检索结果-内蒙古大学图书馆

IEEE international conference on Cloud Computing, CLOUD

作者： Linh Phan Kaikai Liu Computer Engineering Department San Jose State University (SJSU) San Jose CA USA

Cloud virtualization and multi-tenant networking provide Infrastructure as a Service (IaaS) providers a new and innovative way to offer on-demand services to their customers, such as easy provisioning of new applications and better resource efficiency and scalability. However, existing data-intensive intelligent applications require more powerful processors, higher bandwidth and lower-latency networking service. In order to boost the performance of computing and networking services, as well as reduce the overhead of software virtualization, we propose a new data center network design based on OpenStack. Specifically, we map the OpenStack networking services to the hardware switch and utilize hardware-accelerated L2 switch and L3 routing to solve the software limitations, as well as achieve software-like scalability and flexibility. We design our prototype system via the Arista Software-Defined-Networking (SDN) switch and provide an automatic script which abstracts the service layer that decouples OpenStack from the physical network infrastructure, thereby providing vendor-independence. We have evaluated the performance improvement in terms of bandwidth, delay, and system resource utilization using various tools and under various Quality-of-Service (QoS) constraints. Our solution demonstrates improved cloud scaling and network efficiency via only one touch point to control all vendors' devices in the data center.

关键词： Switches Cloud computing Quality of service Neutrons Software Hardware Servers

来源：评论

学校读者我要写书评

暂无评论

Automatically Design Distance Functions for Graph-based Semi-Supervised learning 16

Automatically Design Distance Functions for Graph-based Semi...

引用

16th IEEE international conference on Trust, Security and Privacy in Computing and Communications / the 11th IEEE international conference on Big data Science and engineering / the 14th IEEE international conference on Embedded Software and Systems

作者： Miquilini, Patricia Rossi, Rafael G. Quiles, Marcos G. de Melo, Vinicius V. Basgalupp, Marcio P. Univ Fed Sao Paulo Inst Sci & Technol Sao Paulo Brazil Univ Fed Mato Grosso do Sul Campo Grande MS Brazil

ISBN: (纸本)9781509049066

Automatic data classification is often performed by supervised learning algorithms, producing a model to classify new instances. Reflecting that labeled instances are expensive, semi supervised learning (SSL) methods prove to be an alternative to performing data classification, once the learning demands only a few labeled instances. there are many SSL algorithms, and graph-based ones have significant features. In particular, graph-based models grant to identify classes of different distributions without prior knowledge of statistical model parameters. However, a drawback that might influence their classification performance relays on the construction of the graph, which requires the measurement of distances (or similarities) between instances. Since a particular distance function can enhance the performance for some data sets and decrease to others, here, we introduce a novel approach, called GEAD, a Grammatical Evolution for Automatically designing Distance functions for Graph-based semi-supervised learning. We perform extensive experiments with 100 public data sets to assess the performance of our approach, and we compare it with traditional distance functions in the literature. Results show that GEAD is capable of designing distance functions that significantly outperform the baseline manually-designed ones regarding different predictive measures, such as Micro-F-1, and Macro-F-1.

关键词： Semisupervised learning Algorithm design and analysis Supervised learning Classification algorithms Euclidean distance data models

来源：评论

学校读者我要写书评

暂无评论

Intermediate data Caching Optimization for Multi-Stage and Parallel Big data Frameworks

Intermediate Data Caching Optimization for Multi-Stage and P...

引用

IEEE international conference on Cloud Computing, CLOUD

作者： Zhengyu Yang Danlin Jia Stratis Ioannidis Ningfang Mi Bo Sheng Dept. of Electrical & Computer Engineering Northeastern University Boston MA Dept. of Computer Science University of Massachusetts Boston Boston MA

In the era of big data and cloud computing, large amounts of data are generated from user applications and need to be processed in the datacenter. data-parallel computing frameworks, such as Apache Spark, are widely used to perform such data processing at scale. Specifically, Spark leverages distributed memory to cache the intermediate results, represented as Resilient Distributed datasets (RDDs). this gives Spark an advantage over other parallel frameworks for implementations of iterative machine learning and data mining algorithms, by avoiding repeated computation or hard disk accesses to retrieve RDDs. By default, caching decisions are left at the programmer's discretion, and the LRU policy is used for evicting RDDs when the cache is full. However, when the objective is to minimize total work, LRU is woefully inadequate, leading to arbitrarily suboptimal caching decisions. In this paper, we design an algorithm for multi-stage big data processing platforms to adaptively determine and cache the most valuable intermediate datasets that can be reused in the future. Our solution automates the decision of which RDDs to cache: this amounts to identifying nodes in a direct acyclic graph (DAG) representing computations whose outputs should persist in the memory. Our experiment results show that our proposed cache optimization solution can improve the performance of machine learning applications on Spark decreasing the total work to recompute RDDs by 12%.

