| 相容RS理论中的属性约简算法 |
| |
| 引用本文： | 王珏,刘三阳,等.相容RS理论中的属性约简算法[J].计算机科学,2003,30(2):161-162. |
| |
| 作者姓名： | 王珏 刘三阳 |
| |
| 作者单位： | 西安电子科技大学理学院,西安,710071 |
| |
| 基金项目： | 国家自然科学基金(69972036)，陕西省自然科学基金(2000SL03) |
| |
| 摘 要： | 1.引言 Skowron等提出的相容RS理论是经典的RS理论的推广,它用相容关系(tolerance)代替原来的不可分辨关系(indiscernibility),可以发现属性值之间的相似性、滤除属性值之间的微小偏差,提高系统决策的鲁棒性和决策效率。Duntsch、Gediga等从信息论的角度建立了粗糙集理论中的知识与信
|
| 关 键 词： | 相容RS理论 属性约简算法 粗糙集理论 信息熵 人工智能 |
Tolerant Rough Set Based Attribute Reduction Algorithm |
| |
| WANG Jue LIU San-Yang LIU Zhen-Hua.Tolerant Rough Set Based Attribute Reduction Algorithm[J].Computer Science,2003,30(2):161-162. |
| |
| Authors: | WANG Jue LIU San-Yang LIU Zhen-Hua |
| |
| Abstract: | In this paper, a novel definition of entropy is introduced. It is used for measuring the uncertainty of roughness of knowledge in tolerant rough sets- In addition,we prove that the entropy of knowledge decreases monotonously as the granularity of information becomes smaller. Then, a new reduction algorithm based on entropy is developed. Simulation results show that the algorithm can find the minimal reduction in most cases. |
| |
| Keywords: | Tolerant RS theory Tolerance relation Information granularity Information entropy Reduction of attribute |
| 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 |
