检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Towards Optimization of Replicated Erasure Codes for Efficient Cooperative Repair in Cloud Storage

Towards Optimization of Replicated Erasure Codes for Efficie...

引用

第10届全国计算机支持的协同工作学术会议暨中国计算机学会协同计算专委年度工作会议

作者： Guangping Xu Huan Li Xing Guo Sheng Lin Qunfang Mao Hua Zhang Tianjin Key Lab. of Intelligence Computing and New Software Technology Tianjin University of TechnologyTianjinChina 300384

In cloud storage,various erasure coding techniques,particularly regenerating codes,not only need to ensure the multi-node fault tolerance,but also need to reduce bandwidth consumption during storage repair to cope with frequent failures of storage *** paper studies the optimization of replicated erasure codes in cloud storage by using a variant of balls-inbins *** network bandwidth is much valuable,such replicated coding scheme supplies the efficient fault repair by cooperation of parts of storage *** that a set of balls of n different colored are thrown into m distinguishable bins such that ball number of each color is the same and the number of balls in each bins is the *** that here the same color balls are also *** can we ensure the number of balls with distinct colors is at least c in any k bins(k ≤ m)with the minimum number of balls? Considering that balls correspond to coded packets and bins correspond to storage nodes,we present that the optimal colored bins in bins is equivalent to the optimization design of fractional repetition codes in cloud storage *** optimal repetition code can be described by a biregualr graph and then this problem deduced to the Zarankiewicz *** can optimize the storage capacity of an FR code with the required k fault-tolerance from the Ks,t-free structure of a biregular ***,constructions of the optimized codes by 2-desings are analyzed to tolerate the desired k fault-tolerance with c = n-1.

关键词：

来源：评论

学校读者我要写书评

暂无评论

newBalance: Efficient data space management and algorithmic optimization for cloud storage

NewBalance: Efficient data space management and algorithmic ...

引用

第10届全国计算机支持的协同工作学术会议暨中国计算机学会协同计算专委年度工作会议

作者： Guangping Xu Sheng Lin Xing Guo Kai Shi Hua Zhang Tianjin Key Lab. of Intelligence Computing and New Software Technology Tianjin University of TechnologyTianjinChina 300384

Fragmentation usually occurs when data space of original storage nodes has to be reallocated to new added storage nodes during the scale-out evolution of the large-scale storage *** greatly influences the performance of the large-scale storage *** this paper,we present an efficient space management framework,called newBalance,to reduce fragmentation with the minimum data movement while keeping the storage system load *** space management framework has two phases including the collection phase and the allocation *** the collection phase,we propose a novel algorithm,called the greedy bi-direction collector,which collects enough space for the new storage *** the allocation phase,we formally represent it as one variant of the bin packing problem and then utilize some bin packing heuristics including the first fitting and the best fitting to allocate collected intervals to new added storage *** experimental results show that the amount of intervals can be reduced by 20%~55%and our algorithmic optimization improves the data lookup performance by at least 10%and the scale-out performance by 2×~3×.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Irregular community discovery for cloud service improvement

Irregular community discovery for cloud service improvement

引用

作者： Liu, Jin Zhou, Jing Wang, Junfeng Zhang, Feng Liu, Fei State Key Lab. of Software Engineering Wuhan University Wuhan 430072 China Lab. of Complex Systems and Intelligence Science Institute of Automation CAS Beijing 100190 China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Computer Science Communication University of China Beijing 100024 China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Beijing 100190 China College of Computer Science Sichuan University Chengdu 610064 China Software School Sun Yat-sen University Guangzhou 510006 China

Utility services provided by cloud computing rely on virtual customer communities forming spontaneously and evolving continuously. Clarifying the explicit boundaries of these communities is thus essential to the quality of utility services in cloud computing. Communities with overlapping features or prominent peripheral vertexes are usually typical irregular communities. Traditional community identification algorithms are limited in discovering irregular topological structures from CR networks, whereas these irregular shapes typically play an important role in finding prominent customers which are ignored in social CRM otherwise. We present a novel method of discovering irregular communities. It firstly finds and merges primitive maximal cliques and the irregular features of overlapping and prominent sparse vertices are further considered. An empirical case and a methodology comparison confirm the feasibility and efficiency of our approach. © 2012 Springer Science+Business Media, LLC.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

