检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Che, Wang Zheng, Jinhua Hu, Yaru Zou, Juan Yang, Shengxiang Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science School of Cyberspace Science of Xiangtan University Hunan Province Xiangtan China Faculty of School of Computer Science School of Cyberspace Science of Xiangtan University Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Dynamic constrained multi-objective optimization problems (DCMOPs) involve objectives, constraints, and parameters that change over time. This kind of problem presents a greater challenge for evolutionary algorithms because it requires the population to quickly track the changing pareto-optimal set (PS) while being subject to constrained limitations and maintaining a good distribution of solutions. This paper proposes a dynamic constrained multi-objective optimization algorithm based on co-evolution and diversity enhancement (CEDE). The static optimization part involves the co-evolution of three populations. We evolve the first population to prioritize the preservation of feasible individuals. The second population is evolved to assist the first population in finding better feasible regions, while the third population is evolved to aid the first population in exploring feasible regions comprehensively. At different stages, the co-evolution of these three populations will also be adjusted. Additionally, to prevent the elimination of potentially valuable infeasible individuals due to pareto domination, we employ an archive set to store and update these individuals. When the environment changes, we propose a diversity enhancement strategy, which includes a diversity maintenance strategy and a center point-based exploration strategy. The experimental results demonstrate that CEDE is highly competitive in handling DCMOPs compared to several state-of-the-art algorithms. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Dynamic Constrained Multi-Objective Optimization Algorithm Based on Co-Evolution and Diversity Enhancement

SSRN

引用

SSRN 2024年

Dynamic constrained multi-objective optimization problems (DCMOPs) involve objectives, constraints, and parameters that change over time. This kind of problem presents a greater challenge for evolutionary algorithms because it requires the population to quickly track the changing pareto-optimal set (PS) while being subject to constrained limitations and maintaining a good distribution of solutions. This paper proposes a dynamic constrained multi-objective optimization algorithm based on co-evolution and diversity enhancement (CEDE). The static optimization involves the co-evolution of three populations. We evolve the first population to prioritize the preservation of feasible individuals. The second population is evolved to assist the first population in finding better feasible regions, while the third population is evolved to aid the first population in exploring feasible regions comprehensively. At different stages, the co-evolution of these three populations will also be adjusted. Additionally, to prevent the elimination of potentially valuable infeasible individuals due to pareto domination, we employ an archive set to store and update these individuals, providing more useful information for both static and dynamic optimization. When the environment changes, we propose a diversity enhancement strategy, which includes a diversity maintenance strategy and a center point-based exploration strategy. The experimental results demonstrate that CEDE is highly competitive in handling DCMOPs compared to several state-of-the-art algorithms. © 2024, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Weak Relationship Indicator-Based Evolutionary Algorithm for Multimodal Multi-Objective Optimization

SSRN

引用

SSRN 2023年

作者： Xiang, Yi Zheng, Jinhua Hu, Yaru Liu, Yuan Zou, Juan Deng, Qi Yang, Shengxiang Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Computer Science School of Cyberspace Science of Xiangtan University Hunan Province Xiangtan China Faculty of School of Computer Science School of Cyberspace Science of Xiangtan University Xiangtan411105 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Multimodal multi-objective problems (MMOPs) refer to multiple equivalent Pareto sets (PSs) that can be mapped to the same Pareto optimal front (PF) and have widespread applications in real life. Traditional multimodal multiobjective algorithms (MMEAs) use strong relationships (such as global domination relationships and global indicators) to guide population convergence. This may lead to two problems: first, when there are PSs with different search difficulties, the population will tend to explore the easier-to-search PSs and lose the more difficult-to-search PSs. Second, it cannot retain local PSs well (slightly worse in the objective space but far apart in the decision space). To address these issues, we propose a weak relationship indicator-based MMEA that includes weak convergence indicators and density evaluation indicators. The weak convergence indicator considers the relationship between an individual and a certain number of its neighbors. The density evaluation indicator comprehensively considers the density information of the individual and its neighbors. This allows the population to retain solutions from different PSs during exploration, even local PSs. In addition, an archive based on weak convergence indicators also retains excellent solutions generated during the evolution of the population. Experimental results show that our algo-rithm has higher competitive performance than seven other state-of-the-art MMEAs on chosen benchmark problems. © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

IF2Net: Innately Forgetting-Free Networks for Continual Learning

arXiv

引用

arXiv 2023年

作者： Li, Depeng Wang, Tianqi Xu, Bingrong Kawaguchi, Kenji Zeng, Zhigang Suganthan, Ponnuthurai Nagaratnam The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China The School of Automation Wuhan University of Technology Wuhan430070 China The School of Computing National University of Singapore 117417 Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore The KINDI Center for Computing Research College of Engineering Qatar University Doha Qatar

