检索结果-内蒙古大学图书馆

International Conference on Intelligent Transportation

作者： Lei Yang Yafei Liu Zhanbo Sun Qiruo Yan Ziye Qin Xuting Wang National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Transportation and Logistics Southwest Jiaotong University Chengdu China

The paper investigates the longitudinal control problem of a connected automated vehicle (CAV) platoon operating under the multiple-predecessor following (MPF) topology, while considering unreliable communication circumstances characterized by random packet loss and heterogeneous time-varying delay. To model random packet loss, a Bernoulli probabilistic distribution is employed, where the packet loss rate is influenced by the communication distance. A linear feedback controller is then developed to handle such packet loss and delay. The sufficient conditions for the asymptotic stability of the platoon controller are derived using linear matrix inequalities and a Lyapunov-based approach. The delay margin condition is obtained, which is associated with the packet loss rate and the number of consecutive packet losses. The string stability of the platoon with delay and packet loss is also analyzed by the transfer function. Simulation experiments demonstrate that the proposed method approach effectively maintains the stability of the platoon in the presence of delay and packet loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SC-GNN: A Communication-Efficient Semantic Compression for Distributed Training of GNNs 24

SC-GNN: A Communication-Efficient Semantic Compression for D...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Wang, Jihe Wu, Ying Wang, Danghui School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798400706011

Training big graph neural networks (GNNs) in distributed systems is quite time-consuming mainly because of the ubiquitous aggregate operations that involve a large amount of cross-partition communication for collecting embeddings/gradients during the forward and backward propagation. To reduce the volume of the communication, some recent approaches focused on decaying each of connections via sampling, quantifying, or delaying until satisfactory trade-off are obtained between volume and accuracy. However, when applied to popular GNNs, those approaches are found to be bounded by a common volume/accuracy Pareto frontier which shows that the decaying for individual connection cannot further accelerate the aggregate of training. In this work, SC-GNN, a semantic compression of the cross-partition communication, is proposed to concentrate a group of connections as a high-level semantics and transmit to a target partition. Since carrying the overall intent of a group, the semantics can keep transferring the interactions, i.e., embeddings/gradients, between a pair of remote partitions until GNN models converge. In addition, a connection-pattern based differential optimization is proposed to further prune those weak connections, while guaranteeing the training accuracy. The results show that, for multi-field datasets, the compression rate of SC-GNN is 40.8 × higher than SOTA methods and the epoch time is reduced to 31.8% on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Revisit the scheduling problem in Hurdle, V.F., 1973: A novel mathematical solution approach and two extensions

arXiv

引用

arXiv 2020年

作者： Fan, Wenbo School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China

The scheduling problem in Hurdle (1973) was formulated in a general form that simultaneously concerned the vehicle dispatching, circulating, fleet sizing, and patron queueing. As a constrained variational problem, it remains not fully solved for decades. With technical prowess in graphic analysis, the author unveiled the closed-form solution for the optimal dispatch rates (with key variables undetermined though), but only suggested the lower and upper bounds of the optimal fleet size. Additionally, such a graphic analysis method lacks high efficiency in computing specific scheduling problems, which are often of a large scale (e.g., hundreds of bus lines). In light of this, the paper proposes a novel mathematical solution approach that first relaxes the original problem to an unconstrained one, and then attacks it using calculus of variations. The corresponding Euler-Lagrange equation yields the closed-form solution of the optimal dispatching rates, to which Hurdle's results are a special case. Thanks to the proposed approach, the optimal fleet size can also be solved. This paper completes the work of Hurdle (1973) by formalizing a solution method and generalizing the results. Based on that, we further make two extensions to the scheduling problem of general bus lines with multiple origins and destinations and that of mixed-size or modular buses. Closed-form results are also obtained with new insights. Among others, we find that the solutions for shuttle/feeder lines are a special case to our results of general bus lines. Numerical examples are also provided to demonstrate the effectiveness and efficiency of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Wind-Bell Index: Towards Ultra-Fast Edge Query for Graph databases

Wind-Bell Index: Towards Ultra-Fast Edge Query for Graph Dat...

