检索结果-内蒙古大学图书馆

Game Theoretic application to Intersection Management: A Literature Review

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Qin, Ziye Ji, Ang Sun, Zhanbo Wu, Guoyuan Hao, Peng Liao, Xishun The School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu611756 China The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Sichuan Chengdu611756 China The College of Engineering Center for Environmental Research and Technology University of California at Riverside RiversideCA92507 United States The University of California at Los Angeles Los AngelesCA90095 United States

The emergence of vehicle-to-everything (V2X) technology offers new insights into intersection management. This, however, has also presented new challenges, such as the need to understand and model the interactions of traffic participants, including their competition and cooperation behaviors. Game theory has been widely adopted to study rationally selfish or cooperative behaviors during interactions and has been applied to advanced intersection management. In this paper, we review the application of game theory to intersection management and sort out relevant studies under various levels of intelligence and connectivity. First, the problem of urban intersection management and its challenges are briefly introduced. The basic elements of game theory specifically for intersection applications are then summarized. Next, we present the game-theoretic models and solutions that have been applied to intersection management. Finally, the limitations and potential opportunities for subsequent studies within the game-theoretic application to intersection management are discussed. Copyright © 2023, The Authors. All rights reserved.

关键词： Game theory

Encoding Global Semantic and Localized Geographic Spatial-Temporal Relations for Traffic Accident Risk Prediction

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Alhaek, Fares Li, Tianrui Rajeh, Taha M. Javed, Muhammad Hafeez Liang, Weichao School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China

The proliferation of vehicles and the intricate layout of road systems have contributed to a significant rise in traffic accidents, posing a pressing concern globally. Despite the advancements facilitated by deep learning, several challenges persist in the domain of traffic accident prediction. Firstly, the sparsity of accident data in certain city regions presents a significant obstacle, particularly when attempting fine-grained predictions at a local level. Secondly, the intricate spatial-temporal relations inherent in traffic accident data pose a challenge for existing prediction models. In response to these formidable challenges, this paper presents GLST-TARP, a novel model for predicting traffic accident risk in urban environments by leveraging both global semantic and localized geographic spatial-temporal relations. Specifically, we construct multi-graphs to encode global static and dynamic spatial relations, incorporating attention mechanisms to adaptively focus on relevant information and temporal relations. Additionally, we employ channel-wise convolutional neural network blocks to extract localized geographic features and enhance predictive accuracy. The proposed model is trained using a Huber loss function tailored for regression tasks, relieving the impact of zero values during optimization. Experimental results demonstrate that GLST-TARP outperforms state-of-the-art methods in predicting traffic accident risks, showcasing its potential for enhancing urban safety and transportation management. © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

A performance evaluation of correspondence grouping methods for 3D rigid data matching

学校读者我要写书评

暂无评论

arXiv

arXiv 2019年

作者： Yang, Jiaqi Xian, Ke Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710129 China National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations. To fill this gap, this paper gives a comprehensive evaluation of nine state-of-the-art 3D correspondence grouping methods. A good correspondence grouping algorithm is expected to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall as well as facilitating accurate transformation estimation. Toward this rule, we deploy experiments on three benchmarks with different application contexts including shape retrieval, 3D object recognition, and point cloud registration together with various perturbations such as noise, point density variation, clutter, occlusion, partial overlap, different scales of initial correspondences, and different combinations of keypoint detectors and descriptors. The rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation. Based on the outcomes, we give a summary of the traits, merits, and demerits of evaluated approaches and indicate some potential future research directions. Copyright © 2019, The Authors. All rights reserved.

关键词： Benchmarking

USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Li, Xiaofan Peng, Bo Hu, Jie Ma, Changyou Yang, Daipeng Xie, Zhuyang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Data Recovery Key Laboratory of Sichuan Province Neijiang Normal University Sichuan Neijiang641100 China

