检索结果-内蒙古大学图书馆

Models of parallel computation :a survey and classification

中国高等学校学术文摘·计算机科学 2007年第2期1卷 156-165页

作者： ZHANG Yunquan CHEN Guoliang SUN Guangzhong MIAO Qiankun Laboratory of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100080China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100080China Anhui Province-MOST Key Co-Lab of High Performance Computing and Its Applications Department of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230027China

In this paper,the state-of-the-art parallel computational model research is *** will introduce various models that were developed during the past *** to their targeting architecture features,especially memory organization,we classify these parallel computational models into three *** models and their characteristics are discussed based on three generations *** believe that with the ever increasing speed gap between the CPU and memory systems,incorporating non-uniform memory hierarchy into computational models will become *** the emergence of multi-core CPUs,the parallelism hierarchy of current computing platforms becomes more and more *** this complicated parallelism hierarchy in future computational models becomes more and more important.A semi-automatic toolkit that can extract model parameters and their values on real computers can reduce the model analysis complexity,thus allowing more complicated models with more parameters to be *** memory and hierarchical parallelism will be two very important features that should be considered in future model design and research.

关键词： parallel computational models hierarchicalmemory hierarchical parallelism three generations memorymodel

来源：评论

学校读者我要写书评

暂无评论

Directed differential evolution based on directional derivative for numerical optimization problems

Directed differential evolution based on directional derivat...

引用

2011 11th International Conference on Hybrid Intelligent Systems, HIS 2011

作者： Zhang, Jun Luo, Wenjian School of Computer Science and Technology University of Science and Technology of China Hefei 230027 Anhui China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei 230027 Anhui China

ISBN: (纸本)9781457721502

Differential Evolution is one kind of Evolutionary Algorithms, which has been successfully applied to solve many optimization problems. In this paper, a directed differential mutation (DDM), which utilizes the directional derivative to decide a suitable search direction and a proper mutation step size, is proposed. It is merged into the classical DE to form a new algorithm, named directed differential evolution (DDE). The performance of the DDE is tested on 23 classical problems for numerical optimization. The experimental results demonstrate that the performance of the DDE outperforms the classical DE on most functions. © 2011 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

SvdNPD: A negative data publication method based on the sensitive value distribution

SvdNPD: A negative data publication method based on the sens...

引用

International Workshop on Artificial Immune Systems, AIS 2015

作者： Wu, Linli Luo, Wenjian Zhao, Dongdong School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei Anhui230027 China

ISBN: (纸本)9781509002986

Existing data publication methods retain the relationship between the quasi-identifier attributes and sensitive attributes of published data. We call them "positive data publication". However, it will lead to potential risk that attackers could deduce the privacy of the corresponding individuals from the published data. Recently, by combining the negative representation with k-anonymity and l-diversity, (k, m)- anonNPD and (l, m)-divNPD algorithms have been proposed, which improve the degree of privacy because the sensitive value of each individual is transformed into a negative value randomly. However, to reduce the average error of the reconstructed distribution, the data published by (k, m)-anonNPD and (l, m)-divNPD are often much larger than the original data. In this paper, we take the Sensitive Value Distribution into consideration, and propose a novel Negative Data Publication approach (i.e. SvdNPD), which is based on l-diversity. According to the sensitive value distribution, the negative selection probability of the sensitive attribute in each record can be calculated. Then the data could be published by transforming the sensitive value to a negative one with this probability. Experimental results show that the effective usage of the individual sensitive value distribution could enhance the utility of published data. Meanwhile, compared with (l, 1)-divNPD, SvdNPD just sacrifices a tiny privacy degree which is acceptable. © 2015 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Real-Valued Negative Databases 12

Real-Valued Negative Databases

引用

12th European Conference on the Synthesis and Simulation of Living Systems: Advances in Artificial Life, ECAL 2013

作者： Zhao, Dongdong Luo, Wenjian School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei Anhui230027 China

ISBN: (纸本)9780262317092

The negative database (NDB) is the negative representation of original data. Existing work has demonstrated that NDB can be used to preserve privacy and hide information. However, most work about NDB is based on binary representation. In some applications which are naturally descripted in real-valued space, the binary negative database is hard to be applied appropriately. Therefore, the real-valued negative database is proposed in this paper, and reversing the real-valued negative database is proved to be an NP-hard problem. Moreover, an effective algorithm for generating real-valued negative databases is given. Finally, an example of applying the realvalued negative database to the privacy-preserving data publication is descripted, and it shows that the real-valued negative database is valuable in practice. © 2013 Proceedings of the 12th European Conference on the Synthesis and Simulation of Living Systems: Advances in Artificial Life, ECAL 2013. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Tuning linux's load balancing algorithm for CMT system

Tuning linux's load balancing algorithm for CMT system

引用

2013 IEEE Conference Anthology, ANTHOLOGY 2013

作者： Peng, Jianzhang Gu, Naijie Li, Yehua Xu, Zhang School of Computer Science and Technology University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Computing and Communication Software USTC SICT Joint Laboratory of Network and Communication Hefei China

ISBN: (纸本)9781479916603

Linux 2.6 load balancing algorithm on scheduling domain supports CMP, CMT, SMP, NUMA architecture. For SMT, the algorithm try to assign the new process to the idlest CPU of the idlest core, and if the first CPU of a core is comparati vely idle, it tries to pull moderate amount of tasks from the busiest CPU of the core to balance the system workload periodically. Under certain circumstances, this strategy would cause the system to be more unbalanced. For the above defects, the algorithm can be adjusted in two ways. (1) The idlest CPU of the entire system should be selects for the new process;(2) the idlest CPU of a scheduling domain periodically can move tasks from the scheduling domain to itself. After applying this optimization, the system's performance achieved the highest increase of 8% in hackbench testing on an 8-core 32-thread XLR532 processor. © 2013 IEEE.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

