检索结果-南通市图书馆

Improving bagging performance through multi-algorithm ensembles

Frontiers of Computer Science 2012年第5期6卷 498-512页

作者： Kuo-Wei HSU jaideep srivastava Department of Computer Science Chengchi University Taipei 11605 China Department of Computer Science and Engineering University of Minnesota Minneapolis MN 55455 USA

Working as an ensemble method that establishes a committee of classifiers first and then aggregates their out- comes through majority voting, bagging has attracted consid- erable research interest and been applied in various applica- tion domains. It has demonstrated several advantages, but in its present form, bagging has been found to be less accurate than some other ensemble methods. To unlock its power and expand its user base, we propose an approach that improves bagging through the use of multi-algorithm ensembles. In a multi-algorithm ensemble, multiple classification algorithms are employed. Starting from a study of the nature of diver- sity, we show that compared to using different training sets alone, using heterogeneous algorithms together with different training sets increases diversity in ensembles, and hence we provide a fundamental explanation for research utilizing het- erogeneous algorithms. In addition, we partially address the problem of the relationship between diversity and accuracy by providing a non-linear function that describes the relation- ship between diversity and correlation. Furthermore, after re- alizing that the bootstrap procedure is the exclusive source of diversity in bagging, we use heterogeneity as another source of diversity and propose an approach utilizing heterogeneous algorithms in bagging. For evaluation, we consider several benchmark data sets from various application domains. The results indicate that, in terms of Fl-measure, our approach outperforms most of the other state-of-the-art ensemble meth- ods considered in experiments and, in terms of mean margin, our approach is superior to all the others considered in experiments.

关键词： bagging classification diversity ensemble

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Efficient Aggregation Algorithms on Very LargeCompressed Data Warehouses

引用

Journal of Computer Science & Technology 2000年第3期15卷 213-229页

作者：李建中李英姝 jaideep srivastava DepartmentofComputerScienceandEngineering HarbinInstituteofTechnologyHatrbin150001P.R.China

Multidimensional aggregation is a dominant operation on data ware-houses for on-line analytical processing (OLAP). Many efficient algorithms to compute multidimensional aggregation on relational database based data warehouseshave been developed. However, to our knowledge, there is nothing to date in theliterature about aggregation algorithms on multidimensional data warehouses thatstore datasets in multidimensional arrays rather than in tables. This paper presentsa set of multidimensional aggregation algorithms on very large and compressed mul-tidimensional data warehouses. These algorithms operate directly on compresseddatasets in multidimensional data warehouses without the need to first decompressthem. They are applicable to a variety of data compression methods. The algorithmshave differefit performance behavior as a function of dataset parameters, sizes of out-puts and main memory availability. The algorithms are described and analyzed withrespect to the I/O and CPU costs. A decision procedure to select the most efficientalgorithm, given an aggregation request, is also proposed. The analytical and ex-perimental results show that the algorithms are more efficient than the traditionalaggregation algorithms.

关键词： OLAP aggregation data warehouse

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

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：