Unsupervised skin lesion segmentation offers several benefits, such as conserving expert human resources, reducing discrepancies caused by subjective human labeling, and adapting to novel environments. However, segmenting dermoscopic images without manual labeling guidance is a challenging task due to image artifacts such as hair noise, blister noise, and subtle edge differences. In this paper, we introduce an innovative Uncertainty Self-Learning Network (USL-Net) to eliminate the need for manual labeling guidance for the segmentation. Initially, features are extracted using contrastive learning, followed by the generation of Class Activation Maps (CAMs) as saliency maps. High-saliency regions in the map serve as pseudo-labels for lesion regions while low-saliency regions represent the background. Besides, intermediate regions can be hard to classify, often due to their proximity to lesion edges or interference from hair or blisters. Rather than risking potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, they are taken as uncertainty regions by exempted from pseudo-labeling and allowing the network to self-learning. Further, we employ connectivity detection and centrality detection to refine foreground pseudo-labels and reduce noise-induced errors. The performance is further enhanced by the iterated refinement process. The experimental validation on ISIC-2017, ISIC-2018, and PH2 datasets demonstrates that its performance is comparable to supervised methods, and exceeds that of other existing unsupervised methods. On the typical ISIC-2017 dataset, our method outperforms state-of-the-art unsupervised methods by 1.7% in accuracy, 6.6% in Dice coefficient, 4.0% in Jaccard index, and 10.6% in sensitivity. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

Modeling Individuals' Largest Daily Trip Displacement using Extreme Value Theory

学校读者我要写书评

暂无评论

Modeling Individuals' Largest Daily Trip Displacement using ...

International Conference on Intelligent transportation

作者： Kaiqiang Xie Lu Ma Hui Xiong Shasha Wu Shenzhen Urban Transport Planning Center Transport Information & Model Institute Shenzhen China MOT Key Lab of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing China School of Mechanical Engineering Beijing Institute of Technology Beijing China Department of Transportation Planning and Management Henan College of Transportation Zhengzhou China

ISBN: (纸本)9781538670255

As a significant factor in urban planning and traffic forecasting, human mobility draws intensive attentions in recent years with the emergence of geo-related data. In this paper, we build models for human mobility with regards to individuals' largest daily displacement using Extreme Value Theory (EVT) based on nearly 40 million individuals' trajectories. It is found that the largest daily displacement can be well fitted by the Generalized Pareto Distribution (GPD) and is not heavy tailed compared to the exponential distribution. Besides, we also explored differences in distribution of the largest daily displacement according to gender and weekday. The analysis results indicate that male tend to have a larger displacement and individuals tend to travel longer on weekends.

关键词： Geophysical measurements Human factors Exponential distribution Urban planning Maximum likelihood estimation Fitting Global Positioning System

How Stair Configurations in Buildings Affect Pedestrian Dynamics on Stairs? A Simulation Study Via an Extended Three-Dimensional Force-Based Model

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Wang, Jianyu Ma, Jian Sarvi, Majid Chen, Tao Hu, Xiangmin Institute of Public Safety Research Department of Engineering Physics Tsinghua University Beijing100084 China School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu610031 China Transport Engineering Group Melbourne School of Engineering & IT The University of Melbourne VIC3010 Australia Anhui Province Key Laboratory of Human Safety Hefei Institute for Public Safety Research of Tsinghua University Hefei Anhui230601 China

Pedestrian movement on stairs is a complex three-dimensional dynamic process. However, previous models are inherently limited in that they ignored the significantly effect of stair configurations. This paper presents an extended three-dimensional force-based model to describe pedestrian movement and evacuation dynamics on stairs. By calibrating with previous real-human experiments, this unique model is able to accurately reproduce the velocity/density relation under a wide range of inclination stairways. Then, we explored the basic questions about pedestrian dynamics on complex stair configurations. The results demonstrated that: (1) this unique model shows good universality for simulating pedestrian dynamics on stairs;(2) Under the combined effect of narrow exit and stairs, the stair part is the primary factor that affects the specific capacity;(3) the optimal stair dimension is tread drpth≤0.325m & riser height≤0.1m;(4) pedestrian density and the geometric layout of the stairwell significantly influence pedestrian merging ratio at the merging zone. © 2022, The Authors. All rights reserved.

关键词： Stairs

Momentum Recursive Darts

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Ma, Benteng Xia, Yong Zhang, Yanning National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

DARTS has emerged as a popular method for neural architecture search (NAS) owing to its efficiency and simplicity. It employs gradient-based bi-level optimization to iteratively optimize the upper-level architecture parameters and lower-level super-network weights. One of the key challenges in DARTS is the accurate estimation of gradients for both upper-level and lower-level object functions, which existing methods struggle with, leading to significant errors in gradient approximation. To address this issue, we propose a new approach called MR-DARTS that incorporates a momentum term and a recursive scheme to improve gradient estimation. Specifically, MR-DARTS leverages historical information by using a running average of past observed gradients to enhance the quality of current gradient estimation in both upper-level and lower-level functions. Our theoretical analysis shows that the variance of our estimated gradient decreases with each iteration. By utilizing momentum and a recursive scheme, MR-DARTS effectively controls the error in stochastic gradient updates that results from inaccurate gradient estimation. Furthermore, we utilize the Neumann series approximation and Hessian Vector Product scheme to reduce computational requirements and memory usage. We evaluate our proposed method on several search spaces, including NAS Bench-201 and four variants of the DARTS search space, and demonstrate its effectiveness through comprehensive experiments. © 2023, The Authors. All rights reserved.

