检索结果-内蒙古大学图书馆

IEEE International Conference on High Performance Computing and Communications

作者： Shuo Cheng Chun Cao Ping Yu Xiaoxing Ma State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

ISBN: (纸本)9781509042982

Cloud computing has become a most popular computing pattern in both industry and academia. Infrastructure as a Service (IaaS) cloud platform provides an elastic way to require computing resources in a pay-as-you-go paradigm. While bringing great convenience to both customers and service providers, the cloud platform has some problems demanding prompt solution, one of which is how to achieve energy saving with a low Service Level Agreement (SLA) violation rate. Though existing works achieve optimization to a certain extent, most of them do not take the overall resource utilization balancing into account. In this paper, heuristic greedy algorithms are proposed based on a novel conception, "Healthy Threshold". By regulating resource utilization of clouds towards Healthy Threshold, the overall balancing of resource utilization is achieved, so energy consumption can be reduced more effectively. Besides, we also propose a strict SLA enforcement strategy to further guarantee a low SLA violation rate. Results of real-world trace driven simulations show that our algorithms outperform other works when solving the problem.

关键词： Energy Efficient Cloud Computing IaaS SLA-Aware VM Migration

来源：评论

学校读者我要写书评

暂无评论

Tracking slowly moving clairvoyant: Optimal dynamic regret of online learning with true and noisy gradient 33

Tracking slowly moving clairvoyant: Optimal dynamic regret o...

引用

33rd International Conference on Machine Learning, ICML 2016

作者： Yang, Tianbao Zhang, Lijun Jin, Rong Yi, Jinfeng Department of Computer Science University of Iowa Iowa CityIA52242 United States National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute of Data Science and Technologies Alibaba Group Seattle United States IBM Thomas J. Watson Research Center Yorktown HeightsNY10598 United States

ISBN: (纸本)9781510829008

This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at each step. By assuming that the clairvoyant moves slowly (i.e., the minimizers change slowly), we present several improved variationbased upper bounds of the dynamic regret under the true and noisy gradient feedback, which are optimal in light of the presented lower bounds. The key to our analysis is to explore a regularity metric that measures the temporal changes in the clairvoyant's minimizers, to which we refer as path variation. Firstly, we present a general lower bound in terms of the path variation, and then show that under full information or gradient feedback we are able to achieve an optimal dynamic regret. Secondly, we present a lower bound with noisy gradient feedback and then show that we can achieve optimal dynamic regrets under a stochastic gradient feedback and two-point bandit feedback. Moreover, for a sequence of smooth loss functions that admit a small variation in the gradients, our dynamic regret under the two-point bandit feedback matches what is achieved with full information.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

New Tampered Features for Scene and Caption Text Classification in Video Frame

New Tampered Features for Scene and Caption Text Classificat...

引用

International Workshop on Frontiers in Handwriting Recognition

作者： Sangheeta Roy Palaiahnakote Shivakumara Umapada Pal Tong Lu Chew Lim Tan Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China Department of Computer Science National University of Singapore

ISBN: (纸本)9781509009824

The presence of both caption/graphics/superimposed and scene texts in video frames is the major cause for the poor accuracy of text recognition methods. This paper proposes an approach for identifying tampered information by analyzing the spatial distribution of DCT coefficients in a new way for classifying caption and scene text. Since caption text is edited/superimposed, which results in artificially created texts comparing to scene texts that exist naturally in frames. We exploit this fact to identify the presence of caption and scene texts in video frames based on the advantage of DCT coefficients. The proposed method analyzes the distributions of both zero and non-zero coefficients (only positive values) locally by moving a window, and studies histogram operations over each input text line image. This generates line graphs for respective zero and non-zero coefficient coordinates. We further study the behavior of text lines, namely, linearity and smoothness based on centroid location analysis, and the principal axis direction of each text line for classification. Experimental results on standard datasets, namely, ICDAR 2013 video, 2015 video, YVT video and our own data, show that the performances of text recognition methods are improved significantly after-classification compared to before-classification.

关键词： Discrete cosine transforms Text recognition Image color analysis Linearity Bars Character recognition Mathematical model

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

Securing big data in the Cloud by protected mapping over multiple providers

Securing big data in the Cloud by protected mapping over mul...

引用

Digital Media Industry & Academic Forum (DMIAF)

作者： Chunming Rong Hongbing Cheng Martin Gilje Jaatun Department of Electronic Engineering & Computer Science University of Stavanger Norway State Key Laboratory for Novel Software Technology Nanjing University China

ISBN: (纸本)9781509010011

The Cloud is increasingly being used to store and process big data, and conventional security mechanisms using encryption are either not sufficiently efficient or not suited to the task of protecting big data in the Cloud. In this paper we present an alternative approach which divides big data among multiple Cloud providers, and instead of protecting the data itself, protects the mapping of the various data elements to each provider using a trapdoor function. Our initial analysis indicates that this is an efficient and secure approach for securing big data.

关键词： Cloud computing Big data Encryption Partitioning algorithms Memory

来源：评论

学校读者我要写书评

暂无评论

Recommendations Based on LDA Topic Model in Android Applications

Recommendations Based on LDA Topic Model in Android Applicat...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Tianhao Pan Weifeng Zhang Ziyuan Wang Lei Xu School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China State Key Lab. for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9781509037148

With the popularity of smart phones, mobile applications have become an essential element in people's lives. Wherever you are, the Android market can allow people to download these applications. When you open Android mobile phone market in a mobile application program interface, we can see not only the application content presentation but also other information. The user can also see the scoring for this application, comments and so on. The text describes the application content information and user reviews, no more than 200 words, the contents of which are closely related to mobile applications. How to use these text data to obtain valuable information for the users has been an important research field of data mining, it is also the focus of this study. The topics of different mobile applications are the summary of their contents. This generalization to some extent reflects the different mobile application content core idea. Therefore mobile applications relating to mining user interest analysis has important significance, the results relating to mining can provide data support for topic-based personalized recommendation applications. This article extracts the contents and users' descriptions from a real Android Market dataset, and builds a new topic model called combineLDA to analyze different topics of each mobile application. By combineLDA model we can analyze the topic probability distribution of each mobile application, and then we can calculate the similarity and recommend to users with high similarity applications.

