摘要
对Skowron可辨识矩阵方法进行分析,并应用反例说明基于Skowron可辨识矩阵的属性约简算法对不相容决策表的属性约简,可能会导致错误的结果。针对这一问题,提出了一种基于改进可辨识矩阵的属性频率约简算法。该算法以改进的可辨识矩阵为基础,以属性频率作为启发信息,同时在算法中加入消除冗余属性二次约简过程。提供了实例分析,验证了该算法能够有效地对相容与不相容的决策表进行属性约简。
The Skowron＇s discernibility matrix is analyzed in this article.The anti-cases is presented that shows the mistake still exists in the attribute reduction algorithm based on Skowron＇s discernibility matrix.To this issue,an attribute frequency reduction algorithm based on improved discernibility matrix is presented in this article.The discernibility matrix is the foundation of the algorithm,the attribute frequency is used as heuristic information in this algorithm and a process of reducing again is used in the algorithm in order to eliminate redundancy attributes.The example is presented in the article that validates the attribute reduction algorithm can be used in consistent decision tables and inconsistent decision tables.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第24期162-164,共3页
Computer Engineering and Applications
基金
国家火炬计划(No2004EB33006)
关键词
不相容决策表
属性约简
属性频率
可辨识矩阵
核
inconsistent decision table
attribute reduction
attribute frequency
discernibility matrix
core
