory-routing Optimization of Maritime Logistics Network in Remote Islands Under Demand Uncertainty WU Di, HAN Xinli, SHI Shuaijie, JI Xuejun, ZHENG Jianfeng, LIU Baoli Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 268-282.   DOI: 10.16097/j.cnki.1009-6744.2024.05.025 Abstract （1079）      PDF （2962KB）（586）       To reduce the effects of uncertain material demands on the stability of maritime logistics network in remote islands, this paper investigates the design problem of a three-level hub-and-spoke material distribution network consisting of a mainland supply port, central islands, and satellite islands. The problem is formulated as a locationinventory-routing model that includes decisions on the number of central island locations, aiming to minimize system costs. The model takes into account some practical factors such as heterogeneous fleets, transportation mode diversity, and inventory capacity constraints. An Integrated Genetic-Annealing Optimization Algorithm Embedded with Monte Carlo Simulation-Based Neighborhood Traversal Operators (GAAEMCNT) is developed to decompose the original problem into several sub-problems, including location and assignment, route grouping, and optimization of route and inventory. The integrated optimization of the problem is realized through the interaction and iteration of inner and outer layer of the GAAEMCNT algorithm. Experiments on islands in the South China Sea are conducted to analyze the effects of changes in the number of islands, density distributions and demand on the maritime network system. The results show that: (i) when the distribution of material demand on islands is unchanged and the number of islands is the same, the unit cost of logistics network in the aggregation distribution is lower than that in the discrete distribution; (ii) when the distribution of island material demand is unchanged and the distribution of island is the same, the change of island number has minimum influence on the unit cost of logistics network; (iii) the change of the mean value of the material demands in the islands has a significant impact on the cost of each part of the system, and the total cost is positively correlated with the mean value; (iv) the fluctuation of the demand has a more obvious impact on the cost of the storage system, but a smaller impact on the cost of the transportation system. These findings validate the applicability of the algorithm proposed in this study across various island scenarios, providing decision-making support for the construction and optimization of maritime logistics network in remote islands under demand uncertainty.

Select

Impact of "Star-Type" High-speed Railway Network on High-quality Development of Regional Social Economy YUE Guoyong, HU Hao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 24-36.   DOI: 10.16097/j.cnki.1009-6744.2024.05.003 Abstract （737）      PDF （2915KB）（584）       This paper focuses on the first "Star-type" high-speed railway network in China and analyzes its impact on regional high-quality development from four dimensions: spatial pattern, economic development, social development and ecological environment. The study constructs a comprehensive impact evaluation model and establishes a multidimensional indicator system to evaluate the effects. It culminates in a detailed quantitative analysis of the outcomes to provide a nuanced understanding of the impacts. The result indicates that the opening of the "Star-type" high-speed railway network has significantly reduced the weighted average travel time between and within Henan province to 4.90 hours and 1.62 hours, with improvements rate of 65.6% and 37.8% . The intensity of regional connections has been significantly enhanced, gradually forming a "center-periphery" development structure which focuses on intra-provincial connections and steadily expands to the energy consumption optimization and comprehensive operational emission reduction of railway northeast and southeast. The primacy index of Zhengzhou high-speed railway hub has increased from 1.90 to 2.83, further consolidated its position as a core hub. The differencein-differences model is used to verify that the "Star-type" high-speed railway network has a positive promotion on economic and social development indicators of Henan，such as social fixed assets investment, foreign capital utilization, per capita Gross Domestic Product (GDP), urbanization rate, employment upgrading index, etc. The amount of optimized comprehensive energy consumption and comprehensive operational emission reduction in railway passenger transport has steadily increased, and industrial SO2 emissions reduced, with significant ecological environment effects.

