| 一种改进的基于正区域的决策树算法 |
| |
| 引用本文： | 高静,杨炳儒,徐章艳,宋威.一种改进的基于正区域的决策树算法[J].计算机科学,2008,35(5):138-142. |
| |
| 作者姓名： | 高静 杨炳儒 徐章艳 宋威 |
| |
| 作者单位： | 1. 北京科技大学信息工程学院,北京,100083
2. 北京科技大学信息工程学院,北京,100083;广西师范大学计算机系,桂林,541004 |
| |
| 基金项目： | 国家自然科学基金
,
教育部科学技术研究重点项目
,
北京市自然科学基金 |
| |
| 摘 要： | 首先分析了基于正区域、基于粗糙边界和基于依赖度的属性选择标准的关系,并证明了这三种属性选择标准彼此等价.然后以正区域的属性选择标准为代表,分析了、基于正区域的决策树生成算法的优点和不足.针对这些不足,给出了一种新的属性选择标准,即基于伴随正区域的属性选择标准.用新的属性选择标准生成的决策树一般具有叶子数目较少,叶子的平均深度也较小,且叶子具有较强的泛化能力.最后,用一实例说明了新的属性选择标准的优越性.
|
| 关 键 词： | 决策树 粗糙集 正区域 粗糙边界 依赖度 伴随正区域 |
Improved Algorithm for Decision Tree Based on Positive Region |
| |
| GA Jing,YANG Bing-ru,XU Zhang-yan,SONG Wei.Improved Algorithm for Decision Tree Based on Positive Region[J].Computer Science,2008,35(5):138-142. |
| |
| Authors: | GA Jing YANG Bing-ru XU Zhang-yan SONG Wei |
| |
| Affiliation: | GAO Jing~1 YANG Bing-ru~1 XU Zhang-yan~(1,2) SONG Wei~1 (School of Information Engineering,University of Science , Technology Beiiing,Beijing 100083,China)~1(Department of Computer,Guanxi Normal University,Guangxi 541004,China)~2 |
| |
| Abstract: | In this paper,the relationship of selected attribute standards between based on positive region,based on rough bound and based on attribute dependency is firstly analyzed.At the same time,it is proved that the three kinds of selected attribute standards are equivalent to each other.And then advantages and disadvantages of algorithm for constructing decision tree based on positive region are analyzed.Meanwhile,aiming at these disadvantages,a new se- lected attribute standard based on adjoint positive region ... |
| |
| Keywords: | Decision tree Rough set Positive region Rough bound Attribute dependency Adjoint positive region |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