引用

International Conference on data engineering

作者： Rui Qiu Yi Ming Yisen Hong Haoyu Li Tong Yang School of Computer Science and National Engineering Laboratory for Big Data Analysis Technology and Application Peking University Beijing China Academy for Advanced Interdisciplinary Studies Peking University Peng Cheng Laboratory Shenzhen China

Graphs are good at presenting relational and structural information, making it powerful in the representation of various data. For the efficient storage and processing of graph-like data, graph databases have been rapidly developed and extensively studied. However, graph databases mostly use adjacency lists as their basic data structure (e.g., Neo4j), which could result in poor performance of edge due to the skewed degree distribution of *** design the Wind-Bell Index to address this problem. Wind-Bell Index is a memory-efficient index data structure, which can be attached to existing graph databases to speed up the edge. We have fully implemented our data structure in Neo4j, the most popular graph database today, and conduct theoretical and experimental analysis to evaluate the performance. Theoretical results prove the high query efficiency of our algorithm. And experimental results show that the average edge query speed is increased by hundreds of times compared with the original query interface of Neo4j. We believe that the excellent performance and scalability of Wind-Bell Index make it suitable for the application in a variety of graph databases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Coordinated Congestion Pricing for Bi-Modal Multi-Region Urban Networks

Coordinated Congestion Pricing for Bi-Modal Multi-Region Urb...

引用

International Conference on Intelligent Transportation

作者： Xiangyu He Yu Zhao Yafei Liu Zhanbo Sun National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Transportation and Logistics Southwest Jiaotong University Chengdu China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Extensive studies have explored designing pricing schemes for single-mode or homogeneous networks. The development of bi-modal Macroscopic Fundamental Diagrams (3D-MFD) facilitates real-time coordinated control strategies for bi-modal multi-regional urban networks. This research explores the traffic dynamics of mixed networks with urban networks and expressways, proposing two 3D-MFD-based coordinated pricing schemes for bi-modal multi-region urban networks. The first scheme utilizes a Model Predictive Control (MPC) approach to integrating toll rates into the 3D-MFD-based optimization problem. The second scheme applies feedback control theory to simultaneously determine the dynamic price and estimate the value of Time (VOT) and trip length distribution of commuters. The proposed coordinated pricing schemes are further compared with uncoordinated pricing schemes. Numerical examples indicate that coordinated pricing by comprehensively considering the traffic flow and demand across different regions of the urban network achieves more effective congestion alleviation.

关键词： Sensitivity Pricing Real-time systems Feedback control Optimization Intelligent transportation systems Predictive control

来源：评论

学校读者我要写书评

暂无评论

Research on the Network Operation Mode of High-Speed Rail Express 5th

Research on the Network Operation Mode of High-Speed Rail Ex...

引用

5th International Conference on Smart Vehicular technology, Transportation, Communication and applications, VTCA 2022

作者： Wang, Yongcheng Li, Yi Sun, Yunhao Chen, Tao Department of Transportation China Railway Beijing Group Co. Ltd Beijing100860 China School of Transportation and Logistics Southwest Jiaotong University Chengdu610031 China National and Local Joint Engineering Laboratory of Comprehensive Intelligent Transportation Southwest Jiaotong University Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

