检索结果-内蒙古大学图书馆

How Do Age Compositions Affect Pedestrian Dynamics on Stairways? Findings from laboratory Experiments

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Shi, Dongdong Liu, Jiahui Ma, Jian Lovreglio, Ruggiero Wang, Qiao Chen, Juan School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu610031 China School of Built Environment MasseyUniversity Auckland0632 New Zealand Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University Chengdu610031 China

Understanding pedestrian dynamics for different age compositions is paramount for enhancing their safety level on stairways in normal and evacuation conditions. In this study, we illustrate the findings of a series of single-file pedestrian flow experiments on stairways. This experiment was carried out with 131 participants having different age compositions, including preschool students (4-5 years), primary school students (8-10 years), middle school students (12-14 years), middle-aged pedestrians (27-57 years), and the elderly pedestrians (63-81 years). We collect data using three experimental settings: individual experiments, single-file pedestrian experiments with age homogeneity, and single-file pedestrian experiments with age-mixed heterogeneity. Our findings show that age plays a substantive non-linear impact on individual unconstrained ascending and descending speeds. In addition, we developed a linear regression model that predicts the pedestrians’ free speed of different ages on stairways. Then, the effects of age compositions on pedestrian dynamics with fundamental diagrams (i.e., speed-density and specific flow-density relations) are analyzed, and the maximum specific flow of age homogeneity is higher than that of age-mixed heterogeneity crowds. Finally, we illustrate how the headway distance impacts participants’ ascending and descending speeds in both homogeneity and heterogeneous age conditions. As such, these new experimental results can provide the foundation for future calibration and validation of pedestrian evacuation models as well as insight into safety guidelines. © 2024, The Authors. All rights reserved.

关键词： Dynamics

Research on equipment state correlation analysis based on digital model of high-speed railway public works equipment 1

学校读者我要写书评

暂无评论

Research on equipment state correlation analysis based on di...

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Wu, Yanhua Li, Ping Cheng, Zhibo Xu, Wenya Jin, Chenkun Dong, Hairong China Academy of Railway Sciences Corporation Limited National Engineering Laboratory of Comprehensive Transportation Big Data Application Technology Beijing China China Academy of Railway Sciences Corporation Limited Beijing China Beijing Jiaotong University Beijing China

ISBN: (纸本)9781665433372

One of the key factors in the safe operation of high-speed railways is the operational status of public works equipment. Constructing the digital model of public works equipment, fusing basic attribute information with detection and monitoring status information, and characterizing the current operating status of public works equipment, will provide more intuitive support for the change law of state change analysis. The correlation analysis between TQI and settlement based on digital model will provide auxiliary decision support for equipment maintenance. © 2021 IEEE.

关键词： Railroads

A Surrogate-Assist Quasi-Affine Transformation Evolutionary for Multi-Objective Optimization of Empty Train Deployment on Heavy-Haul Railways

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Du, Zhi-Gang Pan, Jeng-Shyang Xu, He-Ying Chu, Shu-Chuan Ni, Shao-Quan School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu610031 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031 China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031 China

In recent years, surrogate-assisted evolutionary algorithms have become increasingly popular for solving expensive and time-consuming single-objective and multi-objective problems. However, in multi-objective optimization, the Pareto non-dominated solution set space can quickly become computationally intractable, making it challenging to select which samples to evaluate using the expensive fitness function. In this paper, we propose a novel surrogate-assist QUasi-Affine TRansformation Evolutionary algorithm (SA-QUATRE/MO) for solving multi-objective optimization problems. The SA-QUATRE/MO algorithm uses a radial basis neural network as a surrogate model to improve the speed of the algorithm operation by replacing the expensive fitness evaluation with the surrogate model. To ensure the excellence and diversity of the selected samples while keeping the archived sample space fixed, we propose a technique called Vector Space Sampling, which samples objective points in the current set of non-dominated solutions by dividing several sub-vector spaces. Additionally, we propose an uncertain sample infilling strategy to select samples for real fitness evaluation using a designed uncertainty function. We compare the SA-QUATRE/MO algorithm with three state-of-the-art algorithms for multi-objective problems in the DTLZ, MaF, and ZDT test function suites. Finally, we apply the SA-QUATRE/MO algorithm to solve the optimization problem of the empty train deployment at the loading end of a heavy-haul railway. We build a model based on the S12 section of a certain railway and optimize it using the SA-QUATRE/MO algorithm, demonstrating the effectiveness and practicality of our proposed approach. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

The impact of selfish driving behavior of autonomous vehicles on mixed traffic flow

学校读者我要写书评

暂无评论

Physica A: Statistical Mechanics and its applications 2025年 672卷

作者： Wu, Yunxia Li, Le Jiang, Chenming Jiang, Yangsheng Yao, Zhihong National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Chengdu611756 China School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu610031 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Chengdu611756 China China Institute of FTZ Supply Chain Shanghai Maritime University Shanghai201306 China

