检索结果-内蒙古大学图书馆

作者： Huawei ZHU Yihao MAO Yiming ZHAO Liyuan SHI Yanli SHAO School of Information and Electrical Engineering Zhejiang University City College Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and TechnologyHangzhou Dianzi University

With the development of urbanization,the number of residents' motor vehicles has increased sharply,and traffic congestion problem has become increasingly *** construction of Intelligent Traffic System(ITS) has become the main means to alleviate traffic ***-term traffic flow prediction has guiding significance for residents' travel planning and intelligent management of transportation,and has become one of the research hotspots in intelligent transportation ***,A short-term traffic flow prediction method based on the spatio-temporal characteristics of complex road networks is proposed to further improve the prediction accuracy and reduce the prediction ***,a graph convolutional network(GCN) capable of processing non-Euclidean data structures is used to extract the spatial characteristics of traffic flow ***,the long and short-term memory(LSTM) neural network is used to process the time ***,the two are combined to realize the effective processing of the spatio-temporal characteristics of traffic flow *** results on the real traffic flow dataset prove the feasibility and effectiveness of the proposed method,and can provide a basis for intelligent traffic control and smart city construction.

关键词： Traffic Flow Prediction Spatio-temporal GCN LSTM

来源：评论

学校读者我要写书评

暂无评论

Relaxation dynamics in the alternating XY chain following a quantum quench

arXiv

引用

arXiv 2023年

作者： Cao, Kaiyuan Hu, Yayun Tong, Peiqing Yang, Guangwen Liu, Peng Zhejiang Lab Hangzhou311100 China Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing210023 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China Department of Computer Science and Technology Tsinghua University Haidian District Beijing100084 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China

We investigate the relaxation dynamics of the fermion two-point correlation function Cmn(t) = 〈ψ(t)|c†mcn|ψ(t)〉 in the XY chain with alternating nearest-neighbor hopping interaction after a quench. We find that the deviation δCmn(t) = Cmn(t) − Cmn(∞) decays with time following the power law behavior t−µ, where the exponent µ depends on whether the quench is to the commensurate phase (µ = 1) or incommensurate phase (µ = 1/2). This decay of δCmn(t) arises from the transient behavior of the double-excited quasiparticle occupations and the transitions between different excitation spectra. Furthermore, we find that the steady value Cmn(∞) only involves the average fermion occupation numbers (i.e. the average excited single particle) over the time-evolved state, which are different from the ground state expectation values. We also observe nonanalytic singularities in the steady value Cmn(∞) for the quench to the critical points of the quantum phase transitions (QPTs), suggesting its potential use as a signature of QPTs. Copyright © 2023, The Authors. All rights reserved.

关键词： Ground state

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Emerging Intelligent Vehicles and Intelligent Vehicle Carriers Collaborative systems

The Emerging Intelligent Vehicles and Intelligent Vehicle Ca...

引用

IEEE Symposium on Intelligent Vehicle

作者： Zhipeng Shen Chao Huang Hailong Huang Yutong Wang Fei-Yue Wang Abbas Jamalipour Duc Truong Pham Ljubo Vlacic Andrey V. Savkin Department of Aeronautical and Aviation Engineering the Hong Kong Polytechnic University Hong Kong Department of Industrial and Systems Engineering the Hong Kong Polytechnic University Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China School of Electrical and Information Engineering University of Sydney Sydney Australia Department of Mechanical Engineering University of Birmingham Birmingham UK Institute of Intelligent & Integrated Systems and the School of Engineering and Built Environment Griffith University Brisbane Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we propose the innovative use of Intelligent Vehicle Carriers (IVCs) as a key solution to address the energy constraints of small-scale unmanned Intelligent Vehicles (IVs). IVCs function as both transporters and charging stations, significantly boosting the operational range and efficiency of IVs. Our research delves into the IV-IVC collaborative framework, highlighting the existing challenges, exploring potential solutions, and examining a range of applications. This study offers a visionary approach to revolutionizing intelligent transportation systems by leveraging the synergistic relationship between IVs and IVCs.