Fast searching optimal negative surveys

Fast searching optimal negative surveys

引用

2014 International Conference on Information and Network Security, ICINS 2014

作者： Lu, Yihui Luo, Wenjian Zhao, Dongdong School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei Anhui230027 China

ISBN: (纸本)9781849199094

In a negative survey, a category which does not agree with the fact of each participant is collected. Hence, data collectors cannot acquire the realistic data of participants, and this can efficiently protect participants' private information and sensitive data. However, existing approaches used to estimate the distribution of positive surveys from negative surveys are not practical and time-consuming. This paper proposed a method in order to acquire practical estimation results with a lower computing cost, namely fastNStoPS. Usually, privacy and utility are used to measure the performances of negative surveys, and they are two conflicting metrics. Users have different demands on privacy (or utility) under different circumstances. The optimal negative surveys are a Pareto font of these two objectives. To demonstrate its practicability, the proposed fastNStoPS method is embedded into a Differential Evolution (DE), which is used to find the optimal negative surveys. The experiment results show that the DE has a much better performance on find the optimal negative surveys, and the computing cost is very low.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Games on Weighted Newman-Watts Small-World Networks

引用

Chinese Physics Letters 2009年第5期26卷 255-258页

作者：杜文博曹先彬赵琳周宏 Department of Computer Science and Technology University of Science and Technology of China Hefei 230026 Anhui Province Key Laboratory of Software in Computing and Communication University of Science and Technology of China Hefei 230026 School of Life Sciences University of Science and Technology of China Hefei 230026

We investigate the evolutionary prisoner＇s dilemma game （PDG） on weighted Newman-Watts （NW） networks. In weighted NW networks, the link weight ωij is assigned to the link between the nodes i and j as： ωij = （ki · kj）^β, where ki（kj） is the degree of node i（j） and β represents the strength of the correlations. Obviously, the link weight can be tuned by only one parameter β. We focus on the cooperative behavior and wealth distribution in the system. Simulation results show that the cooperator frequency is promoted by a large range of β and there is a minimal cooperation frequency around β = -1. Moreover, we also employ the Gini coefficient to study the wealth distribution in the population. Numerical results show that the Gini coefficient reaches its minimum when β≈ -1. Our work may be helpful in understanding the emergence of cooperation and unequal wealth distribution in society.

关键词： PRISONER'S dilemma game COOPERATIVENESS INCOME distribution SIMULATION methods & models GINI coefficient NUMERICAL analysis

来源：评论

学校读者我要写书评

暂无评论

Stochastic prefix-based fault tolerant source routing algorithm for network on chip

Stochastic prefix-based fault tolerant source routing algori...

引用

2012 International Conference on computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012

作者： Xu, Gengchun Ren, Kaixin Gu, Naijie Anhui Province Key Laboratory of Computing and Communication Software Hefei China USTC-SICT Joint Laboratory on Network and Communication Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781467319386

In this paper, a novel fault-tolerant source routing algorithm for Network on Chip (NOC) called Stochastic Prefix-based Source Routing (SPSR) is proposed. Compared to non-source routing algorithms, it releases the intermediate node from complicated decision-making or routing table maintenance. Unlike the traditional source routing algorithms which use broadcast packets to record the YD of every intermediate node in Route Discovery, it predetermine prospective routes, which can greatly reduces the packets generated and forwarded in the Route Discovery phase, and therefore reduces the power consumption. The proposed routing algorithm is implemented on the open source simulator Nirgam [14], incorporating Orion [15] to estimate the power consumption. Experiment results show that the proposed algorithm can greatly reduce the power consumption in the route discovery and the latency of SPSR is comparable with that of the broadcasting mechanism. © 2012 IEEE.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Learning with privileged information using Bayesian networks

引用

Frontiers of computer Science 2015年第2期9卷 185-199页

作者： Shangfei WANG Menghua HE Yachen ZHU Shan HE Yue LIU Qiang JI School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Key Lab of Computing and Communicating Software of Anhui Province Hefei 230027 China School of Mathematical Sciences University of Science and Technology of China Hefei 230027 China Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY 12180-3590 USA

For many supervised learning applications, addi- tional information, besides the labels, is often available dur- ing training, but not available during testing. Such additional information, referred to the privileged information, can be exploited during training to construct a better classifier. In this paper, we propose a Bayesian network （BN） approach for learning with privileged information. We propose to in- corporate the privileged information through a three-node BN. We further mathematically evaluate different topologies of the three-node BN and identify those structures, through which the privileged information can benefit the classifica- tion. Experimental results on handwritten digit recognition, spontaneous versus posed expression recognition, and gender recognition demonstrate the effectiveness of our approach.

关键词： Bayesian network privileged information clas-sification maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Test Case Generation Based on Program Invariant and Adaptive Random Algorithm

Test Case Generation Based on Program Invariant and Adaptive...

引用

Advances in Information Technology and Education

作者： Yuan Yuan Zeng Fanping Zhu Guanmiao Deng Chaoqiang Xiong Neng Department of Computer University of Science and Technology of China Anhui Province Key Lab of Software in Computing and Communication

Testing is a critical activity to find software errors. And choosing an effective test suite is the key problem in software testing area. Program invariant, as an attribute of program, can record the implementation state of test case very well and reveal the coverage of program data. In this paper, we integrate adaptive random testing and invariant technology, and present a new method which makes full use of the feedback information of program invariant and invalid case suite to generate the next case. Experiment results show that, compared with other similar methods, running for the same time, our method can achieve higher coverage and faster convergence speed.

关键词： Random testing Program invariant Adaptive random algorithm Test case generation

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：