Select

Vehicle Conflict Risk Prediction Integrating Trajectory Time Series and Behavior Correction CHEN Xiqun, ZHU Wenqi, LV Chaofeng Journal of Transportation Systems Engineering and Information Technology    2025, 25 (4): 219-229.   DOI: 10.16097/j.cnki.1009-6744.2025.04.020 Abstract （476）      PDF （2756KB）（572）       To address the abrupt changes in conflict indicators for vehicles on highways, this paper proposes a real-time prediction model for longitudinal conflict risk based on trajectory data to improve the accuracy of vehicle conflict prediction. The model adopts Time-to-Collision (TTC) as a surrogate safety measure for longitudinal conflict, through transforming a discontinuous indicator prediction into a continuous time-series prediction of speed parameters. A TTC real-time deduction module is used to output the predicted conflict risk values. A time-series Transformer is employed to achieve high-precision predictions, and an adaptive correction module is integrated to address error biases caused by the subjective behaviors of drivers during conflict situations. When the current conflict indicator reaches the threshold, a short-term acceleration fitting is activated to correct the predicted values of transformer using the fitted acceleration. The effectiveness of model is validated on real-world vehicle trajectory data. The results show that the proposed model outperforms benchmark models in performance metrics. Compared with the baseline Transformer model, the Adaptive Risk Adjustment Transformer model (ARA-Transformer), which incorporates an adaptive bias correction module, reduces MSE by 48.33%, RMSE by 21.33%, and MAE by 24.10% under conflict conditions. Additionally, the proposed model demonstrates generalizability across different driver trajectories by providing an effective method for conflict warning and improving system risk intervention responsiveness in assisted driving scenarios.

Select

Energy-efficient Train Timetable Optimization Model for Urban Rail Transit Line with Asymmetric Passenger Demand SUN Yuanguang, DENG Chengyuan, PENG Lei, CHEN Hongbing, LI Zongran, BAI Yun Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 128-139.   DOI: 10.16097/j.cnki.1009-6744.2024.05.012 Abstract （998）      PDF （2500KB）（559）       To relieve the asymmetric phenomenon of urban rail transit line, such as the stranding of passengers in the heavy-demand direction, the wastage of capacity and high energy consumption in the low-demand direction, this paper proposes an asymmetric transportation strategy combining skip-stop tactics and flexible train composition technology. In this strategy, more train services will be arranged in the heavy-demand direction of the transit line, and the service frequencies will be reduced in the low-demand direction. The flexible train composition technology is also utilized to improve the flexibility of capacity supply and reduce energy consumption waste. In addition, several express trains are operated in the low- demand direction to accelerate the turnover speed of rolling stocks. Based on this, an integrated optimization model of operation plan, train timetable and rolling stock circulation plan were constructed to determine the bidirectional service frequency, train composition, stopping plan, timetable and circulation plan of rolling stocks, to minimize the total passenger travel time and total traction energy cost of the entire corridor. A customized variable neighborhood search algorithm is designed to solve the mixed integer nonlinear programming model. The case study in Guangzhou Metro Line 14 showed that: compared with the actual symmetric transportation strategy, the proposed method can reduce the total passenger travel time by 6.52 %, the total traction energy consumption by 34.20 %, and the total objective function by 11.40 %. Express trains can accelerate the turnover speed of the rolling stocks, reducing six on-line rolling stocks, which can facilitate the asymmetric strategy. Flexible train composition technology can further improve the flexibility of the capacity supply, and significantly reduce the number of on-line rolling stocks, where the average load factor of trains is increased by approximately 20%, and the optimization rate of the total traction energy consumption is increased by approximately 33%. The asymmetric strategy combined with skip-stop trains and flexible train composition can save train operating costs, and greatly improve the capacity matching degree under the asymmetric passenger demand.

Select

Automatic Driving Risk Prediction Model Based on Improved Vision Algorithm ZHAO Hongzhuan, ZHANG Jikang, PAN Jiawen, YUAN Quan, XU Enyong, WEI Jinzhan, ZHOU Dan, LIU Chengkun Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 79-90.   DOI: 10.16097/j.cnki.1009-6744.2024.05.008 Abstract （747）      PDF （3045KB）（557）       In order to deal with the problem of traditional vehicles cutting too close to each other resulting in disengagement of automatic driving, this paper proposes an automatic driving risk prediction model with improved YOLOV7-Tiny and SS-LSTM. The model improves the visual target detection model YOLOV7-Tiny(You Only Look Once Version 7 Tiny), adds a small target detection layer, introduces the SimAM (A Simple, Parameter-Free Attention Module for Convolutional Neural Networks) attention mechanism module, optimizes the training loss function, and performs trajectory tracking and prediction of its target vehicle. The short-term prediction of Strong SORT (Strong Simple Online and Realtime Tracking) is utilized to continuously correct the long-term prediction of LSTM (Long Short Term Memory) to establish the SS-LSTM model. And the predicted overtaking trajectory is fitted with the trajectory of the intelligent networked vehicle itself at the same time latitude, so as to obtain the risk prediction model when the traditional vehicle cuts in. The experimental results show that the automatic driving risk prediction method in this paper effectively predicts the risk of traditional vehicles when cutting in, and the simulation experiments show that the improved YOLOV7-Tiny improves the prediction accuracy by 2.3% compared with the original algorithm mAP (mean Average Precision). The FPS (Frames Per Second) is 61.35 Hz. The model size is 12.6 MB, and the model meets the lightweight demand of the vehicle end. The real-vehicle experiments show that the accuracy of risk prediction based on the SS-LSTM model is 90.3%.

