基于spearman秩相关的序值决策系统约简

计算机应用 ›› 2009, Vol. 29 ›› Issue (07): 1758-1759.

基于spearman秩相关的序值决策系统约简

祁云嵩¹,谢军²

1. 江苏科技大学
2. 江苏大学

收稿日期:2009-01-05 修回日期:2009-02-27 发布日期:2009-07-01 出版日期:2009-07-01
通讯作者: 祁云嵩
基金资助:
国家级基金

Reduction in ordered decision system based on spearman rank correlations

Received:2009-01-05 Revised:2009-02-27 Online:2009-07-01 Published:2009-07-01

摘要/Abstract

摘要：

约简是知识发现的重要过程。经典的基于等价关系的粗糙集理论,没有考虑系统取值的序值性，并且对数据噪声较为敏感。提出了一个基于spearman秩相关分析的序值决策系统约简方法，该方法通过各属性对被决策个体的spearman秩次的影响来确定约简结果。实验结果表明，该方法不但考虑了系统属性值的序值关系，并且对数据噪声不敏感，因而更符合实际应用的要求。

关键词: 粗糙集;知识约简;序值决策系统;spearman秩相关

Abstract:

Reduction is an important knowledge discovery process. The original rough set theory based on equivalence relations does not consider attributes with preferenceordered domains and is sensitive to data noise. Based on spearman rank correlation analysis, a method was introduced to reduction ordered decision systems. This method computes the reduction according to the impact of certain attributes on the spearman rank correlations between objects. Experimental results show that this method is effective as it not only takes into account the preference relationship, but also improves noise immunity, and thus is more suitable for practical application.

祁云嵩谢军. 基于spearman秩相关的序值决策系统约简[J]. 计算机应用, 2009, 29(07): 1758-1759.