No-go theorem for one-way quantum computing on naturally occurring two-level systems

引用

Physical Review A 2011年第5期83卷 050301(R)-050301(R)页

作者： Jianxin Chen Xie Chen Runyao Duan Zhengfeng Ji Bei Zeng Department of Computer Science and Technology Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China Department of Physics Massachusetts Institute of Technology Cambridge Massachusetts USA Centre for Quantum Computation and Intelligent Systems (QCIS) Faculty of Engineering and Information Technology University of Technology Sydney New South Wales Australia Perimeter Institute for Theoretical Physics Waterloo Ontario Canada State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Institute for Quantum Computing and Department of Combinatorics and Optimization University of Waterloo Waterloo Ontario Canada

The ground states of some many-body quantum systems can serve as resource states for the one-way quantum computing model, achieving the full power of quantum computation. Such resource states are found, for example, in spin-52 and spin-32 systems. It is, of course, desirable to have a natural resource state in a spin-12, that is, qubit system. Here, we give a negative answer to this question for frustration-free systems with two-body interactions. In fact, it is shown to be impossible for any genuinely entangled qubit state to be a nondegenerate ground state of any two-body frustration-free Hamiltonian. What is more, we also prove that every spin-12 frustration-free Hamiltonian with two-body interaction always has a ground state that is a product of single- or two-qubit states. In other words, there cannot be any interesting entanglement features in the ground state of such a qubit Hamiltonian.

关键词： QUANTUM computers QUANTUM theory HAMILTONIAN operator HAMILTONIAN systems PHYSICS

来源：评论

学校读者我要写书评

暂无评论

Design of Robot Lawn Mower based on Computer Vision

Design of Robot Lawn Mower based on Computer Vision

引用

The 2013 2nd International Symposium on Manufacturing Systems Engineering(ISMSE 2013)

作者： Fayu Wang Zhenli Gao Hongyu Yin Key Laboratory of Computer Vision and System(TUT) Ministry of Education Tianjin University of Technology Tianjin Key Lab of Intelligent Computing & Novel Software Technology Tianjin University of Technology

In this paper, we introduce a new research about mowing robot on obstacle avoidance and path tracking controlling theoretically and practically, and propose the mowing control method which based on computer visionLawn images collected by camera, through the extraction of programming dealing with lawn, obstacles and boundary characteristics to achieve edge separationThrough special processing algorithm to determine boundary arises and obstacles location, size and speed of the robot, with real-time capturing and processingThis paper gives the complete image recognition processing, and analyzes several methods of image filtering and edge detection, and proposes simple control algorithm for obstacle avoidance, and applies MATlab for obstacle avoidance simulationThe results show that: the method can correctly identify the obstacles and boundaries, through the output about location, size of the obstacles and boundary, border slope and speed of the robot to control robot mowerMost importantly, that computer vision applying in the mowing robot itself is an innovation.

关键词： Lawn Mower Obstacle avoidance controlling Computer vision Image processing

来源：评论

学校读者我要写书评

暂无评论

An Improved Genetic Algorithm for Degree Constrained Minimum Spanning Trees

An Improved Genetic Algorithm for Degree Constrained Minimum...

引用

第28届中国控制与决策会议

作者： Kai Shi Qingfeng Song Sheng Lin Guangping Xu Zhanxu Cao Key Lab of Intelligent Computing and Novel Software Technology Key Laboratory of Computer Vision and System Ministry of Education School of Science Tianjin Chengjian University

ISBN: (纸本)9781467397155

The Minimum Spanning Tree(MST) is of crucial importance for Communication Networks(CNs),which can solve problems of unconstrained CNs ***,in practical CNs,the degree of the spanning tree is *** such a case,the problem is very difficult,which has been proved to be *** this paper,an improved genetic algorithm(I-GA) is proposed for solving the problem of Degree Constrained Minimum Spanning Tree(DCMST).We use Prufer number as the chromosome,and improve the crossover and mutation processes of the existing genetic algorithm for obtaining high locality,heritability,and *** results show that our mechanism of I-GA can get relatively better results.