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated how to design an Innately Forgetting-Free Network (IF2Net) for continual learning context. This study proposed a straightforward yet effective learning paradigm by ingeniously keeping the weights relative to each seen task untouched before and after learning a new task. We first presented the novel representation-level learning on task sequences with random weights. This technique refers to tweaking the drifted representations caused by randomization back to their separate task-optimal working states, but the involved weights are frozen and reused (opposite to well-known layer-wise updates of weights). Then, sequential decision-making without forgetting can be achieved by projecting the output weight updates into the parsimonious orthogonal space, making the adaptations not disturb old knowledge while maintaining model plasticity. IF2Net allows a single network to inherently learn unlimited mapping rules without telling task identities at test time by integrating the respective strengths of randomization and orthogonalization. We validated the effectiveness of our approach in the extensive theoretical analysis and empirical study. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Detection of Deepfake videos using long distance attention

arXiv

引用

arXiv 2021年

作者： Lu, Wei Liu, Lingyi Luo, Junwei Zhao, Xianfeng Zhou, Yicong Huang, Jiwu School of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100195 China School of Cyber Security University of Chinese Academy of Sciences Beijing100195 China Department of Computer and Information Science University of Macau 999078 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video contents and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this paper, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and inter-frame inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively. The two components are designed using a novel long distance attention mechanism. The one component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves the state-of-the-art performance, and the proposed long distance attention method can effectively capture pivotal parts for face forgery. Copyright © 2021, The Authors. All rights reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Butson Hadamard matrices, bent sequences, and spherical codes

arXiv

引用

arXiv 2023年

作者： Shi, Minjia Lu, Danni Armario, Andrés Egan, Ronan Ozbudak, Ferruh Solé, Patrick The Key Laboratory of Intelligent Computing Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China State Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China Departamento de Matemática Aplicada I Universidad de Sevilla Avda. Reina Mercedes s/n Seville41012 Spain School of Mathematical Sciences Dublin City University Ireland Faculty of Engineering and Natural Sciences Sabancı University Istanbul34956 Turkey I2M Aix Marseille Univ CNRS Centrale Marseille Marseilles France

We explore a notion of bent sequence attached to the data consisting of an Hadamard matrix of order n defined over the complex qth roots of unity, an eigenvalue of that matrix, and a Galois automorphism from the cyclotomic field of order q. In particular we construct self-dual bent sequences for various q ≤ 60 and lengths n ≤ 21. Computational construction methods comprise the resolution of polynomial systems by Groebner bases and eigenspace computations. Infinite families can be constructed from regular Hadamard matrices, Bush-type Hadamard matrices, and generalized Boolean bent functions. As an application, we estimate the covering radius of the code attached to that matrix over Zq. We derive a lower bound on that quantity for the Chinese Euclidean metric when bent sequences exist. We give the Euclidean distance spectrum, and bound above the covering radius of an attached spherical code, depending on its strength as a spherical design. © 2023, CC BY.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

The improved Hagedorn wavepacket method for semiclassical Schrödinger equation

引用

International Journal of Modeling, Simulation, and Scientific computing 2014年第4期5卷

作者： Xueyang Li Aiguo Xiao Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan P. R. China

The Hagedorn wavepacket method is an important numerical method for solving the semiclassical time-dependent Schrödinger equation. In this paper, a new semi-discretization in space is obtained by wavepacket operator. In a sense, such semi-discretization is equivalent to the Hagedorn wavepacket method, but this discretization is more intuitive to show the advantages of wavepacket methods. Moreover, we apply the multi-time-step method and the Magnus-expansion to obtain the improved algorithms in time-stepping computation. The improved algorithms are of the Gauss–Hermite spectral accuracy to approximate the analytical solution of the semiclassical Schrödinger equation. And for the given accuracy, the larger time stepsize can be used for the higher oscillation in the semiclassical Schrödinger equation. The superiority is shown by the error estimation and numerical experiments.

关键词： High oscillation semiclassical Schrödinger equation Hagedorn wavepacket multi-time-step method Magnus-expansion

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Virtual Machine Placement in Data Centers Via Accelerated Genetic Algorithm with Improved Fitness Computation

SSRN

引用

SSRN 2021年

作者： Hormozi, Elham Hu, Shuwen Ding, Zhe Tian, Yu-Chu Wang, You-Gan Yu, Zu-Guo Zhang, Weizhe School of Computer Science Queensland University of Technology GPO Box 2434 BrisbaneQLD4001 Australia School of Mathematical Sciences Queensland University of Technology GPO Box 2434 BrisbaneQLD4001 Australia Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan Xiangtan411105 China School of Cyberspace Science Harbin Institute of Technology Harbin China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China Queensland University of Technology

