检索结果-内蒙古大学图书馆

作者： Liao, Bo Jiang, Yan Liang, Wei Peng, Lihong Peng, Li Hanyurwimfura, Damien Li, Zejun Chen, Min Key Laboratory for Embedded and Network Computing of Hunan Province College of Information Science and Engineering Hunan University Changsha Hunan410082 China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Department of Computer Science and Engineering Changsha Medical University Changsha Hunan410219 China

Efficient mining of high-throughput data has become one of the popular themes in the big data era. Existing biology-related feature ranking methods mainly focus on statistical and annotation information. In this study, two efficient feature ranking methods are presented. Multi-target regression and graph embedding are incorporated in an optimization framework, and feature ranking is achieved by introducing structured sparsity norm. Unlike existing methods, the presented methods have two advantages: (1) the feature subset simultaneously account for global margin information as well as locality manifold information. Consequently, both global and locality information are considered. (2) Features are selected by batch rather than individually in the algorithm framework. Thus, the interactions between features are considered and the optimal feature subset can be guaranteed. In addition, this study presents a theoretical justification. Empirical experiments demonstrate the effectiveness and efficiency of the two algorithms in comparison with some state-of-the-art feature ranking methods through a set of real-world gene expression data sets. © 2015 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Duplication based energy aware scheduling algorithm in heterogeneous many-core system-on-chip

引用

Journal of Computational Information Systems 2015年第8期11卷 2981-2988页

作者： Liu, Yan An, Mengmeng Chen, Xiaoming Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Changsha China College of Computer National University of Defense Technology Changsha China

With the rapid development of semiconductor technology, hundreds of processor cores can be integrated into a single chip, known as "many-core system-on-chip". For the problem that performance and power consumption are equally important in heterogeneous many-core system-on-chip, this paper proposes an duplication based energy aware task scheduling algorithm, which balances the relationship between task scheduling time and energy consumption. Simulation experimental results show that the proposed algorithm can reduce the completion time and energy consumption, and leverage the relationship between them effectively. ©, 2015, Binary Information Press. All right reserved.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Dynamic negotiation strategy based parallel-offer in cloud computing

引用

Journal of Computational Information Systems 2015年第10期11卷 3691-3699页

作者： Hu, Jun Xu, Ru Xiao, Deyu College of Computer Science and Electronics Engineering Hunan University Changsha China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Key Laboratory for Embedded and Network Computing of Hunan Province Changsha China

Cloud computing can dynamically provide service based on service level agreements that between cloud services and consumers. Establish a viable and efficient dynamic negotiation strategy is one of hot research in cloud negotiation. This paper proposes a dynamic negotiation strategy based on parallel-offer under cloud computing environment, which combines dynamic concession strategy with parallel-offer tradeoff mechanism. The strategy can adjust negotiation strategy according to the supply demand relationship and tradeoff strategy of multi-issue, to achieve flexible and efficient cloud computing negotiation. This work firstly, establishes predicting market supply-demand relationship model, to build the dynamic concession strategy. Then on the base of above, introduces a parallel offer multi-issue tradeoff strategy into negotiation strategy, to achieve the dynamic concession tradeoff strategy (DCT). Finally, DCT mechanism is implemented in CloudSim test bed, and empirical results show DCT negotiation mechanism reach faster agreements and achieve higher utilities than other related approaches in cloud computing environment. ©, 2015, Binary Information Press. All right reserved.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Optimized roles set algorithm in distributed parallel computing system

Optimized roles set algorithm in distributed parallel comput...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Wu, Wenkang Tang, Zhuo Key Laboratory for Embedded and Network Computing of Hunan Province Changsha Hunan 410082 China

ISBN: (纸本)9783642539619

With the rapid development of computer technology, distributed computing and parallel computing have made great progress. Distributed parallel computing system is a combination of distributed computing and parallel computing, which can provide fast solutions to information sharing and subtasks in high-speed network environment. In this paper, we propose a new access control model-Distributed Parallel computing Role Based Access Control (DPCRBAC) Model on the basis of the traditional RBAC model. We propose a new roles set assignment algorithm-Optimized Roles Set (ORS) algorithm. According to the results of simulation, the proposed algorithm ORS can effectively improve the efficiency roles and is effective in reducing role conflicts in the process of role assignment, and ensure the safety and reliability of the distributed parallel computing system. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

An offline scheduling algorithm for certifiable mixed-critical embedded system

An offline scheduling algorithm for certifiable mixed-critic...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Wu, Chengtao Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410086 China

ISBN: (纸本)9783642539619

In modern embedded platforms, safety-critical functionalities that must be certified correctly to high level of assurance co-exist with less critical software that are not subjected to certification requirements. These caused many scheduling problems. Nowadays, many researches focused on promising techniques for meeting the following two goals: (1) being able to certify the safety-critical functionalities under very conservative assumptions, and (2) ensuring high utilization of platform resources under less pessimistic assumptions. In this paper we propose an offline scheduling algorithm called OSS for certifiable mixed-criticality systems on a uniprocessor platform. Compared to previous proposed algorithm CBEDF, OSS can supply better schedulability. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

The implementation of MapReduce scheduling algorithm based on priority

The implementation of MapReduce scheduling algorithm based o...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Gu, Lianjun Tang, Zhuo Xie, Guoqi Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410082 China

ISBN: (纸本)9783642539619

Nowadays cloud computing has become a popular platform for scientific applications. Cloud computing intends to share a large scale resources and equipments of computation, storage, information and knowledge for scientific researches. Job Scheduling problem is a core and challenging research issue in the current cloud computation area, and the aim is to the reasonable control of the job execution sequence as well as the allocation of computing resources, making the job total completion time of the shortest and resources are fully utilized. Data locality is one of the main factors to influence scheduling algorithm. The paper proposed an improved scheduling algorithm based on priority, after taking full account of data locality (IPDSA), which can distinguish the user's job levels, so as to reduce the job execution time and avoid losing into locally optimal solution. The experimental results on the Hadoop platform show that the new scheduling algorithm can reduce the job average execution time, and raises the rate availability of resources. © Springer-Verlag Berlin Heidelberg 2014.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Dynamic slack reclamation with EDL scheduling for periodic multimode real-time task

Dynamic slack reclamation with EDL scheduling for periodic m...

