检索结果-内蒙古大学图书馆

Annual Conference on Neural Information Processing Systems

作者： Sheng-Jun Huang Rong Jin Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University Nanjing 210093 China Department of Computer Science and Engineering Michigan State University East Lansing MI 48824

ISBN: (纸本)9781617823800

Most active learning approaches select either informative or representative unla-beled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criteria for query selection, they are usually ad hoc in finding unlabeled instances that are both informative and representative. We address this challenge by a principled approach, termed Quire, based on the min-max view of active learning. The proposed approach provides a systematic way for measuring and combining the informativeness and representativeness of an instance. Extensive experimental results show that the proposed Quire approach outperforms several state-of-the-art active learning approaches.

关键词： quires REPRESENTATIVE SAMPLES HALOGENATED ORGANIC COMPOUNDS

来源：评论

学校读者我要写书评

暂无评论

Sparse Representation for Face Verification in Social Insurance System

Sparse Representation for Face Verification in Social Insura...

引用

Chinese Conference on Pattern Recognition (CCPR)

作者： Rui Xue Ming-Yu You Guo-Zheng Li Department of Control Science & Engineering University of Tongji Shanghai China State Key Laboratory of Novel Software Technology Nanjing University China

Face verification system has been applied in the process of social insurance payment to prevent the pension impostors. However, the previous methods of face verification compare the test face with the corresponding training sample in the database, and then simply calculate the similarity of both, ignoring global similarity distribution. In this paper, we put the sparse representation method into the face verification system and propose a new method called SRS. Experiments are performed on six face data sets, such as Yale A, Extended Yale B, AR etc., combing the feature extraction methods of Randomfaces, Eigenfaces, Fisherfaces and Laplacianfaces. Cosine method is used for comparison. Experimental results show that the new method achieves higher accuracy with large numbers of classes.

关键词： Face Face recognition Principal component analysis Databases computer vision Electronic mail Pattern analysis

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Routing Protocol for Heterogeneous Sensor Networks

A Probabilistic Routing Protocol for Heterogeneous Sensor Ne...

引用

International Conference on Networking, Architecture, and Storage (NAS)

作者： Yuefei Hu Wenzhong Li Xiao Chen Xin Chen Sanglu Lu Jie Wu State Key Laboratory of Novel Software Technology Nanjing University China Department of Computer Science Texas State University San Marcos San Marcos USA Department of Computer and Information Sciences Temple University Philadelphia PA USA

The past five years witnessed a rapid development in wireless sensor networks, which have been widely used in military and civilian applications. Due to different requirements in their application environment, sensors with different capacities, power, and so on are deployed. Data routing in such heterogeneous sensor networks is a challenging task. On one hand, the heterogeneous features bring about the diversity in their transmission ranges, which subsequently lead to asymmetric links in the communication graph. As a result, conventional routing strategies based on undirected graphs become unsuitable. On the other hand, sensors communicate with each other through intermittent asymmetric links. It is important to provide assurable delivery rate for mission critical applications. In this paper, we propose ProHet: a Probabilistic routing protocol for Heterogeneous sensor networks, which can deal with asymmetric links well and work in a distributed manner with low overhead and assurable delivery rate. The ProHet protocol first produces a bidirectional routing abstraction by finding a reverse routing path for every asymmetric link. Then, it uses a probabilistic strategy to choose forwarding nodes based on historical statistics, which is shown to achieve assurable delivery rate by theoretical analysis. Extensive simulations are conducted to verify the efficiency of the proposed protocol.

关键词： Routing Receivers Routing protocols Probabilistic logic Wireless sensor networks Broadcasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive resource allocation for preemptable jobs in cloud systems

Adaptive resource allocation for preemptable jobs in cloud s...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Jiayin Li Meikang Qiu Jian-Wei Niu Yu Chen Zhong Ming Department of Electrical and Computer Engineering University of Kentucky Lexington KY USA State Key Laboratory of Software Develop. Environment Beihang University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China College of Computer Science and Software Shenzhen University Shenzhen China

In cloud computing, computational resources are provided to remote users in the form of leases. For a cloud user, he/she can request multiple cloud services simultaneously. In this case, parallel processing in the cloud system can improve the performance. When applying parallel processing in cloud computing, it is necessary to implement a mechanism to allocate resource and schedule the tasks execution order. Furthermore, a resource allocation mechanism with preemptable task execution can increase the utilization of clouds. In this paper, we propose an adaptive resource allocation algorithm for the cloud system with preemptable tasks. Our algorithms adjust the resource allocation adaptively based on the updated of the actual task executions. And the experimental results show that our algorithms works significantly in the situation where resource contention is fierce.

