Bulletin Board
Highlights
Low-altitude trajectory planning for aircraft considering RAIM availability undercomplex terrain conditions, TANG Xinmin, et al.
2025-08-12 TopAnalysis of low altitude flyable airspace in major cities in china, JIN Sheng, et al.
2025-07-29 TopLand-air integrated transportation: research opportunities for the low-altitudeeconomy from the perspective of road transportation, TANG Li.
more..Cross-cultural analysis of microlevel driving-behavior characteristics between China and America
BAI Congcong;CHEN Mengdi;RONG Donglei;GAO Xi;JIN Sheng;[Background] Driving behavior is not only a reflection of individual characteristics but is also determined significantly by regional culture, traffic environment, and social habits, which collectively shape driving cultures. Comprehensive investigations into these cultural differences in driving behavior can provide support for cross-cultural applications of autonomous driving. However, existing studies are limited to a single country or local indicators and don't adequately perform systematic comparisons of driving-behavior characteristics under different cultural backgrounds. [Objective]This study aims to systematically reveal the differences in micro-driving behavior characteristics between Chinese and American drivers in terms of safety, efficiency, and comfort, thus providing a basis for developing culturally adaptive optimization strategies for autonomous driving. [Methods]Based on the framework of “data preprocessing-macro-traffic-state matching-three-dimensional indicator system construction-micro-driving-behavior comparison”, six indicators are extracted from the safety, efficiency, and comfort aspects to systematically compare and quantitatively analyze the micro-driving behaviors of Chinese and American drivers. [Data] An empirical analysis is conducted by integrating the Citysim dataset from China and the Next Generation Simulation(NGSIM) highway vehicle trajectory dataset from the United States, totaling more than 28 000 vehicle trajectories.[Conclusions] Significant differences in micro-driving behavior between China and the United States are observed in terms of safety, efficiency, and comfort. Under the same traffic conditions, Chinese drivers exhibit higher safety, with their risk exposure time being 105.3% higher in the United States than in China, while the intensity of risk exposure increased by 95.0%. Chinese drivers demonstrate higher driving efficiency, and their relative desired velocity deviation is 3.2%～7.8% lower than that of American drivers, thus indicating a greater tendency to drive at the desired speed. Meanwhile,their average time headway is 8.48%～35.48% lower, thus enabling a more effective use of road resources. Furthermore, Chinese drivers exhibit significantly higher driving comfort, with their average absolute jerk being 19.72%～50.68% lower, as well as a lower frequency of acceleration and deceleration events, thus reflecting smoother driving behavior. [Application] This study reveals the cultural differences in micro-driving behaviors between the East and West. The proposed framework for quantifying these cultural differences is paramount for the localization optimization and global deployment of autonomous driving algorithms.
Individual-level metro route extraction and travel behavior pattern mining
LIU Xiaolei;ZOU Guojian;DUAN Zhengyu;LAI Fengbo;CHEN Zhuoqi;LI Zhenming;LI Weifeng;[Background]With the large-scale construction and increasingly integrated operation of metro networks, metro ridership has grown rapidly. Passenger travel demands and patterns have become increasingly complex and diverse, presenting new challenges for metro operations and management. [Objective] Leveraging the advantages of mobile signaling data in continuously tracking users' travel trajectories, metro travel episodes are identified on the basis of the layout and coverage of base stations within metro stations, combined with thresholds like travel activity time. Next, typical metro travel patterns are mined to support metro optimization. [Method] Based on the metro network topology model and Dijkstra algorithm, passenger travel paths are reconstructed to obtain detailed daily travel records. A two-step classification method is then employed to uncover the heterogeneity of passenger travel behavior. Specifically, the users are divided into high-and low-frequency groups on the basis of their travel frequencies. Subsequently, using indicators such as temporal regularity, spatial distribution, and route utilization, the K-means++ clustering algorithm is employed to further refine the segmentation of each group. [Data] The study uses mobile signaling data from Shanghai in May 2019, which include 400 million signaling records generated by 4.48 million metro users. [Conclusions] The analysis extracts 30.09 million metro trips from 3.83 million users. Highfrequency users(18% of the total) contributed 67% of all trips, whereas low-frequency users(82%)accounted for only 33%. High-frequency users can be classified into three groups: commuters relying on a single route, commuters with flexible route choices, and regular users traveling for noncommuting purposes. Low-frequency users can be classified into three categories: business, leisure and entertainment, and single-day or transit travelers. The findings can inform resource allocation, targeted marketing strategies, and help improve operational efficiency in metro systems.