关键词： Sparks Task analysis Optimization Machine learning Clustering algorithms Companies

来源：评论

学校读者我要写书评

暂无评论

Large-scale multi-label ensemble learning on Spark 16

Large-scale multi-label ensemble learning on Spark

引用

作者： Gonzalez-Lopez, Jorge Cano, Alberto Ventura, Sebastian Virginia Commonwealth Univ Dept Comp Sci Richmond VA 23284 USA Univ Cordoba Dept Comp Sci Cordoba Spain

ISBN: (纸本)9781509049066

Multi-label learning is a challenging problem which has received growing attention in the research community over the last years. Hence, there is a growing demand of effective and scalable multi-label learning methods for larger datasets both in terms of number of instances and numbers of output labels. the use of ensemble classifiers is a popular approach for improving multi-label model accuracy, especially for datasets with high-dimensional label spaces. However, the increasing computational complexity of the algorithms in such ever-growing high dimensional label spaces, requires new approaches to manage data effectively and efficiently in distributed computing environments. Spark is a framework based on MapReduce, a distributed programming model that offers a robust paradigm to handle large-scale datasets in a cluster of nodes. this paper focuses on multi-label ensembles and proposes a number of implementations through the use of parallel and distributed computing using Spark. Additionally, five different implementations are proposed and the impact on the performance of the ensemble is analyzed. the experimental study shows the benefits of using distributed implementations over the traditional single-node single-thread execution, in terms of performance over multiple metrics as well as significant speedup tested on 29 benchmark datasets.

关键词： Multi-label learning Ensemble learning Distributed computing Apache Spark Big data

来源：评论

学校读者我要写书评

暂无评论

Software Effort Estimation using Machine learning Techniques 7

Software Effort Estimation using Machine Learning Techniques

引用

7th international conference on Cloud Computing, data Science and engineering (Confluence)

作者： Monika Sangwan, Om Prakash Guru Jambheshwar Univ Sci & Technol Dept Comp Sci & Engn Hisar Haryana India

ISBN: (纸本)9781509035199

Effort Estimation is a very important activity for planning and scheduling of software project life cycle in order to deliver the product on time and within budget. Machine learning techniques are proving very useful to accurately predict software effort values. this paper presents a review of various machine-learning techniques using in estimation of software project effort namely Artificial Neural Network, Fuzzy logic, Analogy estimation etc. Machine learning techniques consistently predicting accurate results because of its learning natures form previously completed projects. this paper summarizes that each technique has its own features and behave differently according to environment so no technique can be preferred over each other.

关键词： Effort estimation literature review comparative analysis machine learning MMRE

来源：评论

学校读者我要写书评

暂无评论

11th Curtin University Technology, Science and engineering (CUTSE) international conference

引用

IOP conference Series: Materials Science and engineering 2019年第1期495卷

Preface the 11th Curtin University Technology, Science and engineering (CUTSE) international conference was held on 26-28 November 2018 at Curtin University Malaysia at Miri, Sarawak, Malaysia. this year's conference theme is Digital Transformation and Innovations in the Digital Era. Technological innovations using augmented and virtual reality, internet of things (IoTs), robotics and big data will transform the way we live and work. this digital transformation provides the basis for future jobs, resource efficiency and economic activities in the new digital era. CUTSE 2018 provides an excellent platform for researchers, engineers, scientists, academicians, industrial experts, technological enthusiast as well as students of higher learning institutions to share and deliberate on the latest and relevant theories, practices and R&D findings related to technological innovations. the wide range of topics covered in this conference includes communication, electronics, intelligent systems, machine vision, security, technology trends, energy and environment, engineering science fundamentals, structures and materials, geology and e-learning. this CUTSE 2018 proceeding contains 115 selected papers that have been accepted for presentation on the conference. All articles were subjected to revisions by a minimum of two expert reviewers appointed by the conference technical committee. First, we wish to record our gratitude to all reviewers, both local and international, for their time and effort in reviewing the papers. their feedbacks to the authors have been excellent and useful to ensure the high quality of papers for the conference. Special thanks to the publication team for their efforts in preparing this proceeding. Last but not least, we would like to thank also the organizing committee members for their hard work, cooperation and suggestions in ensuring the success of this conference. Editors Dr. M.V. Prasanna Dr. Ling Huo Chong Dr. R. Nagarajan Dr. Hieng Ho Lau

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning Approach to Task Ranking 14

Machine Learning Approach to Task Ranking

引用

14th international Symposium on Pervasive Systems, Algorithms and Networks (I-SPAN) / 11th international conference on Frontier of Computer Science and Technology (FCST) / 3rd international Symposium of Creative Computing (ISCC)

作者： Ricky, Michael Yoseph Hendric, Spits Warnars Harco Leslie Budiharto, Widodo Abbas, Bahtiar Saleh Bina Nusantara Univ Jakarta Indonesia