With the development of automatic control and artificial intelligence technology, autonomous vehicles (AVs) are becoming more and more intelligent. However, this individual intelligence means that the driving behavior of AVs can be more aggressive and selfish. To investigate the impact of the selfish driving behavior of AVs on the characteristics of mixed traffic flow, this paper proposes a cellular automata model that considers the selfish driving behavior of AVs. First, we analyze the vehicle types‌ in the current mixed traffic flow and develop a universal safety distance model. Then, based on this, a cellular automata model is proposed. This model can not only describe the longitudinal car-following and lateral lane-changing behavior of human-driven vehicles and AVs, but also characterize the selfish degree in the driving behavior of AVs. Finally, simulation experiments are designed to analyze the impact of the selfish driving behavior of AVs on the performance indicators of mixed traffic flow. The results show that: (1) The increase in the penetration rate of AVs has a positive effect on the average velocity, traffic stability, and throughput of mixed traffic flow;(2) On the whole, the selfish lane-changing behavior of AVs has a relatively small impact on the average velocity of mixed traffic flow. The impact becomes smaller with the increase in traffic density. (3) In most scenarios, the selfish car-following behavior of AVs has an improving effect on the average velocity and throughput of mixed traffic flow. In summary, the relevant research results can provide theoretical support for the design of micro-behavioral control schemes for AVs. © 2025 Elsevier B.V.

关键词： Behavioral research

AdvMap: Crafting Adversarial Maps to Counter AI Aimbot in First-Person Shooter Games

学校读者我要写书评

暂无评论

IEEE Transactions on Games 2025年

作者： Yan, Kai Chen, Xianyi Cui, Qi Yuan, Haoqin Tan, Zhenshan Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education the School of Computer Science Nanjing210044 China Beijing Jiaotong University Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing100044 China

AI-based automatic aiming cheats (a.k.a., AI aimbots) have proliferated in first-person shooter (FPS) games, which grant malicious users an unfair gameplay advantage. Since AI aimbots operate independently of game data and are developed using object detection algorithms, they are difficult to detect with traditional anti-cheating methods. To actively counter AI aimbots, we propose AdvMap, which introduces invisible adversarial perturbations into game scene elements. In optimizing these adversarial perturbations, we design a mixture-of-misleading loss function that increases the total target confidence score within each misleading bounding box. It mitigates the risk of segment missing even when AdvMap is obscured, thereby enhancing the robustness. Besides, an L1-norm constraint with a small scale is employed during each update of the adversarial perturbations, which preserves the fidelity of the game scene. Additionally, to enable effective adaptation to interact with various elements within game environments, we introduce an Image-Subspace-Based Multi-Directional (ISMD) optimization strategy. It enables the adversarial perturbations to adaptively fit into each element by leveraging the mapping relationship between the game's 3D scenes and its corresponding 2D images. Furthermore, we construct a comprehensive benchmark, which includes various FPS games with different graphics styles and perspectives. Extensive experimental results demonstrate the efficacy of our method in countering various AI aimbot tools on different state-of-the-art object detection methods. © 2021 IEEE.

关键词： Adversarial machine learning

Do Electric Vehicles Lead to More Severe Crashes? A Doubly Robust-Based Causal Inference Approach

学校读者我要写书评

暂无评论

SSRN 2025年

作者： Zhai, Guocong Xie, Kun Yang, Di Yang, Hong School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China Department of Civil & Environmental Engineering Old Dominion University NorfolkVA23529 United States Department of Transportation & Urban Infrastructure Studies Morgan State University BaltimoreMD21251 United States Department of Electrical & Computer Engineering Old Dominion University NorfolkVA23529 United States Singapore

Electric vehicles (EVs) possess distinct physical characteristics compared to conventional vehicles, including greater mass, larger torque, higher acceleration rates, and a lower center of gravity. However, the safety implications of these differences remain underexplored in existing literature. This study examines the relationship between vehicle type and crash injury severity by employing a rigorous causal inference framework. We analyzed seven years of police-reported crash data (2017-2023) from Virginia, USA, treating EV crashes as the treatment group and conventional vehicle crashes as the control group. To address potential confounding issues in this high-dimensional covariate space, we implement a doubly robust estimator that integrates Bayesian Additive Regression Trees for matching-based estimation (inverse probability of treatment weighting) with logistic regression for outcome modeling. This approach provides reliable causal estimates even if one component is incorrectly specified. Our findings reveal that EV crashes are associated with a 14% reduction in the odds of severe injury compared to conventional vehicle crashes, with consistent estimates across methodological approaches. This study advances knowledge on EV safety and contributes methodologically by developing a doubly robust framework for binary safety outcomes through log-transformed causal odds ratios. From a practical perspective, our findings can guide transportation agencies in developing EV-related regulations, inform insurance providers in designing premium structures for EVs, and help consumers make informed choices on EV adoptions. © 2025, The Authors. All rights reserved.

