检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Tang, Zhuorui Zhao, ShiBo Wang, Gang Li, Jian Tang, Hongyu Fan, Jiajie Zhang, Guoqi Institute of Wide Bandgap Semiconductors and Future Lighting Academy for Engineering & Technology Fudan University Shanghai200433 China Shanghai Research Center for Silicon Carbide Power Devices Engineering & Technology Fudan University Shanghai200433 China College of Software Northeastern University Shenyang110819 China Technology Innovation Institute of Jilin Province Changchun130000 China State Key Laboratory of Optoelectronic Materials and Technologies Sun Yat-sen University Guangzhou510275 China School of AI–Guangdong & Taiwan Foshan University Foshan528225 China EEMCS Faculty Delft University of Technology Delft2628 Netherlands

This study aims to develop a 3D multi-physics model combined with a machine learning algorithm and experiments to optimize the CVD process of the 4H-SiC epitaxial layer. Firstly, a 3D CFD model was developed to calculate the deposition rate and uniformity of the epitaxial layer in a horizontal hot-wall chemical vapor reactor by coupling with multi-physics models, such as fluid flow, heat and mass transfer, and chemical reactions. An experiment was performed to validate the feasibility of the numerical model. Secondly, single-factor analysis was conducted to investigate the effects of process parameters, including the deposition temperature, inlet-flow volume, rotational speed of susceptor, and cavity pressure, on the quality of 4H-SiC epitaxial layer. Finally, a machine learning algorithm, the ant colony optimization-back propagation neural network (ACO–BPNN), was employed to develop the input/output model and optimize process parameters for obtaining high quality epitaxial layer and reducing the optimization cycle and costs. Notably, the optimized process was validated by real experiments, where the error between calculation and experiment is 4.2% for growth rate and 0.294% for coefficient of variation, respectively. The results highlight the model as reliable and lay the foundation for the CVD growth of 4H-SiC epitaxial layer. © 2024, The Authors. All rights reserved.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

A bit error rate optimization method for wsn node energy consumption 2nd

A bit error rate optimization method for wsn node energy con...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： He, Miao Cheng, Shen-shen Ma, Tian-yi Lv, Shi School of Computer and Software Nanjing Institute of Information Technology NanjingJiangsu210043 China School of Energy and Power Engineering Nanjing University of Science and Technology NanjingJiangsu210094 China

ISBN: (纸本)9789811561122

In order to reduce the energy consumption of nodes and prolong the lifetime of indoor wireless sensor network nodes, it is necessary to establish an optimal bit error rate model under multiple indoor influencing factors so as to maximize the efficiency of receiving and receiving signals. Based on the researching of relationship between indoor factors such as wall and floor reflection, obstacle shadow fading, channel error rate and energy consumption of node signal transceiver and receiver, the energy consumption model of node single frame transmission is given, it is also proved that there exists an optimal bit error rate to minimize the energy consumption of nodes under the condition of co-channel coding. Finally, the simulation experiments are carried out to further analyze and verify the energy consumption of node. The results show that even if the indoor signal interference factors are complex, the minimum energy consumption of receiving and receiving nodes can be found by optimizing the bit error rate adjustment, which shows that the optimization model has engineering application value. © Springer Nature Singapore Pte Ltd 2020.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Multi-Feature Fusion based Image Steganography using GAN

Multi-Feature Fusion based Image Steganography using GAN

引用

IEEE International Conference on software Reliability engineering Workshops (ISSRE Wksp)

作者： Zhen Wang Zhen Zhang Jianhui Jiang School of Computer Science and Technology Shanghai University of Electric Power Shanghai China School of Software Engineering Tongji University Shanghai China

ISBN: (纸本)9781665426046

In order to solve the problem of information loss, some image steganography methods utilize generative adversarial networks (GANs), while the existing methods can not capture both texture information and semantic features. In this paper, a more accurate image steganography method is proposed, where a multi-level feature fusion procedure based on GAN is designed. Firstly, convolution and pooling operations are added to the network for feature extraction. Then, short links are used to fuse multi-level feature information. Finally, the stego image is generated by confrontation learning between discriminator and generator. Experimental results show that the proposed method has higher steganalysis security under the detection of high-dimensional feature steganalysis and neural network steganalysis. Comprehensive experiments show that the performance of the proposed method is better than ASDL-GAN and UT-GAN.