关键词： Resource management Cloud computing Processor scheduling Scheduling Computational modeling Heuristic algorithms Schedules

来源：评论

学校读者我要写书评

暂无评论

Quantum state Reduction for Universal Measurement Based Computation

引用

Physical Review Letters 2010年第2期105卷 020502-020502页

作者： Xie Chen Runyao Duan Zhengfeng Ji Bei Zeng 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 NSW Australia Department of Computer Science and Technology Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China 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 University of Waterloo Waterloo Ontario Canada Department of Combinatorics and Optimization University of Waterloo Waterloo Ontario Canada

Measurement based quantum computation, which requires only single particle measurements on a universal resource state to achieve the full power of quantum computing, has been recognized as one of the most promising models for the physical realization of quantum computers. Despite considerable progress in the past decade, it remains a great challenge to search for new universal resource states with naturally occurring Hamiltonians and to better understand the entanglement structure of these kinds of states. Here we show that most of the resource states currently known can be reduced to the cluster state, the first known universal resource state, via adaptive local measurements at a constant cost. This new quantum state reduction scheme provides simpler proofs of universality of resource states and opens up plenty of space to the search of new resource states.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

A Trust-Based Approach to Estimating the Confidence of the software System in Open Environments

引用

Journal of computer science & technology 2009年第2期24卷 373-385页

作者：徐锋潘静陆文 State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University

Emerging with open environments, the software paradigms, such as open resource coalition and Internetware, present several novel characteristics including user-centric, non-central control, and continual evolution. The goal of obtaining high confidence on such systems is more difficult to achieve. The general developer-oriented metrics and testing-based methods which are adopted in the traditional measurement for high confidence software seem to be infeasible in the new situation. Firstly, the software development is changed from the developer-centric to user-centric, while user＇s opinions are usually subjective, and cannot be generalized in one objective metric. Secondly, there is non-central control to guarantee the testing on components which formed the software system, and continual evolution makes it impossible to test on the whole software system. Therefore, this paper proposes a trust-based approach that consists of three sequential sub-stages： 1） describing metrics for confidence estimation from users; 2） estimating the confidence of the components based on the quantitative information from the trusted recommenders; 3） estimating the confidence of the whole software system based on the component confidences and their interactions, as well as attempts to make a step toward a reasonable and effective method for confidence estimation of the software system in open environments.

关键词： trust confidence open resource coalition Internetware software architecture

来源：评论

学校读者我要写书评

暂无评论

Trust based routing for misbehavior detection in Ad hoc networks

引用

Journal of Networks 2010年第5期5卷 551-558页

作者： Gong, Wei You, Zhiyang Chen, Danning Zhao, Xibin Gu, Ming Lam, Kwok-Yan Department of Computer Science and Technology Tsinghua University Beijing 100084 China Key Laboratory of Information System Security of Ministry of Education School of Software Tsinghua University Beijing 100084 China

Node misbehavior due to selfish or malicious intention could significantly degrade the performance of MANET because most existing routing protocols in MANET are aiming at finding most efficiency path. To deal with misbehavior in MANET, an incentive mechanism should be integrated into routing decision-making. In this paper firstly we review existing techniques for secure routing, and then propose to use trust vector model based routing protocols. Each node would evaluate its own trust vector parameters about neighbors through monitoring neighbors' pattern of traffic in network. At the same time, trust dynamics is included in term of robustness. Then we integrated trust model into Dynamic Source Routing (DSR) and Ad-hoc On Demand Distance Vector (AODV) which are most typical routing protocols in MANET. We evaluate the performance of those trust routing protocols by comparing the simulation results of with and without the proposed trust mechanism. The simulation results demonstrate that modified routing protocols can effectively detect malicious nodes and mitigate their attacks. © 2010 ACADEMY PUBLISHER.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Data Reconstruction Algorithm for Solid-state Disks

A Fine-Grained Data Reconstruction Algorithm for Solid-State...

