节点文献
基于互信息的模糊粗糙集属性约简
Mutual Information-Based Algorithm for Fuzzy-Rough Attribute Reduction
【摘要】 模糊粗糙集知识约简是模糊粗糙集理论的核心内容之一。该文从粗糙集知识熵出发,结合模糊集隶属度函数,将其应用于模糊环境下,推广了互信息的度量概念,使其能评价模糊决策表中属性的重要性。并给出了一种模糊决策表的启发式属性约简算法,通过实例验证了它的可行性,为模糊决策表的属性约简提供了一种有效的方法。
【Abstract】 Fuzzy-rough attribute reduction is one of the important topics in the research on fuzzy-rough set theory. In this paper,the information entropy is generalized in rough set so that it could be used to value the importance of attribute under fuzzy circumstance.A new heuristic algorithm based on mutual information for fuzzy-rough attribute reduction is introduced and illustrated with a simple example.
【关键词】 模糊粗糙集;
属性约简;
模糊决策表;
互信息;
【Key words】 Fuzzy-rough set; Attribute reduction; Fuzzy decision table; Mutual information;
【Key words】 Fuzzy-rough set; Attribute reduction; Fuzzy decision table; Mutual information;
【基金】 国家自然科学基金(60475019);教育部博士点专项基金(20060247039)资助课题
- 【文献出处】 电子与信息学报 ,Journal of Electronics & Information Technology , 编辑部邮箱 ,2008年06期
- 【分类号】TP182
- 【被引频次】74
- 【下载频次】875