检索结果-内蒙古大学图书馆

9th International Conference on Big Data and information Analytics, BigDIA 2023

作者： Li, Yaoyu Jin, Shuai Zhu, Jianghan National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (纸本)9798350330076

This study examines key characteristics of cloud computing technology within the domain of federated learning, with the primary objective of exploring the principles concerning distributed computing acceleration ratio and storage input/output efficiency across various network segments. Combining the heterogeneous characteristics of cloud segments, we present a novel approach for distributed model training strategies by using the federated learning technique. This approach can keep the accuracy of the model, enhance training efficiency, and protect user privacy. The experiment demonstrates that the proposed strategy outperforms the baseline method, which does not account for variations in different segments. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Wu, Guotong Nan, Yang Shang, Ke Ishibuchi, Hisao Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9781665410205

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An adaptive multitasking optimization algorithm based on population distribution

引用

Mathematical Biosciences and engineering 2024年第2期21卷 2432-2457页

作者： Li, Xiaoyu Wang, Lei Jiang, Qiaoyong Xu, Qingzheng School of Computer Science and Engineering Xi'an University of Technology Xi'an710048 China School of Electronic and Information Engineering Ankang University Ankang725000 China The Key Laboratory of Industrial Automation of Shaanxi Province Shaanxi University of Technology Hanzhong723001 China College of Information and Communication National University of Defense Technology Wuhan430019 China

Evolutionary multitasking optimization (EMTO) handles multiple tasks simultaneously by transferring and sharing valuable knowledge from other relevant tasks. How to effectively identify transferred knowledge and reduce negative knowledge transfer are two key issues in EMTO. Many existing EMTO algorithms treat the elite solutions in tasks as transferred knowledge between tasks. However, these algorithms may not be effective enough when the global optimums of the tasks are far apart. In this paper, we study an adaptive evolutionary multitasking optimization algorithm based on population distribution information to find valuable transferred knowledge and weaken the negative transfer between tasks. In this paper, we first divide each task population into K sub-populations based on the fitness values of the individuals, and then the maximum mean discrepancy (MMD) is utilized to calculate the distribution difference between each sub-population in the source task and the subpopulation where the best solution of the target task is located. Among the sub-populations of the source task, the sub-population with the smallest MMD value is selected, and the individuals in it are used as transferred individuals. In this way, the solution chosen for the transfer may be an elite solution or some other solution. In addition, an improved randomized interaction probability is also included in the proposed algorithm to adjust the intensity of inter-task interactions. The experimental results on two multitasking test suites demonstrate that the proposed algorithm achieves high solution accuracy and fast convergence for most problems, especially for problems with low relevance. © 2024 the Author(s).

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Collaborative Learning for Cross-Organizational Data Sharing Using Hyperledger Fabric 8

Collaborative Learning for Cross-Organizational Data Sharing...

引用

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Zheng, Yaling Cheng, Ziwen Liu, Yi Wang, Bowen Zhu, Cheng National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (纸本)9798350331035

The rise of edge networking presents both opportunities and challenges. The ever-expanding array of IoT devices generates vast amounts of data, enabling collaboration and smart applications. However, managing decentralized data, resolving heterogeneity, and ensuring privacy poses challenges. The combination of blockchain and federated learning offers a solution. But trust management, inefficiencies, and ambiguous assessment of data contribution have become new obstacles. In this paper, we propose a data sharing model that supports cross-organizational collaborative learning based on Hyperledger Fabric, in order to enhance the high-quality data sharing of collaborative learning and improve the effect of learning. The experimental results show that the proposed model can realize decentralized and efficient data sharing and improve the accuracy and stability of collaborative learning under acceptable communication load. © 2023 IEEE.

关键词： blockchain collaborative learning data sharing edge network Hyperledger Fabric

来源：评论

学校读者我要写书评

暂无评论

Coexisting Magnetism, Ferroelectric, and Ferrovalley Multiferroic in Stacking-Dependent Two-Dimensional Materials (vol 24, pg 3541, 2024)

引用

NANO LETTERS 2024年第17期24卷 5393-5394页

作者： Xun, Wei Wu, Chao Sun, Hanbo Zhang, Weixi Wu, Yin-Zhong Li, Ping State Key Laboratory for Mechanical Behavior of Materials Center for Spintronics and Quantum System School of Materials Science and Engineering Xi’an Jiaotong University Xi’an Shaanxi 710049 People’s Republic of China Faculty of Electronic Information Engineering Huaiyin Institute of Technology Huaian 223003 People’s Republic of China Department of Physics and Electronic Engineering Tongren University Tongren 554300 People’s Republic of China School of Physical Science and Technology Suzhou University of Science and Technology Suzhou 215009 People’s Republic of China State Key Laboratory for Surface Physics and Department of Physics Fudan University Shanghai 200433 China