关键词： Minimum Spanning Tree Genetic Algorithm Degree constrained Prufer Number

来源：评论

学校读者我要写书评

暂无评论

A kind of SND-based algorithm for self-adapting network congestion control

引用

Journal of Information and Computational Science 2011年第11期8卷 2033-2044页

作者： Zhang, Degan Hu, Yuxia Liang, Yanpin Liu, Zhaojing Tianjin Key Lab. of Intelligent Computing and Novel software Technology Tianjin University of Technology Tianjin 300191 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

A kind of SND-based algorithm for self-adapting network congestion control has been presented in this paper, which is for the complicated and integrated network environment that the Internet of Things (IOT) to face in the future. As we know, the control of network congestion has become a hot spot in the study of Internet of Things transmission service. The network control algorithm of self-adapting congestion based on semi-normal distribution has improved the original packet loss rate function, and changed congestion situation in Internet of Things. By our many experiments, the validity and correctness of this algorithm has been tested. © 2011 Binary Information Press.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Emergent communication for rules reasoning 23

Emergent communication for rules reasoning

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yuxuan Guo Yifan Hao Rui Zhang Enshuai Zhou Zidong Du Xishan Zhang Xinkai Song Yuanbo Wen Yongwei Zhao Xuehai Zhou Jiaming Guo Qi Yi Shaohui Peng Di Huang Ruizhi Chen Qi Guo Yunji Chen University of Science and Technology of China and State Key Lab of Processors Institute of Computing Technology CAS and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology CAS State Key Lab of Processors Institute of Computing Technology CAS and Shanghai Innovation Center for Processor Technologies State Key Lab of Processors Institute of Computing Technology CAS and Cambricon Technologies University of Science and Technology of China Intelligent Software Research Center Institute of Software CAS State Key Lab of Processors Institute of Computing Technology CAS and University of Chinese Academy of Sciences

Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However, previous attempts have hovered around emerging communication under perception-oriented environmental settings, that forces agents to describe low-level perceptual features intra image or symbol contexts. In this work, inspired by the classic human reasoning test (namely Raven's Progressive Matrix), we propose the Reasoning Game, a cognition-oriented environment that encourages agents to reason and communicate high-level rules, rather than perceived low-level contexts. Moreover, we propose 1) an unbiased dataset (namely rule-RAVEN) as a benchmark to avoid overfitting, 2) and a two-stage curriculum agent training method as a baseline for more stable convergence in the Reasoning Game, where contexts and semantics are bilaterally drifting. Experimental results show that, in the Reasoning Game, a semantically stable and compositional language emerges to solve reasoning problems. The emerged language helps agents apply the extracted rules to the generalization of unseen context attributes, and to the transfer between different context attributes or even tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-aware computing approach with uncertainty for active application

引用

Journal of Information and Computational Science 2008年第1期5卷 179-186页

作者： Zhang, Degan Zhang, Hua Wang, Fayu Xue, Yabing School of Computer Science and Technology Tianjin University of Technology Tianjin 300191 China Tianjin Key Lab. of Intelligent Computing and Novel Software Technology Tianjin 300191 China Key Lab. of Industrial Controlling Technology Zhejiang University Hangzhou 310027 China

For active application of many cases, context-aware computing with uncertainty includes forming model, fusing of aware context, managing context information and so on. Approach research on computing of aware context with uncertainty for making dynamic decision is focused in this paper. We compare dynamic context-aware computing with improved Random Set Theory (RST) and extended D-S Evidence Theory (EDS). We give new modeling mode based on RST for aware context and our computing approach of modeled aware context, extend classic D-S Evidence Theory after considering context's feature. Then compare relative computing methods, enumerate experimental examples and give the evaluation. By comparisons, the more validity of new context-aware computing approach based on RST than EDS with uncertainty information has been tested successfully.

关键词： Set theory

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：