关键词： Conferences software quality software reliability Security

来源：评论

学校读者我要写书评

暂无评论

OpenFunction: An extensible data plane abstraction protocol for platform-independent software-defined middleboxes

OpenFunction: An extensible data plane abstraction protocol ...

引用

International Conference on Network Protocols

作者： Chen Tian Alex X. Liu Ali Munir Jie Yang State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Engineering Michigan State University USA

ISBN: (纸本)9781509032822

We propose OpenFunction, an extensible data plane abstraction protocol for platform-independent software-defined middleboxes. The main challenge is how to abstract packet operations, flow states and event generations with elements. The key decision of OpenFunction is: actions/states/events operations should be defined in a uniform pattern and independent from each other. We implemented a working SDM system including one OpenFunction controller and OpenFunction boxes based on Netmap, DPDK and FPGA to verify OpenFunction abstraction.

关键词： Middleboxes Protocols Hardware Process control Logic gates Semantics Technological innovation

来源：评论

学校读者我要写书评

暂无评论

Macroflow: A fine-grained networking abstraction for job completion time oriented scheduling in datacenters

Macroflow: A fine-grained networking abstraction for job com...

引用

International Conference on Network Protocols

作者： Chen Tian Junhua Yan Alex X. Liu Yizhou Tang Yuankun Zhong Zi Li State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Engineering Michigan State University USA

ISBN: (纸本)9781509032822

For a datacenter running a data-parallel analytic framework, minimizing job completion time (JCT) is crucial for application performance. The key observation is that JCT could be improved, if network scheduling can exploit the opportunity of decreasing the amount of occupied machine slot-time spend on communication. We propose Macroflow, a networking abstraction that captures the primitive resource granularity of data-parallel frameworks. We study the inter-macroflow scheduling problem for decreasing application JCT. We propose the Smallest-Macroflow-First (SMF) and Smallest-Average-Macroflow-First (SAMF) heuristics that greedily schedule macroflows based on their network footprint. Trace-driven simulations demonstrate that our algorithms can reduce the average and tail JCT of network-intensive jobs by up to 20% and 25%, respectively; at the same time, the throughput of computation-intensive jobs is increased by up to 2.2×.

关键词： Throughput Measurement Ports (computers) Processor scheduling Conferences Protocols Fabrics

来源：评论

学校读者我要写书评

暂无评论

Secure Big Data Storage and Sharing Scheme for Cloud Tenants

引用

China Communications 2015年第6期12卷 106-115页

作者： CHENG Hongbing RONG Chunming HWANG Kai WANG Weihong LI Yanyan College of Computer Science Zhejiang University of Technology State Key Laboratory for Novel Software Technology Nanjing University Department of Electronic Engineering & Computer Science University of Stavanger Electrical Engineering and Computer Science University of Southern California

The Cloud is increasingly being used to store and process big data for its tenants and classical security mechanisms using encryption are neither sufficiently efficient nor suited to the task of protecting big data in the *** this paper,we present an alternative approach which divides big data into sequenced parts and stores them among multiple Cloud storage service *** of protecting the big data itself,the proposed scheme protects the mapping of the various data elements to each provider using a trapdoor ***,comparison and simulation prove that the proposed scheme is efficient and secure for the big data of Cloud tenants.

关键词： cloud computing big data stor-age and sharing security

来源：评论

学校读者我要写书评

暂无评论

GB-RC4: Effective brute force attacks on RC4 algorithm using GPU 7

GB-RC4: Effective brute force attacks on RC4 algorithm using...

引用

7th International Green and Sustainable Computing Conference, IGSC 2016

作者： Xue, Pei Li, Tao Dong, Han Liu, Chunbo Ma, Wenjing Pei, Songwen College of Computer and Control Engineering Nankai University Tianjin300071 China Information Security Evaluation Center Civil Aviation University of China Tianjin300300 China Laboratory of Parallel Software and Computational Science State Key Laboratory of Computing Science Institute of Software CAS Beijing China Shanghai Key Lab of Modern Optical Systems Department of Computer Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9781509051175

Encryption algorithms are applied to a variety of fields and the security of encryption algorithms depends heavily on the computational infeasibility of exhaustive key-space search. RC4 algorithm has an extensive application for stream encryption, however, the disadvantages of traditional RC4 serial algorithm are large computational quantity and slow computation speed, which means a great challenge for throughput of computing system. Graphics processors recently have been widely used as accelerators for high throughput computing. In this paper, GPU is used to improve the efficiency and performance of attacking RC4 algorithm. First, we revised RC4 algorithm to make it easier to parallelize on a GPU. Then we take advantage of constant memory and shared memory in GPU to search the key space of RC4 algorithm efficiently. Besides, we solved the bank conflict problem in shared memory to further improve the performance. Our approach was evaluated in the whole key space of 40-bit, and the results show it can complete searching of the whole key space within 12.8 hours. © 2016 IEEE.

关键词： Graphics processing unit

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：