Two-dimensional (2D) multiferroic materials have widespread application prospects in facilitating the integration and miniaturization of nanodevices. However, the magnetic, ferroelectric, and ferrovalley properties in one 2D material are rarely coupled. Here, we propose a mechanism for manipulating magnetism, ferroelectric, and valley polarization by interlayer sliding in a 2D bilayer material. Monolayer GdI2 is a ferromagnetic semiconductor with a valley polarization of up to 155.5 meV. More interestingly, the magnetism and valley polarization of bilayer GdI2 can be strongly coupled by sliding ferroelectricity, making these tunable and reversible. In addition, we uncover the microscopic mechanism of the magnetic phase transition by a spin Hamiltonian and electron hopping between layers. Our findings offer a new direction for investigating 2D multiferroic devices with implications for next-generation electronic, valleytronic, and spintronic devices.

关键词： two-dimensional multiferroic sliding ferroelectricity ferrovalley magnetic phase transition d-orbital hopping

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Source Code Vulnerability Detection via Graph Neural Networks 35

Fine-Grained Source Code Vulnerability Detection via Graph N...

引用

35th International Conference on Software engineering and Knowledge engineering, SEKE 2023

作者： Wang, Jingjing Huang, Minhuan Nie, Yuanpin Kuang, Xiaohui Li, Xiang Zhong, Wenjing National Key Laboratory of Science and Technology Information System Security Beijing China Xidian University Xi’an China

Although the number of exploitable vulnerabilities in software continues to increase, the speed of bug fixes and software updates have not increased accordingly. It is therefore crucial to analyze the source code and identify vulnerabilities in the early phase of software development. However, vulnerability location in most of the current machine learning-based methods tends to concentrate at the function level. It undoubtedly imposes a burden on further manual code audits when faced with large-scale source code projects. In this paper, a fine-grained source code vulnerability detection model based on Graph Neural Networks (GNNs) is proposed with the aim of locating vulnerabilities at the function level and line level. Our empirical evaluation on different C/C++ datasets demonstrated that our proposed model outperforms the state-of-the-art methods and achieves significant improvements even when faced with more complex, real-project source code. © 2023 Knowledge systems Institute Graduate School. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Unlocking Co3O4–ZnO p-n heterojunction for superior acetone gas sensing detection

引用

Progress in Natural science:Materials International 2024年第5期34卷 990-999页

作者： Xingxing Liu Tingting Shao Juntang Dong Huirong Kou Fuchun Zhang Yuyang Cheng Jiaming Guo Shuwei Tian Kuldeep K.Saxena Xinghui Liu School of Physics and Electronic Information Yan'an University Division of Research and Development Lovely Professional University Science and Technology on Aerospace Chemical Power Laboratory Laboratory of Emergency Safety and Rescue Technology Hubei Institute of Aerospace Chemotechnology Department of Materials Physics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMTS)

In this study, we synthesized pure ZnO and Co3O4–ZnO precursors with varied Co, Zn ratios via solvothermal method, and then the precursors were calcined at 400°C for 2 h in a muffle furnace under air to obtain composites for acetone detection. The structure, morphology, elemental composition, microstructure and chemical state of these materials were systematically studied by various characterization techniques. Additionally, we also evaluated the gas sensing performance of the composites-based sensors, focusing on optimal operating temperature,baseline resistance, repeatability, stability, selectivity, response/recovery time, and resistance under varying relative humidity. The findings reveal that 3 % Co3O4–ZnO-based sensor exhibit the highest response value to 100 ppm acetone（74）, showing an enhancement of approximately 9.3 times compared to the pure ZnO-based sensor（8）. Furthermore, the 3 % Co3O4–ZnO-based sensor demonstrate the advantages of rapid response/recovery times（15 s/2 s）, outstanding selectivity, and remarkable stability. The gas sensing mechanism of the composite material is also discussed in detail, which provides insights into the observed enhancement of gas sensing performance. It provides an idea for the follow-up study on gas sensing performance of acetone sensors.

