检索结果-内蒙古大学图书馆

IEEE International Conference on E-science Workshops

作者： Christian Vecchiola Mani Abedini Michael Kirley Xingchen Chu Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Laboratory University of Melbourne Australia Department of Computer Science and Software Engineering University of Melbourne Australia

Microarray technology allows for the simultaneous monitoring of thousands of genes expressions per sample. Unfortunately, the classification of these samples into distinct classes is often difficult as the number of genes (features) greatly exceeds the number of samples. Consequently, there is a need to investigate new, robust machine learning techniques capable of accurately classifying microarray data. In this paper, we present a coevolutionary learning classifier system based on feature set partitioning to classify gene expression data. A distributed implementation, which leverages Cloud computing technologies, is used to address the inherent computational costs of our model. The development and execution of this application was done using the Aneka middleware on the public Cloud (Amazon EC2) infrastructure. Experiments conducted using gene expression profiles demonstrates that the proposed implementation outperforms other well-known classifiers in terms of accuracy. Preliminary analysis into the impact of different Cloud setups on the performance of the classifier are also reported.

关键词： Cloud computing Gene expression Accuracy Machine learning Containers computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Particle Swarm Optimization-Based Heuristic for Scheduling Workflow Applications in Cloud computing Environments

A Particle Swarm Optimization-Based Heuristic for Scheduling...

引用

International Conference on Advanced Information Networking and Applications (AINA)

作者： Suraj Pandey Linlin Wu Siddeswara Mayura Guru Rajkumar Buyya Cloud Computing and Distributed Systems Laboratory Department of Computer Science and Software Engineering University of Melbourne Australia CSIRO Tasmanian ICT Centre Hobart Australia

ISBN: (纸本)9781424466955;9780769540184

Cloud computing environments facilitate applications by providing virtualized resources that can be provisioned dynamically. However, users are charged on a pay-per-use basis. User applications may incur large data retrieval and execution costs when they are scheduled taking into account only the `execution time'. In addition to optimizing execution time, the cost arising from data transfers between resources as well as execution costs must also be taken into account. In this paper, we present a particle swarm optimization (PSO) based heuristic to schedule applications to cloud resources that takes into account both computation cost and data transmission cost. We experiment with a workflow application by varying its computation and communication costs. We compare the cost savings when using PSO and existing `Best Resource Selection' (BRS) algorithm. Our results show that PSO can achieve: (a) as much as 3 times cost savings as compared to BRS, and (b) good distribution of workload onto resources.

关键词： Particle swarm optimization Processor scheduling Cloud computing Application software Cost function Computational efficiency Dynamic scheduling computer science Software engineering Application virtualization

来源：评论

学校读者我要写书评

暂无评论

CloudAnalyst: A CloudSim-based Visual Modeller for Analysing Cloud computing Environments and Applications

CloudAnalyst: A CloudSim-based Visual Modeller for Analysing...

引用

International Conference on Advanced Information Networking and Applications

作者： Bhathiya Wickremasinghe Rodrigo N. Calheiros Rajkumar Buyya The Cloud Computing and Distributed Systems (CLOUDS) Laboratory Department of Computer Science and Software Engineering The University of Melbourne Pontifical Catholic University of Rio Grande do Sul

ISBN: (纸本)9781424466955;9780769540184

Advances in Cloud computing opens up many new possibilities for Internet applications developers. Previously, a main concern of Internet applications developers was deployment and hosting of applications, because it required acquisition of a server with a fixed capacity able to handle the expected application peak demand and the installation and maintenance of the whole software infrastructure of the platform supporting the application. Furthermore, server was underutilized because peak traffic happens only at specific times. With the advent of the Cloud, deployment and hosting became cheaper and easier with the use of pay-peruse flexible elastic infrastructure services offered by Cloud providers. Because several Cloud providers are available, each one offering different pricing models and located in different geographic regions, a new concern of application developers is selecting providers and data center locations for applications. However, there is a lack of tools that enable developers to evaluate requirements of large-scale Cloud applications in terms of geographic distribution of both computing servers and user workloads. To fill this gap in tools for evaluation and modeling of Cloud environments and applications, we propose CloudAnalyst. It was developed to simulate large-scale Cloud applications with the purpose of studying the behavior of such applications under various deployment configurations. CloudAnalyst helps developers with insights in how to distribute applications among Cloud infrastructures and value added services such as optimization of applications performance and providers incoming with the use of Service Brokers.