关键词： Intelligent vehicles Collaboration Charging stations Boosting

来源：评论

学校读者我要写书评

暂无评论

A grain level model for deformation and failure of ultrafine-grained tungsten

引用

science China(Technological sciences) 2019年第5期62卷 755-761页

作者： REN Ke CHEN LiRong CHENG YangYang WANG JianXiang DUAN HuiLing State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of EngineeringPeking University Key Laboratory of High Energy Density Physics Simulation Center of Applied Physics and Technology BIC-ESAT and IFSA Collaborative Innovation Center of MoE Peking University

Ultrafine-grained tungsten(UFG W) produced by severe plastic deformation technology has many potential applications due to its high strength and ductility. To reveal the mechanism for the high ductility of UFG W, the deformation and failure behaviors of coarse-grained tungsten(CG W) and UFG W have been compared based on a three-dimensional crystal plastic finite element method(CPFEM) simulation. Cohesive element method has been utilized to model the behavior of grain boundaries(GBs). Both plastic deformation in grain interiors and grain boundary opening have been observed in different periods of deformation in UFG W. It is concluded that the high GB density and elongated microstructure in the UFG W suppress crack propagation, decrease the stress concentration and impurity concentration on GBs, therefore enhance the ductility of the material.

关键词： ultrafine grain(UFG) tungsten crystal plasticity interface failure

来源：评论

学校读者我要写书评

暂无评论

Impact of Ligand Fields on Kubas Interaction of Open Copper Sites in Mofs with Hydrogen Molecules: An Electronic Structural Insight

SSRN

引用

SSRN 2024年

作者： Nguyen-Thuy, Trang Tran-Van, Hoan Nguyen-Hoang, Linh Nguyen-Minh, Hoang Phan, Bach Thang Nguyen-The, Toan Kawazoe, Yoshiyuki Faculty of physics University of Science Vietnam National University – Hanoi Hanoi Viet Nam School of engineering physics Hanoi University of Technology Hanoi Viet Nam Center for Innovative Materials and Architectures Vietnam National University Ho Chi Minh City Ho Chi Minh City Viet Nam Vietnam National University HoChiMinh City Viet Nam Key Laboratory for Multiscale Simulation of Complex Systems University of Science Vietnam National University – Hanoi Hanoi Viet Nam New Industry Creation Hatchery Center Tohoku University Sendai980-8579 Japan Department of Physics and Nanotechnology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India School of Physics Institute of Science Suranaree University of Technology 111 University Avenue Nakhon Ratchasima30000 Thailand

Using DFT calculations, we investigate hydrogen sorption on open copper sites in various ligand coordinations of metal-organic frameworks (MOFs), including the triangle coordination T(CuL3) in MFU-4l, the linear coordination L(CuL2) in NU2100 and the paddlewheel coordination P(CuL4)2 in HKUST-1. By examining the ligand field splitting of d states and spd hybridizations in copper, we reveal the electronic mechanisms influencing hydrogen sorption performance. Despite Cu+ oxidization state which is expected to facilitate strong Kubas interaction with hydrogen molecules, the vacant s-p-dz2 hybrid orbitals of the open copper site in the L(CuL2) coordination are unsuitable for overlapping with the H2 s bonding orbital, preventing hydrogen adsorption. In contrast, the T(CuL3) and P(CuL4)2 coordinations enable hydrogen adsorption by inducing suitable hydrid orbitals. The vacant Cu s-p-dz2 hybrid orbitals in these cases can overlap with the H2 s bonding orbital to facilitate electron forward donation, forming bonding states between the Cu s-p-dz2 and H2 s bonding orbitals. The occupied Cu s-p-dxz/yz and s-p-dx2-y2 hybrid orbitals in the case of T(CuL3) promote the electron back donation to the H2 s* antibonding orbital, leading to the formation of bonding states. Conversely, in P(CuL4)2 coordination, the absence of such hybridization results in the lack of electron back donation. The complete Kubas interaction with both forward and back electron donations is responsible for a higher adsorption energy of 37.6 kJ/mol in the case of T(CuL3) than the value of 10.6 kJ/mol in the P(CuL4)2 coordination. © 2024, The Authors. All rights reserved.

关键词： Electronic structure

来源：评论

学校读者我要写书评

暂无评论

A Solution Analysis of U.S. Weapon Equipment systems-of-systems Development and Application

A Solution Analysis of U.S. Weapon Equipment Systems-of-Syst...

引用

International Conference on Information science and Control Engineering (ICISCE)

作者： Menglong Lin Shuanghui Yi Mengmeng Zhang Zhen Shu Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China National Key Laboratory for Complex System Simulation Beijing China

In recent years, the development and deployment of the U.S. weapon equipment systems-of-systems (SoS) have yielded rich research results. However, there are still large gaps in the SoS development, joint testing, and design and acquisition of our own equipment SoS. The barriers of these steps have not yet been opened up. This article mainly analyzes the solutions of the U.S. weapon equipment SoS from three aspects, such as capability-based requirement generation and architecture design technology, interconnected-oriented integration test technology, and weapon equipment design and acquisition technology based on complex adaptive systems. We explore key technologies involved in order to form an overall understanding and explore related research approaches.