关键词： Training Steganography Fuses Semantics Neural networks Generative adversarial networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

arXiv

引用

arXiv 2024年

作者： Sun, Li Huang, Zhenhao Wu, Hua Ye, Junda Peng, Hao Yu, Zhengtao Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois ChicagoIL United States

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Revisit Raft Consistency Protocol on Private Blockchain System in High Network Latency 7th

Revisit Raft Consistency Protocol on Private Blockchain Syst...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Cao, Ning Jiang, Dianheng Liu, Yang Zhou, Yulan Du, Haiwen Qiao, Xueming Xia, Yingxue Zhu, Dongjie Yu, Fang Bi, Wenbin College of Information Engineering Sanming University Sanming365000 China School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China School of Astronautics Harbin Institute of Technology Harbin150001 China State Grid Weihai Power Supply Company No. 23 Kunming Road Weihai264200 China College of Information Engineering Qingdao Binhai University Qingdao266555 China Department of Internet of Things Engineering School of Computer and Software Dalian Neusoft University of Information Dalian116033 China

ISBN: (纸本)9783030786175

Raft’s good performance in the CFT system makes it a mainstream implementation solution for the consistency of the private chain system. However, we found in practice that Raft’s performance degradation is very serious when the network latency is greater than 1 ms. Therefore, we simulated the blockchain network environment and tested the TPS performance of Raft and Multi-raft. The results show that when the TPS is the same, Multi-raft reduces network traffic by 30% compared with Raft’s leader, and the CPU load increases slightly. Based on the experimental results, we discussed the optimization scheme of Raft on the geographically distributed system, and provided ideas for future research. © 2021, Springer Nature Switzerland AG.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

WEM: A node importance algorithm in weighted networks

arXiv

引用

arXiv 2021年

作者： Chen, Linjie Zhao, Na Li, Jie Long, Zhen Jing, Ming Wang, Jian Key Laboratory in Software Engineering of Yunnan Province School of Software Yunnan University Kunming650091 China Electric Power Research Institute of Yunnan Power Grid Kunming650217 China College of Information Engineering and Automation Kunming University of Science and Technology Kunming650504 China

In view of the node importance in weighted networks, weighted expected method (WEM), was proposed in this paper, which take an advantages of uncertain graph algorithm. First, a weight processing method is proposed based on the relationship between the weight of edges and the intensity of contact between nodes, and the calculation method of the contribution of the weight of edges to the node importance is defined, even if there are two converse situations in the reality. Then, because of the use of dynamic programming method, which reduces the complexity of computational time to a linear level, WEM will be more suitable for the calculation in large weighted networks. Owning to its features of calculating, WEM can, to the greatest extent, ensure a precise order of node essential scores for each node. The node connectivity experiment and SIR simulation experiment show that the WEM has higher accuracy and relatively low time complexity. © 2021, CC BY.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Resource Optimization for LEO Constellation Networks: A Multi-satellite Cooperative Coverage Design

引用

IEEE Transactions on Communications 2025年

作者： Ma, Xu Zhang, Haijun Song, Wei Lu, Yang Wu, Yuan Leung, Victor C.M University of Science and Technology Beijing Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Beijing100083 China China Electric Power Research Institute Co. Ltd Beijing102209 China University of Macau State Key Laboratory of Internet of Things for Smart City Macau China University of Macau Department of Computer and Information Science Macau China Shenzhen University Department of Computer Science and Software Engineering Shenzhen518061 China

With its low latency, high throughput, good deployment flexibility, and cost-effectiveness, the low earth orbit (LEO) constellation is regarded as a promising technology for seamless coverage. Unlike geosynchronous orbiting (GSO) satellites, the highly dynamic evolution of LEO constellation topology poses a significant challenge to the traditional scheme of allocating wireless resources. This paper proposes a multisatellite cooperative coverage resource allocation for the LEO constellation. A multi-objective optimization problem focusing on throughput and coverage time is proposed for the overall service quality of the LEO constellation. To solve the complex coupling between multi-domain resources, the optimization problem is decomposed into three key subproblems, which are the beam placement problem, the joint beam association with power allocation problem, and the beam hopping time slot allocation problem. For each subproblem, an adaptive algorithm is proposed that effectively exploits the payload of LEO satellites to ensure the coverage performance of the constellation network. Simulation results demonstrate that the proposed coverage scheme enables fast convergence, enhances network throughput utility, and guarantees the stability and fairness of the communication services. © 1972-2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Localized collocation schemes and their applications

引用

Acta Mechanica Sinica 2022年第7期38卷 1-28,I0002页

作者： Zhuojia Fu Zhuochao Tang Qiang Xi Qingguo Liu Yan Gu Fajie Wang Key Laboratory of Ministry of Education for Coastal Disaster and Protection Hohai UniversityNanjing210098China Center for Numerical Simulation Software in Engineering and Sciences College of Mechanics and MaterialsHohai UniversityNanjing211100China Department of Fluid Dynamics and Thermodynamics Faculty of Mechanical EngineeringUniversity of LjubljanaLjubljana1000Slovenia Laboratory for Simulation of Materials and Processes Institute of Metals and TechnologyLjubljana1000Slovenia School of Mathematics and Statistics Qingdao UniversityQingdaoShandong266071China College of Mechanical and Electrical Engineering National Engineering Research Center for Intelligent Electrical Vehicle Power SystemQingdao UniversityQingdao266071China