关键词： Cloud computing Modeling Simulation

来源：评论

学校读者我要写书评

暂无评论

Online multiple instance learning with no regret

Online multiple instance learning with no regret

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Mu Li James T. Kwok Bao-Liang Lu Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been used in a wide range of applications including image classification, object detection and object tracking. Typically, MI algorithms are trained in a batch setting in which the whole training set has to be available before training starts. However, in applications such as tracking, the classifier needs to be trained continuously as new frames arrive. Motivated by the empirical success of a batch MI algorithm called MILES, we propose in this paper an online MI learning algorithm that has an efficient online update procedure and also performs joint feature selection and classification as MILES. Besides, while existing online MI algorithms lack theoretical properties, we prove that the proposed online algorithm has a (cumulative) regret of O(√T), where T is the number of iterations. In other words, the average regret goes to zero asymptotically and it thus achieves the same performance as the best solution in hindsight. Experiments on a number of MI classification and object tracking data sets demonstrate encouraging results.

关键词： Layout Image reconstruction Semiconductor device modeling Image segmentation Stereo vision Surface reconstruction Surface texture Surface fitting Stereo image processing Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A comparative study on two large-scale hierarchical text classification tasks' solutions

A comparative study on two large-scale hierarchical text cla...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jian Zhang Hai Zhao Bao-Liang Lu Center of Brain-Like Computing and Machine Intelligence(ÇïêDepartment of Computer Science and Engineering Shanghai Jiaotong University Shanghai China MOE-Microsoft Key Laboratory of Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Patent classification is a large scale hierarchical text classification (LSHTC) task. Though comprehensive comparisons, either learning algorithms or feature selection strategies, have been fully made in the text categorization field, few work was done for a LSHTC task due to high computational cost and complicated structural label characteristics. For the first time, this paper compares two popular learning frameworks, namely hierarchical support vector machine (SVM) and k nearest neighbor (k-NN) that are applied to a LSHTC task. Experiment results show that the latter outperforms the former in this LSHTC task, which is quite different from the usual results for normal text categorization tasks. Then this paper does a comparative study on different similarity measures and ranking approaches in k-NN framework for LSHTC task. Conclusions can be drawn that k-NN is more appropriate for the LSHTC task than hierarchical SVM and for a specific LSHTC task. BM25 outperforms other similarity measures and List Weak gains a better performance than other ranking approaches. We also find an interesting phenomenon that using all the labels of the retrieved neighbors can remarkably improve classification performance over only using the first label of the retrieved neighbors.

关键词： Patents Support vector machines Text categorization Nearest neighbor searches Training Classification algorithms Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Facial expression synthesis based on emotion dimensions for affective talking avatar

引用

Smart Innovation, systems and Technologies 2010年第1期2010卷 109-132页

作者： Zhang, Shen Wu, Zhiyong Meng, Helen M. Cai, Lianhong Key Laboratory of Pervasive Computing Ministry of Education Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing 100084 China Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at Shenzhen Tsinghua University Shenzhen China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong HKSAR Hong Kong

ISBN: (纸本)9783642126031

Facial expression is one of the most expressive ways for human beings to deliver their emotion, intention, and other nonverbal messages in face to face communications. In this chapter, a layered parametric framework is proposed to synthesize the emotional facial expressions for an MPEG4 compliant talking avatar based on the three dimensional PAD model, including pleasure-displeasure, arousal-nonarousal and dominance-submissiveness. The PAD dimensions are used to capture the high-level emotional state of talking avatar with specific facial expression. A set of partial expression parameter (PEP) is designed to depict the expressive facial motion patterns in local face areas, and reduce the complexity of directly manipulation of low-level MPEG4 facial animation parameters (FAP). The relationship among the emotion (PAD), expression (PEP) and animation (FAP) parameter is analyzed on a virtual facial expression database. Two levels of parameter mapping are implemented, namely the emotion-expression mapping from PAD to PEP, and the linear interpolation from PEP to FAP. The synthetic emotional facial expression is combined with the talking avatar speech animation in a text to audio visual speech system. Perceptual evaluation shows that our approach can generate appropriate facial expressions for subtle and complex emotions defined by PAD and thus enhance the emotional expressivity of talking avatar. © Springer-Verlag Berlin Heidelberg 2010.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Reports of the AAAI 2010 conference workshops