关键词： Image recognition

Robust Airport Gate Assignment to Minimize Aircraft Conflicts

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Du, Wenbo Zhu, Shaochuan Tong, Lu Liang, Zhe School of Electronic and Information Engineering Beihang University Beijing100191 China National Engineering Laboratory for Big Data Application Technologies for Comprehensive Traffic Beijing100191 China Research Institute of Frontier Science Beihang University Beijing100191 China School of Economics and Management Tongji University Shanghai200092 China

The increasing volume of air transportation has led to a scarcity of airport gate resources. The gate assignment is a vital problem for airport operations and management, and good assignment solutions can improve airport operation efficiency and resource utilization. However, the arrival and departure times of aircraft are uncertain in real-life operations, which easily causes aircraft conflicts in the gate assignment system, exacerbating delays spread in the whole airport system. The gate assignment incorporating the impact of aircraft delays in daily planning is essential. Moreover, the towing operations and the utilization of terminal gates greatly affect the operational efficiency of the airport. Therefore, this paper proposes a set-covering problem model simultaneously considering the schedule robustness measured by the expected conflict and the assignment efficiency affected by towing operations and heterogeneous gates. In particular, the conflict is introduced from the perspective of expectations and calculated by precise probabilistic information. A column generation-based heuristic is proposed to solve this model. The computational study based on real-world cases shows that the column generation provides tight LP relaxation solutions and the diving heuristic obtains good IP solutions efficiently. The simulations checking the robustness of assignment solutions reveal that the proposed method can avoid a significant number of conflicts under uncertain aircraft delays. Finally, a sensitivity analysis is studied to explore the trade-off between schedule robustness and assignment efficiency. © 2022, The Authors. All rights reserved.

关键词： Airports

Microscopic Right-of-Way Trading Mechanism for Cooperative Decision-Making: Theories and Preliminary Results

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Sun, Zhanbo Qin, Ziye Ma, Rui Huang, Tianyu Gao, Ziyan Ji, Ang School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Sichuan Chengdu China Department of Civil and Environmental Engineering The University of Alabama in Huntsville HuntsvilleAL United States School of Air Traffic Management Civil Aviation Flight University of China Sichuan Deyang China SenseTime IAG Shanghai China

In this paper, a microscopic right-of-way trading mechanism (Micro-ROWTM) is developed to encourage cooperative behavior in mixed traffic, which consists of cooperative vehicles (CoVs) and non-cooperative vehicles (NCoVs). Micro-ROWTM encompasses the following functions: (i) detection of traffic conflicts and system-improving opportunities;(ii) participants report their attributes;(iii) right-of-way trade proposed by the system;and (iv) trade settlement and cooperative control. In the experiments, the proposed mechanism is tested using an illustrative ramp-merging example, in which each right-of-way trade proposal is offered to a group of participants comprised of a mainline leader, a mainline follower and a ramp vehicle. Upon the acceptance of a proposal, the mainline leader and/or mainline follower agrees to behave cooperatively (yield) to the ramp vehicle, and receive monetary compensation from the ramp vehicle in return. To help design the trading mechanism, six important properties are introduced and discussed, including (i) strong individual rationality, (ii) system efficiency and group efficiency, (iii) dominant-strategy incentive compatibility, (iv) social welfare maximization, (v) utilitarian envy minimization and (vi) payoff difference minimization. A linear programming-based trading and taxation model which satisfies the above properties is then developed and solved. Using the proposed Micro-ROWTM, when the flow rates is 1000veh/h for both the mainline and ramp traffic, the ramp vehicles can save 6.8% travel time and 27.4% fuel consumption on average, and the mainline vehicles can eventually obtain a positive payoff by compensation. From a system perspective, the ramp-merging section can save 107.5s of travel time and 2450.3g of fuel consumption per hour. © 2023, The Authors. All rights reserved.

关键词： Game theory