关键词： Technological innovation Adaptive systems Weapons Agent-based modeling Planning Sustainable development System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training

arXiv

引用

arXiv 2023年

作者： Zhang, Ke Yang, Yan Yu, Jun Jiang, Hanliang Fan, Jianping Huang, Qingming Han, Weidong The Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Regional Medical Center for National Institute of Respiratory Diseases Sir Run Run Shaw Hospital College of Medicine Zhejiang University Hangzhou310016 China AI Lab at Lenovo Research 100094 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Department of Medical Oncology at Sir Run Run Shaw Hospital College of Medicine Zhejiang University Hangzhou China The College of Mathematical Medicine Zhejiang Normal University Jinhua China

In recent years, the growing demand for medical imaging diagnosis has placed a significant burden on radiologists. As a solution, Medical Vision-Language Pre-training (Med-VLP) methods have been proposed to learn universal representations from medical images and reports, benefiting downstream tasks without requiring fine-grained annotations. However, existing methods have overlooked the importance of cross-modal alignment in joint image-text reconstruction, resulting in insufficient cross-modal interaction. To address this limitation, we propose a unified Med-VLP framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework to achieve more comprehensive cross-modal interaction, while a Global and Local Alignment (GLA) module is designed to assist self-supervised paradigm in obtaining semantic representations with rich domain knowledge. Furthermore, we introduce a Memory-Augmented Cross-Modal Fusion (MA-CMF) module to fully integrate visual information to assist report reconstruction and fuse the multi-modal representations adequately. Experimental results demonstrate that the proposed unified approach outperforms previous methods in all downstream tasks, including uni-modal, cross-modal, and multimodal tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Neural architecture search for fault diagnosis

arXiv

引用

arXiv 2020年

作者： Li, Xudong Hu, Yang Zheng, Jianhua Li, Mingtao National Space Science Center. CAS University of Chinese Academy of Sciences Beijing China Science and Technology on Complex Aviation System Simulation Laboratory 9236 mailbox Beijing China

Data-driven methods has made great progress in fault diagnosis, especially deep learning method. Deep learning is suitable for processing big data, and has a strong feature extraction ability to realize end-to-end fault diagnosis systems. Due to the complexity and variability of experimental data, some deep learning models are designed to be complex. However, designing neural network architecture requires rich professional knowledge and debugging experience, and a lot of experiments are needed to screen models and hyperparameters, increasing the difficulty of developing deep learning models. Fortunately, neural architecture search (NAS) is developing rapidly, and is becoming one of the next directions for deep learning. Given a search space, NAS can automatically search for the optimal network architecture. In this paper, we proposed a NAS method for fault diagnosis using reinforcement learning. A recurrent neural network is used as an agent to generate the network architecture. The accuracy of the generated network on the validation dataset is fed back to the agent as a reward, and the parameters of the agent are updated through the strategy gradient algorithm. In order to speed up the search process, parameters sharing method is adopted in this paper. We use PHM 2009 Data Challeng gearbox dataset to prove the effectiveness of propsed method, and obtain state-of-the-art results compared with other artificial designed network structures. To authors best knowledge, its the first time that NAS has been applied in fault diagnosis. Copyright © 2020, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A KDC-enhanced closest point method for thermal analysis on curved geometries using LS-GFDM

引用

Applied Mathematics Letters 2025年 171卷

作者： Zhuochao Tang Jiming Gu Bin Chen Zhuojia Fu School of Management Science and Engineering Anhui University of Technology Maanshan 243002 China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Maanshan 243002 China Center for Numerical Simulation Software in Engineering and Sciences College of Mechanics and Engineering Science Hohai University Nanjing 211100 China

This paper presents a Krylov-deferred correction (KDC)-enhanced closest point method (CPM) integrated with the least-squares generalized finite difference method (LS-GFDM) for thermal analysis on curved geometries. To overcome the inherent limitations of conventional single-step/multi-step temporal schemes in long-time simulations, we systematically unify three advanced components: (i) CPM’s embedding strategy that transforms surface PDEs into extended problems over Cartesian grids, (ii) LS-GFDM’s spatial discretization employing dual point sets to enhance applicability beyond conventional GFDM, and (iii) KDC’s predictor–corrector framework that iteratively refines temporal solutions to achieve high-order accuracy. Building upon our previous work (Tang et al. 2025) where LS-GFDM was integrated with CPM using explicit Euler temporal schemes, this study constitutes a critical advancement by replacing low-order temporal discretization with the KDC methodology. Numerical experiments demonstrate that our KDC-CPM-LSGFDM framework achieves superior numerical performance.

关键词：

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：