This paper presents a summary of various localized collocation schemes and their engineering *** basic concepts of localized collocation methods(LCMs)are first introduced,such as approximation theory,semianalytical collocation methods and localization *** on these basic concepts,five different formulations of localized collocation methods are introduced,including the localized radial basis function collocation method(LRBFCM)and the generalized finite difference method(GFDM),the localized method of fundamental solutions(LMFS),the localized radial Trefftz collocation method(LRTCM),and the localized collocation Trefftz method(LCTM).Then,several additional schemes,such as the generalized reciprocity method,Laplace and Fourier transformations,and Krylov deferred correction,are introduced to enable the application of the LCM to large-scale engineering and scientific computing for solving inhomogeneous,nonisotropic and time-dependent partial differential *** typical benchmark examples are presented to show the recent developments and applications on the LCM solution of some selected boundary value problems,such as numerical wave flume,potential-based inverse electrocardiography,wave propagation analysis and 2D phononic crystals,elasticity and in-plane crack problems,heat conduction problems in heterogeneous material and nonlinear time-dependent Burgers’***,some conclusions and outlooks of the LCMs are summarized.

关键词： Localization Collocation method Semianalytical Computational mechanics

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Infrastructure for Artificial Intelligence with Quantum Resistant 4

Blockchain-Based Infrastructure for Artificial Intelligence ...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Yuan, Bo Wu, Faguo Qiu, Wangjie Wang, Wendi Zhu, Hong Zhou, Dongxu School of Computer Science and Engineering State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Research Institute for Frontier Science Beihang University Beijing China Suzhou Honglian Information Technology Co. Ltd Research and Development Department Suzhou215000 China State Grid Jiangsu Electric Power CO. Ltd. Nanjing Power Supply Company Technology and Internet Department Nanjing210019 China

ISBN: (纸本)9780738131702

It is undeniable that the concepts of artificial intelligence and blockchain are spreading at an alarming speed. These two technologies have different degrees of technical complexity and multi-dimensional business meaning. The convergence of artificial intelligence and blockchain holds the promise of creating smarter, safer, efficient, and more secure systems. However, with the surprising development of quantum technology, most existing blockchain systems are vulnerable to quantum attacks. In this paper, we accordingly propose a lattice-based blockchain infrastructure for artificial intelligence with quantum resistant, aiming at tackling the critical issue of throughput, our infrastructure based on lattice-based aggregate signature which can effectively the proportion of signatures in block size. The proposed scheme can be proved secure in random oracle model, and it is also more efficient than similar literatures. In addition, we also give the detailed description of the post-quantum blockchain transaction. Furthermore, this work can help to enrich the research on the future post-quantum blockchain (PQB). © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Integrated AI Medical Diagnosis Application Based on Deep Learning

An Integrated AI Medical Diagnosis Application Based on Deep...

引用

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Haoyang Li Xiaoyang Li Bolin Shen Zhi Zheng Computer Science School of Information Science and Technology Chengdu University of Technology CDUT Chengdu China Software engineering School of Information Science Beijing University of Technology BJUT Beijing China School of Control and Computer Engineering North China Electric Power University Baoding China Software engineering Beijing University of Technology BDIC Beijing China

ISBN: (纸本)9781665412971

AI medical diagnosis has become an easy and effective approach method by which patients could get their health reports faster. This paper introduced an integrated AI medical diagnosis application with an image recognition system, chat system, and user interface. With the powerful help of the Convolutional Neural Network (CNN), an accurate image diagnosis system for breast cancer is ready to use. The chat system provides a bond between AI and patients through communication, using the Q&A sub-system based on Knowledge Graph (KG) and the casual chat sub-system based on Natural Language Process (NLP). Health condition query and common converse are satisfied respectively by Q&A sub-system and casual chat sub-system. Depending on the user’s intentional probability of medical problems, the casual chat system will interfere if the user’s intention is not matched in Knowledge Graph. Besides the deep learning part to process patient’s data, an easy-to-use user interface is also designed to guide people getting intended information, using Flask framework to offer API and jQuery to send a request. Our accuracy achieves 0.88 in breast cancer detection, and the result of GradCAM indicates the CNN network has a high performance on such a task. The practical experiment shows that the patient’s intention can proceed well in the chat system and that application can provide people advantageous feedback according to their health condition.

关键词： Deep learning Seminars Image recognition Natural languages User interfaces Breast cancer Medical diagnosis

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：