Select

Cross-line Train Service Plan Optimization in Urban Rail Transit Network JIAN Min, CHEN Shaokuan, WANG Zhuo, LI Hao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 116-127.   DOI: 10.16097/j.cnki.1009-6744.2024.05.011 Abstract （698）      PDF （3725KB）（556）       In order to improve the service quality of urban rail transit by reducing transfer times, a method for generating cross-line train routes and an optimization model for planning train routes with cross-line operation are proposed based on the characteristics of passenger flow in the network. First, with the developed inference method of passenger travel routes, the various passenger flows and proportions in the network are calculated to obtain the crossline times, thereby generating the set of alternative long cross-line train routes. Then, with the goal of minimizing passenger transfer times, an optimization model for the operation of long cross-line train routes in the network is constructed, which satisfies the constraints of basic operating conditions and cross-line capacity. An improved genetic algorithm with a frequency-based passenger flow assignment method is used to solve the problem to obtain the operating frequency of the mainline and cross-line train routes in the network. Finally, the effect of long cross-line train routes is analyzed based on an urban rail network. The results show that the optimized train service plan reduces the transfer times of all transfer passengers by 2.02% to 5.97% . Thus, the passenger transfer time and network transfer coefficient are reduced, and the direct passenger flow is increased by 1.58% to 4.58% with the operated long cross-line train routes. The operated long cross-line train routes play the role of short train routes in the connected line to supplement the sectional transportation capacity, thus reducing the total number of running trains on the line and the train kilometers on the main line. In addition, when the transfer passenger volume at the transfer station is high, the cross-line train route cannot be operated due to the high operating frequency of the main-line train on the connected line, and the effect of improving the operational services gradually decreases as the operating frequency of the crossline train route reaches the upper limit of the cross-line capacity

Select

Optimization of Bus Unit Dynamic Formation Plan in Modular Public Transport System YUE Hao, DONG Xianlong, WANG Li, QU Qiushi, ZHANG Xu Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 160-172.   DOI: 10.16097/j.cnki.1009-6744.2024.05.015 Abstract （593）      PDF （2005KB）（549）       This paper investigates the optimization of dynamic formation plan for bus unit road operation based on modular public transport system. A two-stage joint optimization model for the direction assignment and formation permutation of platoon was proposed. In the first stage, an integer linear programming model was developed with the objective of minimizing the number of passengers in-motion transfer. The model enables the direction assignment of bus units and the calculation of replenishment bus units. Based on this, a second-stage bi-objective optimization mixed integer nonlinear programming model was constructed, with the objectives of minimizing formation permutation time and in-motion transfer time, to optimize the efficiency of dynamic formation of bus units. Furthermore, the algorithms was designed to solve the proposed models. The CPLEX solver was used to solve the first-stage direction assignment model and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm was used to solve the second-stage formation permutation model. At last, the study verified the effectiveness of the proposed model and its solution algorithms. It also included an analysis of the optimization of bus unit formation efficiency and change in bus occupancy rate in a modular public transport system under different passenger demands and bus unit capacities. The results indicate that within a certain increase in modular bus unit capacity, the formation efficiency of modular bus units improves with the increase in bus unit capacity. When the increase in bus unit capacity is too big, the dynamic formation efficiency cannot be improved effectively, and the bus occupancy rate will be reduced, which would lead to overcapacity of modular bus platoon.