关键词： Heterojunction Acetone Co_3O_4-ZnO Gas sensing Solvothermal method

来源：评论

学校读者我要写书评

暂无评论

High-Precision DOA Estimation Method Based on Synthetic Aperture Technique

引用

Journal of Beijing Institute of technology 2024年第2期33卷 111-118页

作者： Yongjia Dou Guangcai Sun Yuqi Wang Mengdao Xing National Key Laboratory of Radar Signal Processing Xidian UniversityXi’an 710071China School of Communication and Information Engineering Xi’an University of Science and TechnologyXi’an 710054China

The existing direction-of-arrival(DOA)estimation methods only utilize the current received signals,which are susceptible to *** this paper,a method for DOA estimation based on a motion platform is proposed to achieve high-precision DOA estimation by utilizing past and present *** concept of synthetic aperture is introduced to construct a linear DOA estima-tion model.A DOA fine-tuning method based on the linear model is proposed to eliminate the lin-ear DOA variation,achieving a non-coherent accumulation of DOA ***,the baseband modulation and the phase modulation caused by the range history are compensated to achieve the coherent accumulation of all the DOA *** results show that the proposed method can significantly improve the DOA estimated accuracy at low signal-to-noise ratios(SNR).

关键词： synthetic aperture direction-of-arrival(DOA)estimation coherent accumulation

来源：评论

学校读者我要写书评

暂无评论

AE-TGN: Attribute-Empowered Temporal Graph Networks for Dynamic Graph Link Prediction

AE-TGN: Attribute-Empowered Temporal Graph Networks for Dyna...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Chen, Chonghao Luo, Aimin Huang, Yang National University of Defense Technology Science and Technology on Information Systems Engineering Laboratory Changsha China

ISBN: (纸本)9798350304602

Temporal/dynamic graph link prediction task requires the AI systems to predict the possible future edges based on the observation history of graph events. Existing works for the temporal graph learning mainly use the recurrent neural networks or self-attention mechanism to model the interaction information of graph, and ignore the node attribute features. In particular, they usually adopt a static attribute encoder where the attribute representation can not adjust according the graph structure evolution. To address this issue, we propose Attribute-Empowered Temporal Graph Networks (AE-TGN), which leverages a dynamic attribute leaning module to fine-tune the attribute embedding. In detail, we use the recurrent networks to encode the memory of nodes and the temporal self-attention mechanism to capture the spatial graph information. Next, a trainable multi-layer perceptron is employed to adjust the node attribute representation. Finally, the node attribute embeddings are concatenated with the memory vectors as the temporal embeddings of nodes, and fed into the link prediction decoder. Experimental results on two real-world datasets demonstrates the superiority of our proposal by beating competitive baselines. Specially, AE-TGN presents obvious improvements in the inductive setting, which validates that the attribute encoder can produce accurate node representation for the downstream task. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Port-controllable routing of orbital angular momentum modes using a rotatable diffractive neural network

引用

science China(Physics,Mechanics & Astronomy) 2025年第6期68卷 154-163页

作者： Junmin Liu Jiafu Chen Qingji Zeng Zemin Liang Xinping Wu Xin Zhao Jiangnan Xiao Huapeng Ye Ze Dong Dianyuan Fan Shuqing Chen Institute of Microscale Optoelectronics Shenzhen UniversityShenzhen 518060China College of New Materials and New Energies Shenzhen Technology UniversityShenzhen 518118China Terahertz Technology Innovation Research Institute Shanghai Key Laboratory of Modern Optical SystemTerahertz Science Cooperative Innovation CenterSchool of Optical-Electrical Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Guangdong Provincial Key Laboratory of Optical Information Materials and Technology&Institute of Electronic Paper Displays South China Academy of Advanced OptoelectronicsSouth China Normal UniversityGuangzhou 510006China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China

Orbital angular momentum(OAM)modes provide an additional orthogonal physical dimension,offering transformative potential for enhancing optical communication *** significant progress in mode multiplexing,the development of robust communication networks faces persistent challenges,particularly in effectively routing and controlling these multiplexed channels among network *** tackle these dilemmas,we propose a rotatable diffractive neural network(R-DNN)strategy and demonstrate its capability for port-controllable OAM mode *** leveraging the correlation between the orthogonal evolution of OAM modes in free space and phase modulations during propagation,the R-DNN precisely shapes the spatial evolution of mode fields through multiple rotatable phase layers,enabling efficient routing to specific output *** approach exploits the interaction of secondary wavelets with the relative states of the rotatable layers,allowing on-demand control of mode evolution paths and enhancing routing *** a proof of concept,we developed a tri-functional router that successfully directs three OAM modes to individually controllable output *** router achieves an average intermode crosstalk of less than−16.4 dB across three functional states,one-dimensional,two-dimensional,and cross-connected switching,while supporting the routing of 5.85 Tbit/s quadrature phase-shift keying *** results highlight the R-DNN’s effectiveness in achieving precise and controllable OAM mode manipulation,paving the way for advanced applications in mode-multiplexed communication networks and beyond.

关键词： orbital angular momentum mode mode routing diffractive neural network

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：