ISBN: (纸本)9789819908479

Taking high-speed rail express as the research object, the research is carried out on the network operation mode of high-speed rail express. Taking the minimum cost of transportation enterprises as the optimization goal, the decision model of the network operation mode of high-speed rail express is constructed by taking the remaining capacity limit of the middle section of the high-speed rail express line network, the carrying capacity and operating cost restrictions corresponding to the high-speed rail express operating mode, and the overall transportation task limit as constraints. Taking the train operation map in the third quarter of 2021 as a reference, the decision-making model for the construction of the operation mode is verified, and the ARIMA model is used to calculate the OD of each city node in the prospect year, and the carrying capacity and operation cost of different operation modes are analyzed and calculated. The results show that: my country should adopt a high-speed rail express network operation mode combining direct transit. Transit transportation completes the collection and distribution of small batches of goods, improves the full load rate of high-speed rail freight trains, expands the scope of services, and completes long-distance transportation of large batches of goods through direct transportation, improving economies of scale. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

Innovative remote sensing methodologies and applications in coastal and marine environments

引用

地球空间信息科学学报（英文版） 2024年第3期27卷 836-853页

作者： Qing Zhao Antonio Pepe Virginia Zamparelli Pietro Mastro Francesco Falabella Saygin Abdikan Caglar Bayik Fusun Balik Sanli Mustafa Ustuner Nevin Betul Avşar Jingjing Wang Peng Chen Zhengjie Li Adam T.Devlin Fabiana Calò Key Laboratory of Geographical Information Science Ministry of EducationEast China Normal UniversityShanghaiChina School of Geographic Sciences East China Normal UniversityShanghaiChina Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural ResourcesShanghaiChina Institute for Electromagnetic Sensing of the Environment(IREA) Italian National Research CouncilNapoliItaly School of Engineering University of BasilicataPotenzaItaly Institute for Electromagnetic Sensing of the Environment(IREA) Italian National Research CouncilNapoliItaly Institute for Electromagnetic Sensing of the Environment(IREA) Italian National Research CouncilNapoliItaly Institute of Methodologies for Environmental Analysis(IMAA) Italian National Research CouncilTito ScaloItaly Department of Geomatics Engineering Hacettepe UniversityAnkaraTurkey Department of Geomatics Engineering Zonguldak Bulent Ecevit UniversityZonguldakTurkey Department of Geomatic Engineering Yildiz Technical UniversityIstanbulTurkey Department of Geomatic Engineering Artvin Çoruh UniversityArtvinTurkey Department of Geomatics Engineering Izmir Katip Celebi UniversityİzmirTurkey School of Ocean and Earth Science and Technology University of Hawaii at MānoaHonoluluHIUSA

Remote sensing(RS)technologies are extensively exploited by scientists and a vast audience of local authorities,urban managers,and city *** regions,geohazard-prone areas,and highly populated cities represent natural laboratories to apply RS technologies and test new *** the last decades,many efforts have been spent on improving Earth's surface monitoring,including intensifying Earth Observation(EO)operations by the major national space *** oversee to plan and make operational constellations of satellite sensors providing the scientific community with extensive research and development oppor-tunities in the geoscience *** instance,within this framework,the European Space Agency(ESA)and the Ministry of Science and technology of China(MOST)have sponsored,since the early 2000s,the DRAGON initiative jointly carried out by the European and Chinese RS scientific *** manuscript aims to provide a synthetic overview of some research activities and new methods recently designed and applied and trace the route for further *** main findings are related to ⅰ)the analysis of flood risk in China,ⅱ)the potential of new methods for the estimation and removal of ground displacement biases in small-baseline oriented interferometric Synthetic Aperture Radar(SAR)methods,ⅲ)the analy-sis of the inundation risk in low-lying regions using coherent and incoherent SAR methods;andⅳ)the use of SAR-based technologies for marine applications.

