| 一种粗糙集属性约简算法 |
| |
| 引用本文： | 李侃,刘玉树,王蕾. 一种粗糙集属性约简算法[J]. 计算机工程与应用, 2002, 38(5): 15-19,78 |
| |
| 作者姓名： | 李侃 刘玉树 王蕾 |
| |
| 作者单位： | 北京理工大学计算机系,北京100081 |
| |
| 基金项目： | 部级预研项目(编号:104050202(5)) |
| |
| 摘 要： | 该文针对RoughSet理论的属性约简进行了研究。利用RoughSet和信息论的相关知识,研究了通过可辨识矩阵求得属性约简集,并利用条件熵来计算属性约简集中属性间的相关性,其平均值最小的属性集即为求得的最佳属性约简的结果。实验证明,它可以取得比较理想的效果。最后利用该文的方法给出了对UCI机器学习数据库的例子的约简结果。
|
| 关 键 词： | Rough Set理论 属性约简 可辨识矩阵 条件熵 |
| 文章编号： | 1002-8331-(2002)05-0015-02 |
An Approach for Attribute Reduction Based on Rough Set Theory |
| |
| Li Kan Liu Yushu Wang Lei. An Approach for Attribute Reduction Based on Rough Set Theory[J]. Computer Engineering and Applications, 2002, 38(5): 15-19,78 |
| |
| Authors: | Li Kan Liu Yushu Wang Lei |
| |
| Abstract: | This paper discusses the attribute reduction in Rough Set theory.Using the knowledge of Rough Set and information theory,the paper gets attribute reduction set by discernibility matrix,and compute s relevance of attributes through conditional entropy.The best attribute reduction is the set which value is the minimum of average of relevance of attributes.The experiment shows that it can get better effectivity.Finally,it get reduction results of UCI databases using the algorithm. |
| |
| Keywords: | Rough Set theory attribute reduction discernibility matrix conditional entropy |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