ISBN: (纸本)9781538608401

there are variety of methods and algorithms that can be used to overcome the ranking problem. Task ranking is one of the problems that can be solved by using a machine learning algorithm ranking problem. this work focuses on finding the right approach and corresponding algorithms in the process of ranking to be able to help people in determining which jobs have a higher priority than others. Our approach is to compare several algorithms performed in the process of ranking that are Bipartite Ranking, k-partite Ranking, and Ranking by pairwise comparison. We're used questionnaires and deployment of prototype of intelligent Personal Assistant Agent to apply the appropriate algorithm in intelligence agent in arranging task priority in daily activity that must be done by the users. After training dataset and evaluate the validation dataset using NDCG, it is found that the collaborative ranking used have a more accurate value / lower variance test evaluation because it uses a large dataset and smaller training dataset. We found that labeling for more than 2 values it is not recommended to use a bipartite ranking if there are many repetitive data, both k-partite ranking and rank by pairwise comparison are able to be used for multi-dimensional data labeling.

关键词： Task Ranking Bipartite Ranking k-partite Ranking Ranking by pairwise comparison Intelligence Agent

来源：评论

学校读者我要写书评

暂无评论

Sequential and Unsupervised Document Authorial Clustering Based on Hidden Markov Model 16

Sequential and Unsupervised Document Authorial Clustering Ba...

引用

作者： Aldebei, Khaled Farhood, Helia Jia, Wenjing Nanda, Priyadarsi He, Xiangjian Univ Technol Sydney Global Big Data Technol Ctr Sydney NSW Australia Minjiang Univ Fujian Prov Key Lab Informat Proc & Intelligent C Fuzhou 350121 Fujian Peoples R China

ISBN: (纸本)9781509049066

Document clustering groups documents of certain similar characteristics in one cluster. Document clustering has shown advantages on organization, retrieval, navigation and summarization of a huge amount of text documents on Internet. this paper presents a novel, unsupervised approach for clustering single-author documents into groups based on authorship. the key novelty is that we propose to extract contextual correlations to depict the writing style hidden among sentences of each document for clustering the documents. For this purpose, we build an Hidden Markov Model (HMM) for representing the relations of sequential sentences, and a two-level, unsupervised framework is constructed. Our proposed approach is evaluated on four benchmark datasets, widely used for document authorship analysis. A scientific paper is also used to demonstrate the performance of the approach on clustering short segments of a text into authorial components. Experimental results show that the proposed approach outperforms the state-of-the-art approaches.

关键词： Hidden Markov models Correlation Writing Estimation Clustering algorithms Decoding TV

来源：评论

学校读者我要写书评

暂无评论

Distributed cooperative hierarchical control for DC microgrid

Distributed cooperative hierarchical control for DC microgri...

引用

the 11th IET international conference on Advances in Power System Control, Operation and Management (APSCOM 2018)

作者： Chunyuan Guo Li Qiu Bo Zhang Jianping Yuan College of Mechatronics and Control Engineering Shenzhen University Shenzhen China Intelligent Operation Laboratory Research Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China

ISBN: (数字)9781839530043

this paper proposes a distributed cooperative hierarchical control scheme for DC microgrid based on consensus algorithm. the control architecture includes primary control, secondary control and tertiary control, which secondary controller uses a consensus algorithm. Four power generators are a cooperative relationship with each other through the control layer. the controller of each converter only exchanges data with the adjacent converter on the cyber layer communication network. When the internal power of the microgrid is higher than the external system, the tertiary controller can be used to deliver energy to the external power grid and achieve power optimization between the microgrids. Finally, through the experimental simulation, it is verified that hierarchical control can effectively regulate the DC microgrid bus voltage in the target range and achieve power exchange management with the external power grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AutoLearn - automated Feature Generation and Selection 17

AutoLearn - Automated Feature Generation and Selection

引用

17th IEEE international conference on data Mining (ICDMW)

作者： Kaul, Ambika Maheshwary, Saket Pudi, Vikram Int Inst Informat Technol Kohli Ctr Intelligent Syst Data Sci & Analyt Ctr Hyderabad Andhra Pradesh India

ISBN: (纸本)9781538638354

In recent years, the importance of feature engineering has been confirmed by the exceptional performance of deep learning techniques, that automate this task for some applications. For others, feature engineering requires substantial manual effort in designing and selecting features and is often tedious and non-scalable. We present AutoLearn, a regression-based feature learning algorithm. Being data-driven, it requires no domain knowledge and is hence generic. Such a representation is learnt by mining pairwise feature associations, identifying the linear or non-linear relationship between each pair, applying regression and selecting those relationships that are stable and improve the prediction performance. Our experimental evaluation on 18 UC Irvine and 7 Gene expression datasets, across different domains, provides evidence that the features learnt through our model can improve the overall prediction accuracy by 13.28%, compared to original feature space and 5.87% over other top performing models, across 8 different classifiers without using any domain knowledge.

关键词： Prediction algorithms Correlation Algorithm design and analysis Transforms Predictive models data models

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：