| 一种基于粗糙集属性度量的集成分类器 |
| |
| 作者姓名： | 王永生 郑雪峰 |
| |
| 作者单位： | 北京科技大学计算机与通信工程学院，北京100083;北京科技大学材料领域知识工程北京市重点实验室，北京100083;北京科技大学计算机与通信工程学院，北京100083;北京科技大学材料领域知识工程北京市重点实验室，北京100083 |
| |
| 基金项目： | 材料领域知识工程北京市重点实验室(北京科技大学)2012年度阶梯计划资助项目(Z121101002812005)国家自然科学基金项目(61163025) |
| |
| 摘 要： | 为了准确度量属性的重要性,从基于粗糙集的属性度量视角,提出一种基于混合度量机制的属性评价方法,该方法从不同的信息粒度分析属性的重要性.在混合度量机制中,根据数据分布特点引入参数权重因子.在此基础上,构造一种基于粗糙集属性度量机制的集成分类器.通过实验结果和比较分析表明,所提出的方法能有效地降低数据的属性维度,相比较于单一属性度量准则,分类器具有更好的分类性能.
|
| 关 键 词： | 数据挖掘 属性 度量 分类器 粗糙集理论 |
| 收稿时间： | 2015-08-03 |
An ensemble classifier based on attribute measurement of rough sets |
| |
| Affiliation: | 1. School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China;2. Beijing Key Laboratory of Knowledge Engineering for Materials Science, University of Science and Technology Beijing 100083, China |
| |
| Abstract: | From the viewpoint of the attribute measurement of rough sets,a new attribute measurement based on the hybrid metric mechanism was provided to accurately evaluate the significance of attributes. This proposed attribute measurement analyzes the significance of attributes from different levels of information granularity. In addition,a parameter weighting factor was introduced to the attribute measurement according to the characteristics of data distribution. On this basis,an ensemble classifier was constructed based on the proposed attribute measurement mechanism in rough sets. Experimental results and comparative analysis show that the proposed method can effectively reduce the attribute dimension of data. Compared with the single attribute measurement,the proposed method has a better classification performance. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《》浏览原始摘要信息 |
|
点击此处可从《》下载全文 |
|
