检索结果-内蒙古大学图书馆

17th IEEE International Conference on data Mining Workshops, ICDM Workshops 2007

作者： Shi, Yong Tian, Yingjie Chen, Xiaojun Zhang, Peng College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 United States CAS Research Center on Fictitious Economy and Data Sciences Beijing 100080 China Department of Mathematical Sciences Hirosaki University Hirosaki 036-8561 Japan School of Information Science and Engineering Graduate University of CAS Beijing 100080 China

ISBN: (纸本)0769530192

Although multiple criteria mathematical programs (MCMP), as alternative methods of classification, have been used in various real-life data mining problems, its mathematical structure of solvability are still challenge-able. This paper proposes a regularized multiple criteria linear program (RMCLP) for classification. It first adds some regularization terms in the objective function of the known multiple criteria linear program (MCLP) model for possible existence of solution. Then the paper describes the mathematical framework of the solvability. Finally, a series of experimental tests are conducted to illustrate the performance of the proposed RMCLP with the existing methods: MCLP, multiple criteria quadratic program (MCQP), and support vector machine (SVM). The results of four publicly available datasets and a real-life credit dataset all show that RMCLP is a competitive method in classification. © 2007 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving data mining of medical data using data separation-based techniques

引用

data Science Journal 2007年第SUPPL.期6卷 S429-S434页

作者： Gang, Kou Yi, Peng Yong, Shi Zhengxin, Chen College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 United States Chinese Academy of Sciences Research Center on Data Technology and Knowledge Economy Graduate University Beijing 100080 China

data mining is concerned with the extraction of useful knowledge from various types of data. Medical data mining has been a popular data mining topic of late. Compared with other data mining areas, medical data mining has some unique characteristics. Because medical files are related to human subjects, privacy concerns are taken more seriously than other data mining tasks. This paper applied data separation-based techniques to preserve privacy in classification of medical data. We take two approaches to protect privacy: one approach is to vertically partition the medical data and mine these partitioned data at multiple sites;the other approach is to horizontally split data across multiple sites. In the vertical partition approach, each site uses a portion of the attributes to compute its results, and the distributed results are assembled at a central trusted party using a majority-vote ensemble method. In the horizontal partition approach, data are distributed among several sites. Each site computes its own data, and a central trusted party is responsible to integrate these results. We implement these two approaches using medical datasets from UCI KDD archive and report the experimental results.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Second Order Cone Programming Formulations for Robust Support Vector Ordinal Regression Machine

Second Order Cone Programming Formulations for Robust Suppor...

引用

第一届最优化与系统生物学国际研讨会

作者： Zhi-Xia Yang Ying-Jie Tian Nai-Yang Deng College of Science China Agricultural University College of Mathematics and System Science Xinjiang University Chinese Academy of Sciences Research Center on Data Technology & Knowledge Economy

Support vector ordinal regression machine (SVORM) is an effective method for ordinal regression problem. Up to now, the SVORM implicitly assumes the training data to be known exactly. However, in practice, the training data subject to measurement noise. In this paper, we propose a robust version of SVORM. The robustness of the proposed method is validated by our preliminary numerical experiments.

关键词： Second Order Cone Programming Formulations for Robust Support Vector Ordinal Regression Machine Vector

来源：评论

学校读者我要写书评

暂无评论

A study on the relationship between ERP logic and direct consume coefficient of I/O table

IFIP Advances in Information and Communication Technology

引用

IFIP Advances in Information and Communication technology 2007年 254卷 145-152页

作者： Zhang, Lingling Li, Jtm Wang, Qin Tong, Rencheng Zhang, Yuejin Li, Xingsen School of Management Graduate University of Chinese Academy of Sciences Chinese Academy of Sciences Research Center on Data Technology and Knowledge Economy Beijing100080 China Institute of Computing Technology of the Chinese Academy of Sciences Beijing100080 China

ISBN: (纸本)9781475705638

The paper analyzes necessity and possibility of integrating ERP with Input-Output technology (I/O). It studies relationship between ERP logic and the direct consume coefficient of manufacture enterprise I/O table, and proves that it is feasible to convert basic data of ERP to direct consume coefficient and entire consume coefficient of enterprise I/O table. It also proves that it is convenient to use ERP basic data to make manufacture enterprise I/O table, and to analyze and improve decision making. © 2007, (publisher). All rights reserved.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Network Lifetime of Application-Specific Randomly Deployed Wireless Sensor Networks in Arbitrary Sensor Density

Network Lifetime of Application-Specific Randomly Deployed W...

引用

International Conference on Computer and Information Science (ACIS)

作者： Jing He Yanchun Zhang Guangyan Huang Yong Shi School of Computer Science and Mathematics Victoria University Melbourne VIC Australia Research Center on Data Technology and Knowledge Economy Chinese Academy and Sciences Beijing China Institute of Software Chinese Academy and Sciences Beijing China

In many cases, sensors are randomly deployed in wireless sensor networks (WSN), called sensor- randomly-deployed WSN (SRD WSN). Several cluster-based routing protocols are provided to maximize network lifetime of SRD WSN in different sensor densities. LEACH performs better than direct routing in the density of 0.01. BCDCP excels LEACH in the density of 0.05. DMSTRP outperforms LEACH and BCDCP in the density of. However, simulation results under one or two kinds of sensor densities are not strong enough to prove the optimum of the routing protocols. In this paper, we give the general formulas to compute the network lifetimes of the above three routing protocols, discuss their optimal number of clusters, and compare their optimal network lifetime in arbitrary sensor densities. These formulas can provide more general design guidelines applicable to SRD WSN than simulation results under only one or two kinds of sensor densities.

