检索结果-南通市图书馆

Review of GAN-Based Research on Chinese Character Font Generation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第3期33卷 584-600页

作者： Xuanhong WANG Cong Li Zengguo SUN Luying HUi Xi'an University of Posts and Telecommunications School of Computer Science Shaanxi Normal University Key Laboratory of intelligent computing and Service Technology for Folk Song Ministry of Culture and Tourism

With the rapid development of deep learning,generative adversarial network(GAN) has become a research hotspot in the field of computer *** has a wide range of applications in image *** by GAN,a series of models of Chinese character font generation have been proposed in recent *** this paper,the latest research progress of Chinese character font generation is analyzed and *** and its development history are ***-based methods for Chinese character font generation are clarified as well as their improvements,based on whether the specific elements of Chinese characters are *** public datasets used for font generation are summarized in detail,and various application scenarios of font generation are *** evaluation metrics of font generation are systematically summarized from both qualitative and quantitative *** paper contributes to the in-depth research on Chinese character font generation and has a positive effect on the inheritance and development of Chinese culture with Chinese characters as its carrier.

关键词： Generative adversarial network Font generation image-to-image translation Deep learning

Stabilization and Blow-up in an infinite Memory Wave Equation with Logarithmic Nonlinearity and Acoustic Boundary Conditions

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第4期37卷 1368-1391页

作者： PENG Qingqing ZHANG Zhifei School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific computing Huazhong University of Science and TechnologyWuhan 430074China

in this paper,the authors consider the stabilization and blow up of the wave equation with infinite memory,logarithmic nonlinearity and acoustic boundary *** authors discuss the existence of global solutions for the initial energy less than the depth of the potential well and investigate the energy decay estimates by introducing a Lyapunov ***,the authors establish the finite time blow up results of solutions and give the blow up time with upper bounded initial energy.

关键词： Acoustic boundary condition finite time blow-up general decay infinite memory logarithmic nonlinearity

Spontaneous infection and Periodic Evolving of Domain in a Diffusive SiS Epidemic Model

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2024年第1期40卷 164-191页

作者： Qiang Wen Guo-qiang Ren Bin Liu School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan430074China Hubei Key Laboratory of Engineering Modeling and Scientific computing Huazhong University of Science and TechnologyWuhan430074China

in this paper, we consider a susceptible-infective-susceptible(SiS) reaction-diffusion epidemic model with spontaneous infection and logistic source in a periodically evolving domain. Using the iterative technique,the uniform boundedness of solution is established. in addition, the spatial-temporal risk index R0(ρ) depending on the domain evolution rate ρ(t) as well as its analytical properties are discussed. The monotonicity of R0(ρ)with respect to the diffusion coefficients of the infected di, the spontaneous infection rate η(ρ(t)y) and interval length L is investigated under appropriate conditions. Further, the existence and asymptotic behavior of periodic endemic equilibria are explored by upper and lower solution method. Finally, some numerical simulations are presented to illustrate our analytical results. Our results provide valuable information for disease control and prevention.

关键词： diffusive SiS model spontaneous infection periodically evolving domain periodic endemic equilibrium

Global Optimization for Heilbronn Problem of Convex Polygons Based on Bilinear Matrix inequalities Solving

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年

作者： Qi Niuniu DEHBi Lydia LiU Banglong YANG Zhengfeng ZENG Zhenbing Shanghai Key Laboratory of Trustworthy computing East China Normal University Department of Mathematics Shanghai University

This paper primarily focuses on solving the Heilbronn problem of convex polygons,which involves minimizing the area of a convex polygon P1P2···P_n while satisfying the condition that the areas of all triangles formed by consecutive vertices are equal to 1/*** problem is reformulated as a polynomial optimization problem with a bilinear objective function and bilinear constraints.A new method is presented to verify the upper and lower bounds for the optimization *** upper bound is obtained by the affine regular *** Bilinear Matrix inequalities （BMi） theory and the branch-and-bound technique are used to verify the lower bound of the *** paper concludes by proving that the lower bound for the area minimization problem of a convex polygon with10 vertices is *** relative error compared to the global optimum is 0.104%.

关键词：

More Than Lightening:A Self-Supervised Low-Light image Enhancement Method Capable for Multiple Degradations

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

iEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 622-637页

作者： Han Xu Jiayi Ma Yixuan Yuan Hao Zhang Xin Tian Xiaojie Guo the Electronic information School Wuhan UniversityWuhan 430072China iEEE the Department of Electronic Engineering Chinese University of Hong KongHong Kong 999077China the College of intelligence and computing Tianjin UniversityTianjin 300350China

Low-light images suffer from low quality due to poor lighting conditions,noise pollution,and improper settings of *** enhance low-light images,most existing methods rely on normal-light images for guidance but the collection of suitable normal-light images is *** contrast,a self-supervised method breaks free from the reliance on normal-light data,resulting in more convenience and better *** self-supervised methods primarily focus on illumination adjustment and design pixel-based adjustment methods,resulting in remnants of other degradations,uneven brightness and *** response,this paper proposes a self-supervised enhancement method,termed as *** can handle multiple degradations including illumination attenuation,noise pollution,and color shift,all in a self-supervised *** attenuation is estimated based on physical principles and local neighborhood *** removal and correction of noise and color shift removal are solely realized with noisy images and images with color ***,the comprehensive and fully self-supervised approach can achieve better adaptability and *** is applicable to various low light conditions,and can reproduce the original color of scenes in natural *** experiments conducted on four public datasets demonstrate the superiority of SLiE to thirteen state-of-the-art *** code is available at https://***/hanna-xu/SLiE.

关键词： Color correction low-light image enhancement self-supervised learning.

AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第2期39卷 401-420页

作者：龚成卢冶代素蓉邓倩杜承昆李涛 College of Software Nankai UniversityTianjin 300350China College of Computer Science Nankai UniversityTianjin 300350China State Key Laboratory of Processors Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China

Exploring the expected quantizing scheme with suitable mixed-precision policy is the key to compress deep neural networks(DNNs)in high efficiency and *** exploration implies heavy workloads for domain experts,and an automatic compression method is ***,the huge search space of the automatic method introduces plenty of computing budgets that make the automatic process challenging to be applied in real *** this paper,we propose an end-to-end framework named AutoQNN,for automatically quantizing different layers utilizing different schemes and bitwidths without any human *** can seek desirable quantizing schemes and mixed-precision policies for mainstream DNN models efficiently by involving three techniques:quantizing scheme search(QSS),quantizing precision learning(QPL),and quantized architecture generation(QAG).QSS introduces five quantizing schemes and defines three new schemes as a candidate set for scheme search,and then uses the Differentiable Neural Architecture Search(DNAS)algorithm to seek the layer-or model-desired scheme from the *** is the first method to learn mixed-precision policies by reparameterizing the bitwidths of quantizing schemes,to the best of our *** optimizes both classification loss and precision loss of DNNs efficiently and obtains the relatively optimal mixed-precision model within limited model size and memory *** is designed to convert arbitrary architectures into corresponding quantized ones without manual intervention,to facilitate end-to-end neural network *** have implemented AutoQNN and integrated it into *** experiments demonstrate that AutoQNN can consistently outperform state-of-the-art *** 2-bit weight and activation of AlexNet and ResNet18,AutoQNN can achieve the accuracy results of 59.75%and 68.86%,respectively,and obtain accuracy improvements by up to 1.65%and 1.74%,respectively,compared with state-of-the-art ***,c

关键词： automatic quantization mixed precision quantizing scheme search quantizing precision learning quan-tized architecture generation

Secure control and filtering for industrial metaverse

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of information Technology & Electronic Engineering 2024年第2期25卷 179-181页

作者： Qing-Long HAN Derui DiNG Xiaohua GE School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia Department of Control Science and Engineering University of Shanghai for Science and TechnologyShanghai 200093China

Metaverse can be regarded as a socialized and virtualized cyberspace parallel yet interactive to the real *** from the rapid development of cloud computing and digital twins,metaverse is transforming traditional control and filtering para‐digms of industrial automation systems into cyberphysical social *** this scenario,future industrial automation systems could be an integration of real-world ones and virtual twins combined with great computational power within a certain temporal and spatial range.

关键词： interactive filtering Secure

A TRUST-REGiON METHOD FOR SOLViNG TRUNCATED COMPLEX SiNGULAR VALUE DECOMPOSiTiON

在线全文

学校读者我要写书评

暂无评论

Journal of Computational Mathematics 2024年第4期42卷 999-1031页

作者： Jiaofen Li Lingchang Kong Xuefeng Duan Xuelin Zhou Qilun Luo School of Mathematics and computing Science Guangxi Colleges and Universities Key Laboratory of Data Analysis and ComputationGuangxi Key Laboratory of Automatic Detecting Technology and InstrumentsGuilin University of Electronic TechnologyCenter for Applied Mathematics of Guangxi(GUET)Guilin 541004China School of Mathematical Sciences South China Normal UniversityGuangzhou 510000China School of Mathematics and computing Science Guilin University of Electronic TechnologyGuilin 541004China School of Mathematics and computing Science Guangxi Colleges and Universities Key Laboratory of Data Analysis and ComputationGuilin University of Electronic TechnologyCenter for Applied Mathematics of Guangxi(GUET)Guilin 541004China School of Mathematics and Statistics Yunan UniversityKunming 650000China

The truncated singular value decomposition has been widely used in many areas of science including engineering,and statistics,*** this paper,the original truncated complex singular value decomposition problem is formulated as a Riemannian optimiza-tion problem on a product of two complex Stiefel manifolds,a practical algorithm based on the generic Riemannian trust-region method of Absil et *** presented to solve the underlying problem,which enjoys the global convergence and local superlinear conver-gence *** experiments are provided to illustrate the efficiency of the proposed *** with some classical Riemannian gradient-type methods,the existing Riemannian version of limited-memory BFGS algorithms in the MATLAB toolbox Manopt and the Riemannian manifold optimization library ROPTLiB,and some latest infeasible methods for solving manifold optimization problems,are also provided to show the merits of the proposed approach.

关键词： Truncated singular value decomposition Riemannian optimization Trust-region method

Multi-Smart Meter Data Encryption Scheme Basedon Distributed Differential Privacy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 131-141页

作者： Renwu Yan Yang Zheng Ning Yu Cen Liang School of Electronic Electrical Engineering and PhysicsFujian University of TechnologyFuzhou 350118China Department of computing Sciences at The College at Brockport State University of New YorkNew YorkNY 14420USA

Under the general trend of the rapid development of smart grids,data security and privacy are facing serious challenges;protecting the privacy data of single users under the premise of obtaining user-aggregated data has attracted widespread *** this study,we propose an encryption scheme on the basis of differential privacy for the problem of user privacy leakage when aggregating data from multiple smart ***,we use an improved homomorphic encryption method to realize the encryption aggregation of users’***,we propose a double-blind noise addition protocol to generate distributed noise through interaction between users and a cloud platform to prevent semi-honest participants from stealing data by colluding with one ***,the simulation results show that the proposed scheme can encrypt the transmission of multi-intelligent meter data under the premise of satisfying the differential privacy *** if an attacker has enough background knowledge,the security of the electricity information of one another can be ensured.

关键词： smart grid homomorphic encryption data aggregation differential privacy cloud computing