基于特定类不完备决策系统的分布约简  

Class-specific distribution reduction in incomplete decision systems

作　　者：陈阳[1,2] 张楠 孙雪姣[2] 童向荣 张小峰 Chen Yang;Zhang Nan;Sun Xuejiao;Tong Xiangrong;Zhang Xiaofeng(Key Laboratory for Data Science&Intelligence Technology of Shandong Higher Education Institutes,Yantai University,Yantai Shandong 264005,China;School of Computer&Control Engineering,Yantai University,Yantai Shandong 264005,China;School of Information&Electrical Engineering,Ludong University,Yantai Shandong 264025,China)

机构地区：[1]烟台大学数据科学与智能技术山东省高校重点实验室,山东烟台264005 [2]烟台大学计算机与控制工程学院,山东烟台264005 [3]鲁东大学信息与电气工程学院,山东烟台264025

出　　处：《计算机应用研究》2020年第9期2659-2664,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(61403329,61572418,61572419,61873117);山东省自然科学基金资助项目(ZR2018BA004,ZR2016FM42)。

摘　　要：现有的不完备决策系统的分布约简研究主要针对决策系统中的所有决策类,而某些实际应用中,人们往往仅关注于某个特定类的属性约简问题。基于这种考虑,首先提出了基于特定类的不完备决策系统的分布约简的理论框架,给出了在相容关系下的基于差别矩阵的约简算法,最后将该算法与基于所有决策类的不完备决策系统分布约简算法进行对比。实验结果表明,当决策类为特定类时,约简结果的平均长度相对较短,约简效率也有显著的提高。The existing researches on distribution reduction of incomplete decision systems mainly focus on all decision classes.However,in some practical applications,the decision makers only pay attention to attribute reduction based on a specific decision class. Based on this consideration,this paper proposed a theoretical framework of class-specific distribution reduction in incomplete decision systems and presented a reduction algorithm based on discernibility matrix under the tolerance relation. Finally,this paper compared the proposed algorithm with the distribution reduction algorithm of incomplete decision systems based on all decision classes. The experimental results show that when the decision class is a specific class,the average length of reducts is relatively short and the efficiency of reduction is also improved remarkably.

关 键 词：不完备决策系统 特定类 分布约简 差别矩阵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]