关键词： Wireless sensor networks Routing protocols Energy dissipation Computer networks Wireless communication Energy resources Computer science Mathematics Australia Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A RBF classifier with supervised center selection and weighted norm

A RBF classifier with supervised center selection and weight...

引用

作者： Liu, Rong Shi, Yong Research Center on Data Technology and Knowledge Economy CAS Department of Mathematics Beijing 100080 China Research Center on Data Technology and Knowledge Economy CAS Management School Beijing 100080 China

ISBN: (纸本)0769527027

A variation of RBF (radial basis function) classifier based on supervised (or adaptively) ceneter selection and weighted norm is formulated and then tested in labeling overlapped data sets generated from two binormal distributions in this paper. Besides its simplicity, the experimental results and the comparsions to other classifiers suggest that this method is significant in capability owing to offering reasonable classifications with mild computation costs. Moreover, this variation outperforms the RBF based on exact interpolation not just in accuracy but in efficiency as well. © 2006 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Special issue for Xiangshan Sciences Forum on frontier studies on data technology and knowledge economy

Special issue for Xiangshan Sciences Forum on frontier studi...

引用

作者： Yong, Shi Chinese Academy of Sciences Research Center on Data Technology and Knowledge Economy Beijing 100080 China

来源：评论

学校读者我要写书评

暂无评论

A DYNAMIC APPROACH TO CALCULATE SHADOW PRICES OF WATER RESOURCES FOR NINE MAJOR RIVERS IN CHINA

引用

Journal of Systems Science & Complexity 2006年第1期19卷 76-87页

作者： Jing HE Xikang CHEN Yong SHI Research Center on Data Technology and Knowledge Economy Chinese Academy of Sciences Beijing 100080 Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100080 China

China is experienciug from serious water issues. There are many differences among the Nine Major Rivers basins of China in the construction of dikes, reservoirs, floodgates, flood discharge projects, flood diversion projects, water ecological constructions, water conservancy management, etc. The shadow prices of water resources for Nine Major Rivers can provide suggestions to the Chinese goverument. This article develops a dynamic shadow prices approach based on a multipeziod input-output optimizing model. Unlike previous approaches, the new model is based on the dynamic computable general equilibrium （DCGE） model to solve the problem of marginal long-term prices of water resources. First, definitions and algorithms of DCGE are elaborated. Second, the results of shadow prices of water resources for Nine Major Rivers in 1949-2050 in China using the National Water Conservancy input-holdiug-out in table for Nine Major Rivers in 1999 are listed. A conclusion of this article is that the shadow prices of water resources for Nine Major Rivers are largely based on the extent of scarcity. Selling prices of water resources should be revised via the usage of parameters representing shadow prices.

关键词： Computable general equilibrium dynamic input-output analysis nine major rivers shadow prices water development.

来源：评论

学校读者我要写书评

暂无评论

Unsupervised and semi-supervised two-class support vector machines

Unsupervised and semi-supervised two-class support vector ma...

引用

作者： Zhao, Kun Tian, Ying-Jie Deng, Nai-Yang College of Science China Agricultural University China Chinese Academy of Sciences Research Center on Data Technology and Knowledge Economy China

ISBN: (纸本)0769527027

Support Vector Machines have been a dominant learning technique for almost ten years, moreover they have been applied to supervised learning problems. Recently two-class unsupervised and semi-supervised classification problems based on Bounded C-Support Vector Machines are relaxed to semi-definite programming[7]. In this paper we will present another version to two-class unsupervised and semi-supervised classification problems based on Bounded ν-Support Vector Machines, which trained by convex relaxation of the training criterion: find a labeling that yield a maximum margin on the training data. But the problems have difficulty to compute, we will find their semi-definite relaxations that can approximate them well. Experimental results show that our new unsupervised and semi-supervised classification algorithms often obtain more accurate results than other unsupervised and semi-supervised methods. © 2006 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Evaluation of cluster analysis algorithms enhanced by using R*-Trees

Evaluation of cluster analysis algorithms enhanced by using ...

引用

IEEE International Conference on Computer Systems and Applications, 2006

作者： Jiaxiong, Pi Yong, Shi Zhengxin, Chen College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 Chinese Academy of Sciences Research Center on Data Technology and Knowledge Economy Graduate University Beijing 100080 China

ISBN: (纸本)1424402123

R* tree is a useful data structure for handling spatial data. However, although objects stored in the same R* tree leaf node enjoys spatial proximity, it is well-known that R* trees cannot be used directly for cluster analysis. Nevertheless, R* tree's indexing feature can be used to assist existing cluster analysis methods, thus enhancing their performance or cluster quality. In this paper, we explore how to use R* trees to improve well-known K-means and hierarchical clustering methods. Based on R*-Tree's feature of indexing Minimum Bounding Box (MBB) according to spatial proximity, we extend R*-Tree's application to cluster analysis of time series. Two improved algorithms, KMeans-R and Hierarchy-R, are proposed. The performance of these two methods is evaluated against K-Means and K-Means with sampling technique (KMeans-S) using similarity-oriented, supervised measures of cluster validity. Rand Index (RI), Adjusted Rand Index (ARI) and Information Gain (IG) are used as evaluation measures in our experiments. Compared with K-Means and KMeans-S, the clustering results from different data sets have shown that KMeans-R and Hierarchy-R have achieved better clustering quality. © 2006 IEEE.

关键词： Trees (mathematics)

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：