引用

26th International Conference on Parallel Computational Fluid Dynamics, ParCFD 2013

作者： Hu, Huan Li, Renfa Key Laboratory for Embedded and Network Computing of Hunan Province Changsha 410086 China

ISBN: (纸本)9783642539619

The multiframe task has been considered in dynamic real-time scheduling, its different execution mode optional feature can handle the resource waste caused by pessimistic estimation of the execution requirement. But in runtime, the selection of an instance execution mode with more execution requirement may cause a deadline miss. In this paper, we propose a slack reclamation mechanism of configuring an appropriate execution mode under deadline guarantee. This mechanism is composed of offline phase and online phase. In offline, the initial execution mode of task instances is selected and the static slack is calculated. In online, on the basis of EDL scheduling list, mode upgrade list and actual execution requirement of the instance, the slack is assigned to the instance with the highest value of the r/R in Slack available zone. Our simulation shows that this scheme can obtain a better result of the accured reward when the task's BCET is greater than 40% of its WCET. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Identification of mild cognitive impairment using extreme learning machines model 11th

Identification of mild cognitive impairment using extreme le...

引用

11th International Conference on Intelligent computing, ICIC 2015

作者： Zhang, Wen Shen, Hao Ji, Zhiwei Meng, Guanmin Wang, Bing School of Electronics and Information Engineering Tongji University Shanghai201804 China The Advanced Research Institute of Intelligent Sensing Network Tongji University Shanghai201804 China The Key Laboratory of Embedded System and Service Computing Tongji University Shanghai201804 China Department of Clinical Laboratory Tongde Hospital of Zhejiang Province 234th Gucui Road Hangzhou310012 China

ISBN: (纸本)9783319221854

Alzheimer’s disease (AD) is very common disorder among the older people. Predicting mild cognitive impairment (MCI), an intermediate stage between normal cognition and dementia, in individuals with some symptoms of cognitive decline may have great influence on treatment choice and disease progression. In this work, a novel prediction model based on extreme learning machines algorithm was proposed to identify mild cognitive impairment using the information of some biomarkers, i.e., Position Emission Tomography (PET), Magnetic Resonance Imaging (MRI), and the cerebrospinal fluid (CSF). Firstly, each subject will be represented by three biomarkers using a vector with 201 dimensions after some essential pre-processing. Then, a prediction model based on extreme learning machine algorithm was trained to catch the difference between the patients and healthy persons. Finally, the model had been employed to identify identifying MCI participants from the normal people. Based on a dataset, including 99 MCI patients and 52 health controls, our proposed method achieved 70.86 % prediction accuracy with 67.68 % sensitivity at the precision of 76.92 %. Extensive experiments are performed to compare our method with state-of-the-art techniques, i.e., support vector machine (SVM) and SVM with fusion kernels. Experimental results demonstrate that proposed extreme learning machine is a powerful tool for predicting MCI with excellent performance and less time. © Springer International Publishing Switzerland 2015.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Object-oriented program tailoring based on model 4

Object-oriented program tailoring based on model

引用

4th International Conference on Computer-Aided Design, Manufacturing, Modeling and Simulation, CDMMS2014

作者： Jin, Qing Kai Li, Jun Yi Zhang, Yan College of Information Science and Engineering Hunan University ChangshaHunan China Key Laboratory for Embedded and Network Computing of Hunan Province ChangshaHunan China

ISBN: (纸本)9783038351528

For the redundant codes caused by software reuse and rapid development in object-oriented program, the paper proposes a cutting model and designs a cutting scheme based on this model. Firstly, a cutting model is established. Then, static analysis is made for object-oriented codes and the cutting information base of objects to be clipped is established. Lastly, the cutting information base and cutting model is matched to cut the program. A test on a practical java project indicates that the cutting scheme can make the volume of the project reduce by about 21%. © (2014) Trans Tech Publications, Switzerland.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

A High-performance DAG Task Scheduling Algorithm for Heterogeneous networked embedded Systems

A High-performance DAG Task Scheduling Algorithm for Heterog...

引用

IEEE International Conference on Advanced Information networking and Applications

作者： Guoqi Xie Renfa Li Xiongren Xiao Yuekun Chen Key Laboratory for Embedded and Network Computing of Hunan Province Hunan University Changsha China

ISBN: (纸本)9781479936311

A high-performance scheduling for a DAG (Directed Acyclic Graph) task graph on heterogeneous networked embedded systems or parallel and distributed systems is to maximize concurrency and minimize inter-processor communication. Most of the algorithms using upward rank value for task prioritizing and earliest finish time for processor assignment. But both approaches ignored the heterogeneity of system and could not create accurate and efficient schedules. Yet no one has doubled about and recognized that. A fully heterogeneous task scheduling algorithm is proposed to address the above problems in this paper. The fundamentals of DAG model and corresponding algorithms are investigated. New concepts called Heterogeneous Upward Rank Value (HURV) and Heterogeneous Priority Rank Value (HPRV) are defined. An algorithm called Heterogeneous Select Value (HSV) is proposed in paper. Both benchmark and extensive experimental evaluation demonstrate the significant improvements in proposed algorithm.

关键词： heterogeneous networked embedded systems heterogeneous upward rank value heterogeneous select value DAG

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：