Energy efficiency basically refers to how effectively energy can be utilised or consumed by any virtualised data centre giving cloud administrations. Since Genetic Algorithm (GA) is an acceptable method to solve the VM placement problem, this research formulates the Virtual Machine (VM) placement problem as a constrained optimisation problem. A considerable amount of residual resources is available for each new VM allocation, however they are distributed across multiple active PMs, rendering them inefficient. Our research focuses on improving a data centre’s energy and time efficiency by devising a technique to decrease PM’s residual resources and make them more valuable. As the most time consuming element of a GA is calculating the fitness function, this paper presents a new fitness function to simplify the fitness function calculation in GA. The results are compared to the standard GA and First Fit Decreasing (FFD) algorithm. The findings reveals a 8% energy savings for our GA compared to FFD and a 66% reduction in our GA execution time compared to the standard GA for virtualised data centres. The simulation experiments are conducted on small-, medium- and large-scale of the google data centre to demonstrate the effectiveness of our GA. © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction

arXiv

引用

arXiv 2023年

作者： Fan, Xiaohong Yang, Yin Chen, Ke Feng, Yujie Zhang, Jianping The School of Mathematics and Computational Science Xiangtan University Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Xiangtan411105 China The Centre for Mathematical ImagingTechniques Department of Mathematical Sciences The University of Liverpool Department of Mathematics and Statistics University of Strathclyde Glasgow United Kingdom The School of Mathematics and Computational Science Xiangtan University The Key Laboratory of Intelligent Computing & Information Processing The Ministry of Education Xiangtan411105 China

Proximal gradient-based optimization is one of the most common strategies to solve inverse problem of images, and it is easy to implement. However, these techniques often generate heavy artifacts in image reconstruction. One of the most popular refinement methods is to fine-tune the regularization parameter to alleviate such artifacts, but it may not always be sufficient or applicable due to increased computational costs. In this work, we propose a deep geometric incremental learning framework based on the second Nesterov proximal gradient optimization. The proposed end-to-end network not only has the powerful learning ability for high-/low-frequency image features, but also can theoretically guarantee that geometric texture details will be reconstructed from preliminary linear reconstruction. Furthermore, it can avoid the risk of intermediate reconstruction results falling outside the geometric decomposition domains and achieve fast convergence. Our reconstruction framework is decomposed into four modules including general linear reconstruction, cascade geometric incremental restoration, Nesterov acceleration, and post-processing. In the image restoration step, a cascade geometric incremental learning module is designed to compensate for missing texture information from different geometric spectral decomposition domains. Inspired by the overlap-tile strategy, we also develop a post-processing module to remove the block effect in patch-wise-based natural image reconstruction. All parameters in the proposed model are learnable, an adaptive initialization technique of physical parameters is also employed to make model flexibility and ensure converging smoothly. We compare the reconstruction performance of the proposed method with existing state-of-the-art methods to demonstrate its superiority. Our source codes are available at https://***/fanxiaohong/Nest-DGIL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

MVMS-RCN: A Dual-Domain Unified CT Reconstruction with Multi-sparse-view and Multi-scale Refinement-correction

arXiv

引用

arXiv 2024年

作者： Fan, Xiaohong Chen, Ke Yi, Huaming Yang, Yin Zhang, Jianping The School of Mathematics and Computational Science Xiangtan University Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan411105 China The Centre for Mathematical Imaging Techniques Department of Mathematical Sciences The University of Liverpool LiverpoolL6972L United Kingdom The School of Mathematics and Computational Science Xiangtan University Hunan National Applied Mathematics Center Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan411105 China

X-ray Computed Tomography (CT) is one of the most important diagnostic imaging techniques in clinical applications. Sparse-view CT imaging reduces the number of projection views to a lower radiation dose and alleviates the potential risk of radiation exposure. Most existing deep learning (DL) and deep unfolding sparse-view CT reconstruction methods: 1) do not fully use the projection data;2) do not always link their architecture designs to a mathematical theory;3) do not flexibly deal with multi-sparse-view reconstruction assignments. This paper aims to use mathematical ideas and design optimal DL imaging algorithms for sparse-view CT reconstructions. We propose a novel dual-domain unified framework that offers a great deal of flexibility for multi-sparse-view CT reconstruction through a single model. This framework combines the theoretical advantages of model-based methods with the superior reconstruction performance of DL-based methods, resulting in the expected generalizability of DL. We propose a refinement module that utilizes unfolding projection domain to refine full-sparse-view projection errors, as well as an image domain correction module that distills multi-scale geometric error corrections to reconstruct sparse-view CT. This provides us with a new way to explore the potential of projection information and a new perspective on designing network architectures. The multi-scale geometric correction module is end-to-end learnable, and our method could function as a plug-and-play reconstruction technique, adaptable to various applications. Extensive experiments demonstrate that our framework is superior to other existing state-of-the-art methods. Our source codes are available at https://***/fanxiaohong/MVMS-RCN. Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

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：