关键词： Disaster risk management Remote Sensing(RS) Earth Observation(EO) Synthetic Aperture Radar(SAR) flooding subsidence coastal/marine environments

来源：评论

学校读者我要写书评

暂无评论

Learning from history and present: Next-item recommendation via discriminatively exploiting user behaviors

arXiv

引用

arXiv 2018年

作者： Li, Zhi Zhao, Hongke Liu, Qi Huang, Zhenya Mei, Tao Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China School of Software Engineering University of Science and Technology of China JD AI Research

In the modern e-commerce, the behaviors of customers contain rich information, e.g., consumption habits, the dynamics of preferences. Recently, session-based recommendations are becoming popular to explore the temporal characteristics of customers’ interactive behaviors. However, existing works mainly exploit the short-term behaviors without fully taking the customers’ long-term stable preferences and evolutions into account. In this paper, we propose a novel Behavior-Intensive Neural Network (BINN) for next-item recommendation by incorporating both users’ historical stable preferences and present consumption motivations. Specifically, BINN contains two main components, i.e., Neural Item Embedding, and Discriminative Behaviors Learning. Firstly, a novel item embedding method based on user interactions is developed for obtaining an unified representation for each item. Then, with the embedded items and the interactive behaviors over item sequences, BINN discriminatively learns the historical preferences and present motivations of the target users. Thus, BINN could better perform recommendations of the next items for the target users. Finally, for evaluating the performances of BINN, we conduct extensive experiments on two real-world datasets, i.e., Tianchi and JD. The experimental results clearly demonstrate the effectiveness of BINN compared with several state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Lagrangian traffic flow model considering lane changing behavior: Formulation and numerical implementation

A Lagrangian traffic flow model considering lane changing be...

引用

2020 Forum on Integrated and Sustainable Transportation Systems, FISTS 2020

作者： Lu, Liang Zheng, Fangfang Liu, Xiaobo Yuan, Yufei Southwest Jiaotong University Western Hi-tech Zone Chengdu School of Transportation and Logistics Sichuan611756 China Southwest Jiaotong University School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology 611756 China Delft University of Technology Department of Transport and Planning Delft Netherlands

ISBN: (数字)9781728195032

ISBN: (纸本)9781728195032

This paper proposes a multilane traffic flow model based on the notions of conservation laws in Lagrangian coordinates. Both the mathematical formulation and the graphical representation are provided. A logit choice model is applied to describe drivers' lane choice probability. The lane changing rate is estimated by employing the Incremental Transfer (IT) principle and the lane choice probability model. The numerical implementation of the model in the case of two lanes is discussed. The simulation results reveal that the proposed Lagrangian model is able to describe lane changing dynamics of vehicle platoons;while the lane changing equilibrium curve at the macroscopic level is consistent with that from the multilane Eulerian model as well as the observed data on the highway. © 2020 IEEE.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Optimization Principle of Freight Train Operation Plan for Shenhua Railway 5th

Optimization Principle of Freight Train Operation Plan for S...

引用

5th International Conference on Smart Vehicular technology, Transportation, Communication and applications, VTCA 2022

作者： Wang, Meng Liu, Qiuqi He, Wenhui Guo, Xiuyun Southwest Jiaotong University Chengdu610031 China China National Energy Group Railway Equipment Company Beijing100000 China School of Transportation and Logistics Southwest Jiaotong University Chengdu610031 China National and Local Joint Engineering Laboratory of Comprehensive Intelligent Transportation Southwest JiaoTong University Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Beijing China

ISBN: (纸本)9789819908479

At present, the freight train formation plan cannot dynamically reflect the changes in freight demand in the transportation market, which makes it difficult to guide the actual transportation production work and affects the economic benefits of enterprises. This paper takes Shenhua Heavy Duty Railway as the research object, studies the optimization technology of cargo train programming under dynamic planning type transportation organization mode, and proposes the optimization principle of dynamic cargo train programming of Shenhua Railway. By analyzing the characteristics of the cargo transportation organization of Shenhua Railway, the dynamic planning type transportation organization mode of Shenhua Railway is proposed. On the basis of the concept of the dynamic freight train operation scheme of Shenhua Railway, the feasibility of preparation optimization, influencing factors, and main principles, the idea of dynamic preparation optimization research from the perspective of synergistic consideration of heavy train operation scheme and empty train deployment scheme is also elaborated. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：