粗集中最大相似度的不完备数据补齐

摘要

It is usually to change incomplete data into complete data in knowledge acquirement using Rough set theory. Completing incomplete data based on the maximum similarity in Rough sets is introduced. The method builds similar relationships and defines the similarity between objects, and finds objects with maximum similarity depending on the similarity. And then completing data is completed. The maximum similarity between objects is kept in the information system handled by the method.%在运用Rough集理论获取知识时,经常遇到不完备数据的完备化处理.提出了基于最大相似度的不完备数据补齐方法,通过建立相似关系,定义个体对象间的相似度,通过比较相似度的大小来确立最为相似的个体对象,然后进行数据补齐,这种补齐后的信息系统能使对象之间保持最大的相似度.