Reports of the AAAI 2010 conference workshops

引用

作者： Aha, David W. Boddy, Mark Bulitko, Vadim D'Avila Garcez, Artur S. Doshi, Prashant Edelkamp, Stefan Geib, Christopher Gmytrasiewicz, Piotr Goldman, Robert P. Halevy, Alon Hitzler, Pascal Isbell, Charles Josyula, Darsana Kaelbling, Leslie Pack Kersting, Kristian Kunda, Maithilee Lamb, Luis C. Marthi, Bhaskara McGreggor, Keith Mihalkova, Lilyana Nastase, Vivi Natarajan, Sriraam Provan, Gregory Raja, Anita Ram, Ashwin Riedl, Mark Russell, Stuart Sabharwal, Ashish Smaus, Jan-Georg Sukthankar, Gita Tuyls, Karl Van Der Meyden, Ron Adaptive Systems Section Naval Research Laboratory Washington DC United States Adventium Labs. Minneapolis MN United States Department of Computer Science University of Alberta Canada City University London United Kingdom University of Georgia United States University of Bremen Germany School of Informatics University of Edinburgh United Kingdom University of Illinois Chicago United States Smart Information Flow Technologies LLC Minneapolis MN United States Structured Data Group Google Research United States Department of Computer Science Wright State University Dayton OH United States School of Interactive Computing Georgia Institute of Technology Atlanta GA United States Department of Computer Science Bowie State University United States Department of Computer Science and Engineering Massachusetts Institute of Technology United States Statistical Relational Mining Group Fraunhofer IAIS Germany Department of Computer Science Federal University of Rio Grande Do sul Brazil Willow Garage Inc. CA United States Computer Science Department University of Maryland College Park United States Heidelberg Institute for Theoretical Studies Heidelberg Germany Department of Computer Science University of Wisconsin Madison United States University College Cork Ireland Cork Complex Systems Lab. Ireland Department of Software and Information Systems University of North Carolina Charlotte United States Department of Computer Science and Engineering University of California Berkeley United States Department of Computer Science Cornell University United States Institute for Computational Sustainability United States University of Freiburg Germany School of Electrical Engineering and Computer Science University of Central Florida United States Maastricht University Netherlands University of New South Wales NICTA Australia

The AAAI-10 workshop program was held on July 11-12, 2010, at the Westin Peachtree Plaza in Atlanta, Georgia. The workshop program included 13 workshops covering a wide range of topics in artificial intelligence. There were several presentations on particular formalisms for combining the levels of planning from the perspectives of classical planning, motion planning, POMDPs, search-based planning, and temporal logic-based constraints. Henry Lieberman from Massachusetts Institute of Technology Media laboratory presented work developing a platform for knowledge acquisition and usage from expert users, built upon experience with eliciting information from nonexperts in a collaborative manner. The objective of the AAAI Workshop on Goal-Directed Autonomy (GDA) was to encourage discussion and novel contributions on intelligent agents that can self-select their goals. Jeremy Baxter from QinetiQ focused on user interaction, while Nick Hawes described a goal-directed reasoning framework for controlling a mobile robot.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Hybrid uniform distribution of particle swarm optimizer

引用

IEICE Transactions on Fundamentals of Electronics, Communications and computer sciences 2010年第10期E93-A卷 1782-1791页

作者： Zhang, Junqi Tan, Ying Ni, Lina Xie, Chen Tang, Zheng Department of Computer Science and Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Qingdao China Tongji University Shanghai 200092 China Key Laboratory of Machine Perception Ministry of Education Qingdao China Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing 100871 China College of Info Sci and Engi Shandong University of Science and Technology Qingdao China Department of Intellectual Information Systems Engineering University of Toyama Toyama-shi 930-8555 Japan