引用

International Conference on Networking, Architecture, and Storage (NAS)

作者： Peng Wang Diqing Hu Changsheng Xie Jianzong Wang Xiao Qin Wuhan National Laboratory of Optoelectronics Key Laboratory of Data Storage System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China Department of Computer Science and Software Engineering Samuel Ginn College of Engineering Aubum University USA

Solid-state disks (SSDs) with high I/O performance are increasingly becoming popular. To extend the life time of flash memory, one can apply wear-leveling strategies to manage data blocks. However, wear-leveling strategies certainly inevitably degrade write performance. In addition to low write performance, wear-leveling strategies make one block unwritable when one bit of this block is invalid. Although data reconstruction techniques have been widely employed in disk arrays, the reconstruction techniques has not been studied in the context of solid-state disks. In this paper, we present a new fine-grained data-reconstruction algorithm for solid-state disks. The algorithm aims to provide a simple yet efficient wear-leveling strategy that improves both I/O performance and reliability of solid-state disks. Simulation experiments show that all data blocks have very similar in terms of erasure times. The number of extra erasures incurred by our algorithm is very marginal.

关键词： Reconstruction algorithms Reliability Mathematical model Flash memory Equations Arrays Parity check codes

来源：评论

学校读者我要写书评

暂无评论

A Community-Centric Model for Service Publication, Discovery, Selection, Binding, and Maintenance

A Community-Centric Model for Service Publication, Discovery...

引用

2010 Fifth IEEE International Symposium on Service Oriented System Engineering

作者： Lijun Mei W. K. Chan Zhenyu Zhang Xiaopeng Gao Department of Computer Science City University of Hong Kong Hong Kong China Department of Computer Science University of Hong Kong Hong Kong China State Key Laboratory of Computer Science Institute of Software of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Beihang University Beijing China

Services discovery, selection, composition, verification, and adaptation are important in service-oriented computing. Existing researches often study techniques to maximize the benefits of individual services. However, following the power laws, a small fraction of quality services offers their executions to support a significant portion of all service requests. We argue that locating and maintaining such a small and significant set of services is important to the development of service-oriented computing. In this paper, we propose the notion of adaptive service-oriented community. A community consists of peer reviewed services, and only those operations of member services that the community collectively exceeds a significance threshold are discoverable and bondable. Services also select such communities to bind to its requested operations primarily based on their significance. Our proposal essentially raises a service ecosystem from pursuing the benefits of individual services to that of the community as a whole. Our model also has features to make a namespace or a web service privacy-aware.

关键词： Web services Communities Syntactics Computational modeling Biological system modeling Indexes software

来源：评论

学校读者我要写书评

暂无评论

Middleware Support for Context-awareness in Asynchronous Pervasive Computing Environments

Middleware Support for Context-awareness in Asynchronous Per...

引用

IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC

作者： Jianping Yu Yu Huang Jiannong Cao Xianping Tao Department of Computer Science and Technology Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Internet and Mobile Computing Lab Department of Computing Hong Kong Polytechnic University Hong Kong China

Context-awareness is an essential feature of pervasive applications, and runtime detection of contextual properties is one of the primary approaches to enabling context awareness. However, existing context-aware middleware does not provide sufficient support for detection of contextual properties in asynchronous environments. We argue that in asynchronous environments, the concept of time needs to be reexamined. Instead of assuming the availability of global time or synchronous interaction, we should rely on logical time. To this end, we present the Middleware Infrastructure for Predicate detection in Asynchronous environments (MIPA), which supports context-awareness based on logical time. Design and operation of MIPA are explained in detail. We also evaluate MIPA with a comprehensive case study. The evaluation results show the cost-effectiveness and scalability of MIPA.

关键词： Context Radiofrequency identification Context modeling Middleware Memory management Pervasive computing

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：