Metro feeder-trip identification and service-area analysis using ridesourcing data
MENG Yu;LU Hao;XIE Ruiyuan;YU Weijie;MA Xinwei;[Background] Despite the continuous expansion of urban rail networks, service coverage gaps persist in urban transportation systems. Because of its flexibility and efficiency, ridesourcing has become a key mode for bridging the first-and last-mile segments of metro travel. [Objective] To accurately identify ridesourcing-metro integration trips and delineate their service areas, thereby providing a foundation for improving transfer efficiency and optimizing platform resources. [Method]Metro-integrated ridesourcing trips were accurately identified by matching detailed origin and destination addresses. On this basis, service areas were constructed using point aggregation and hierarchical clustering algorithms to examine their effectiveness in delineating the spatial service coverage of metro systems. [Data] The ridesourcing trip dataset from Tianjin, which contains detailed origin and destination address information, provides a reliable basis for accurately identifying metro-integrated trips and conducting empirical analysis. [Result] Hierarchical clustering demonstrates superior accuracy in delineating the spatial service areas of ridesourcing-metro integration, particularly for complex spatial patterns. Its adaptability to heterogeneous regional demands enables the construction of buffer zones that more closely reflect actual travel distributions. [Conclusion] Metro stations in central areas primarily serve short-distance feeder trips and are characterized by larger buffer areas but lower trip densities. In contrast, suburban stations tend to support longer-distance trips, with smaller buffer zones yet higher trip densities. The results suggest that differentiated transfer management strategies are required for urban centers and suburban areas. Optimizing the layout and dispatching of transfer points based on service-area characteristics can enhance the transfer efficiency and service quality of the public transportation systems.
Road-network-constrained individual trajectory reconstruction via dynamic velocity modeling
YAO Yao;JIANG Yinghong;ZOU Guojian;LI Ye;[Background] The rapid advancement in the Internet of Things(IoT) and smart-device technologies has enabled the monitoring of individual mobility trajectories. However, inherent positioning errors in GPS and other location-tracking devices often result in recorded points that deviate from their true locations, particularly in dense urban road networks, making it challenging to accurately reconstruct actual travel paths. [Objective] This study proposes an individual-level trajectoryreconstruction method based on dynamic velocity simulation and map matching to continuously map discrete global positioning system(GPS) trajectories in urban road networks. The goal is to generate long-term high-precision continuous-movement trajectories of vehicles or individuals that adhere to road-network constraints. [Method] The proposed method integrates shortest-path search, dynamic velocity modeling, and time-driven interpolation, thereby establishing a four-stage reconstruction mechanism comprising spatial mapping, path planning, stochastic speed sampling, and temporal interpolation. [Data] Using mobile signaling data from 50 000 users in Shanghai, coupled with roadnetwork topology data, the algorithm successfully generated highly refined trajectories that adhered to road-network constraints. [Conclusion] Compared with the three mainstream methods,(HMM-Reconstruct, Map-Matching Plus and GAT-Traj), the proposed approach reduced the average trajectory error by 33.3%, 21.1%, and 12.5%, respectively, demonstrating superior precision in trajectory reconstruction. The reconstructed trajectories accurately captured spatiotemporal traffic patterns, including rush-hour flow dynamics and polycentric mobility radiation. A cross-city validation(Beijing and Xiamen) confirmed the transferability of this approach, demonstrating its potential for traffic-flow prediction, OD analysis, and smart-city applications.
Transfer learning method for subway passenger flow prediction with emphasis on fluctuation similarities
HUANG Jia;ZHAO Ling;[Background] The continued expansion and optimization of urban rail transit networks has led to a marked growth in the number of metro stations has increased substantially. This growth demands the development of individualized passenger flow prediction models for hundreds of stations, each with distinct ridership patterns. Conventional station-by-station training methods are timeconsuming and fail to meet the stringent temporal efficiency requirements of contemporary transit management systems. [Objective] To address this issue, we explored transfer learning techniques for passenger flow prediction models, training them exclusively on select prototype stations. Subsequently, the learned parameters are transferred to the remaining stations through transfer learning, enhancing the prediction efficiency throughout the network. [Method] We propose a transfer learning-based prediction model that considers similarities in passenger flow fluctuation characteristics. By extracting each station's passenger flow fluctuation characteristics, we compute similarity scores with other stations and assign each to the most similar station as its transfer learning target, achieving a “one station, one solution” strategy. This method requires extensive prediction model training for only a few stations while allowing others to leverage transfer learning. [Data] For analysis, the Chengdu Metro served as a case study, utilizing passenger flow data of selected stations on Lines 1, 2, 3, and 4 from June to August 2022. [Conclusion] We evaluated four deep-learning passenger flow prediction models. Transfer learning reduced training time by an average of 62.68%, with some stations experiencing over 80% reduction. Despite the decrease in training duration, prediction accuracy slightly improved across all models, confirming the efficacy of this method.
Journal Information
Founded in 2003, Bimonthly
Competent Authority：Ministry of Education of PRC
Sponsor：Southwest Jiaotong University
Editor in Chief： LIU Xiaobo; HE Zhengbing
E-mail：jtt@swjtu.edu.cn
ISSN ：1672-4747
CN ：51-1652/U
Impact Factor: 3.245
Category Ranking: 7/169
Quartile: Q1
Indexed
CSTPCD
Scopus
RCCSE
JST
CSTJ
CNKI
COJ
Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Peer ReviewCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Office WorkOnline Review
Online Communication with the Editorial Department