Particle swarm optimizer (PSO) is a stochastic global optimization technique based on a social interaction metaphor. Because of the complexity, dynamics and randomness involved in PSO, it is hard to theoretically analyze the mechanism on which PSO depends. Statistical results have shown that the probability distribution of PSO is a truncated triangle, with uniform probability across the middle that decreases on the sides. The "truncated triangle" is also called the "Maya pyramid" by Kennedy. However, very little is known regarding the sampling distribution of PSO in itself. In this paper, we theoretically analyze the "Maya pyramid" without any assumption and derive its computational formula, which is actually a hybrid uniform distribution that looks like a trapezoid and conforms with the statistical results. Based on the derived density function of the hybrid uniform distribution, the search strategy of PSO is defined and quantified to characterize the mechanism of the search strategy in PSO. In order to show the significance of these definitions based, on the derived hybrid uniform distribution, the comparison between the defined search strategies of the classical, linear decreasing weight based PSO and the canonical constricted PSO suggested by Clerc is illustrated and elaborated. Copyright © 2010 The Institute of Electronics, Information and Communication Engineers.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Performance Tuning Towards a KVM-Based Low Latency Virtualization System

Performance Tuning Towards a KVM-Based Low Latency Virtualiz...

引用

International Conference on Information engineering and computer science (ICIECS)

作者： Baojing Zuo Kai Chen Alei Liang Haibing Guan Jun Zhang Ruhui Ma Hongbo Yang School of Software Shanghai Jiaotong University Shanghai China School of Information Security Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiaotong University Shanghai China

Utilizing virtualization technology to combine real-time operating system(RTOS)and off-the-shelf time-sharing general purpose operating system (GPOS)is attracting much more interest *** combination has the potential to provide a large application base,and to guarantee timely deterministic response to real-time applications,yet there is no convincible experimental result about its real-time *** this paper,we analyze the interrupt latency of RTOS running on Linux KVM based on some preliminary tunings,and find out System Management Interrupt (SMI) is the main factor which makes the maximum latency unideal, so we propose a method to limit the worst-case interrupt latency in an acceptable ***,we also find out that boosting priority may result in wastes of CPU resources when RTOS is not executing real-time tasks,so we design a co-scheduling mechanism to improve the CPU throughput of the GPOS system.

关键词： Linux Real time systems Kernel Tuning Throughput Hardware

来源：评论

学校读者我要写书评

暂无评论

A Translation Framework for Virtual Execution Environment on CPU/GPU Architecture

A Translation Framework for Virtual Execution Environment on...

引用

International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)

作者： Guoxing Dong Kai Chen Erzhou Zhu Yichao Zhang Zhengwei Qi Haibing Guan School of Software Shanghai Jiaotong University Shanghai China School of Information Security Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science and Engineering Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Jiaotong University Shanghai China

GPUs are many-core processors with tremendous computational power. However, as automatic parallelization has not been realized yet, developing high-performance parallel code for GPUs is still very challenging. The paper presents a novel translation framework designed for virtual execution environment based on CPU/GPU architecture. It addresses two major challenges of taking advantage of general purpose computation on graphics processing units (GPGPU) to improve performance: no rewriting the existing source code and resolving binary compatibility issues between different GPUs. The translation framework uses semi-automatic parallelization technology to port existing code to explicitly parallel programming models. It not only offers a mapping strategy from X86 platform to CUDA programming model, but also synchronizes the execution between the CPU and the GPUs. The input to our translation framework is parallelizable part of the program within binary code. With an additional information related to the parallelizable part, the translation framework transforms the sequential code into PTX code and execute it on GPUs. Experimental results on several programs from CUDA SDK Code Samples and Parboil Benchmark Suite show that our translation framework could achieve very high performance, even up to several tens of times speedup over the X86 native version.

关键词： Graphics processing unit Registers Kernel Instruction sets Driver circuits Programming computer architecture

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：