关键词： Vehicle safety

Industrial Region Planning and Urban transportation Planning Based on Industry-City Integration 6

学校读者我要写书评

暂无评论

Industrial Region Planning and Urban Transportation Planning...

6th International Conference on transportation Information and Safety, ICTIS 2021

作者： Zheng, Shuai Liu, Yugang Zhang, Jia Wan, Qing Zhang, Heyang Ye, Jinsong Southwest Jiaotong University School of Transportation and Logistics Southwest Jiaotong University National United Engineering Laboratory of Integrated Intelligent TransPortation Chengdu China Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport China Academy of Transportation Sciences Beijing100029 China

ISBN: (纸本)9781665497138

With urban expansion and economic development, traditional industrial parks with single function cannot adapt to the pace of urban development. As a new type of industrial park, the industry-city integration has gradually become the development direction. There is no tailor-made quantitative planning scheme at this stage. Aiming at filling the gap, this research does the following work to provide quantitative guidance strategy for industrial park planning. This paper first analyzes the Transit-oriented development (TOD) model requirements of new industrial parks, and makes a detailed analysis of the interaction between land use and transportation. Secondly, based on the relationship between land use and transportation, a combined feedback model of the land planning model and the public transportation utility allocation model is established. The process of modeling is to plan the smallest land unit according to the principle of land use function combination and land use type to meet the needs of residents. The other is to plan public transportation with optimal road load according to the principle of public transportation guiding travel and maximizing travel efficiency. Notedly, this paper uses the TOPSIS method to normalize the planning score through the feedback relationship between land use planning and public transportation planning. Based the analysis, the genetic algorithm is used to optimize the planning score and obtain the best plan which provides quantitative guidance strategies for the industrial park planning. Finally, this paper selects the 'Blank Land' of Suzhou Industrial Parks for case analysis, and the best standardized score after planning is about 87 points. In order to further analyze the planning effect and the relationship between the planned area and the rest of the land, ArcGIS is used to carry out demand analysis and land use radiation range analysis of the planning scheme. The results show that the travel demand after planning matches with t

关键词： Land use

A-Map: Interactive Visual Exploration of Intercity Accessibility Dynamics Based on Railway Network data

学校读者我要写书评

暂无评论

A-Map: Interactive Visual Exploration of Intercity Accessibi...

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Kaichen Nie Hanning Shao Yuchu Luo Min Tian Hao Wu Wei Zeng Xin Fu Xiaoru Yuan Key Laboratory of Machine Perception (Ministry of Education) School of AI Peking University Hong Kong University of Science and Technology Guangzhou Chang’an University National Engineering Laboratory for Big Data Analysis and Application Peking University

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Railway transportation is closely linked to everyday lives while also aiding domain experts in analyzing national or regional development. However, discrepancies between travel time reduced by railways and actual distance pose challenges in visualizing the accessibility. Existing methods either struggle to simultaneously depict the accessibility relationships among all cities or disregard genuine geographical positions, leading to spatial cognitive confusion. In this work, we propose a novel approach to balance between the geographical positions and travel time between cities. We construct linear cartograms to represent accessibility while preserving better local railway network structures compared with existing methods. We further propose the A-Map system, enabling users to interactively explore the extensive development of China’s railway system over decades. We validate the effectiveness of our proposed layout algorithm from qualitative metric evaluation and illustrate the applicability of our system with results.

关键词： Measurement Visualization Heuristic algorithms Urban areas Layout transportation data visualization

Characteristics of Pedestrian Dynamics in Narrow Aisles: Empirical Results

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Fu, Zhijian Feng, Yujing Xiong, Xingwen Yang, Yunjia Luo, Lin Li, Jian School of Transportation and Logistics Southwest Jiaotong University PRC Chengdu611756 China National Engineering Laboratory for Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China China Academy of Safety Science and Technology Beijing100012 China

As an essential problem in non-equilibrium physics, the characteristics of pedestrian dynamics in narrow aisles have not been fully uncovered. Thus, in this study, we performed experiments with participants passing through narrow aisles with various widths under open boundaries. There is a transition from lateral to forward movement with the increase of aisle width, and the critical width is 0.30m, the average hip width of Chinese adults. Transforming from the lateral to forward movement, we observed that the deviation angles, step behaviors, and individual speed represent various features. With the aisle width rising from 0.20m to 0.30m, the jam relieves significantly. However, with the aisle width increasing from 0.30m to 0.35m, the flow efficiency improves little. This study contributes empirical results on movement in narrow aisles to pedestrian dynamics and provides basic inputs for pedestrian models and insights into the design of pedestrian facilities. © 2023, The Authors. All rights reserved.

关键词： Efficiency