基于增量式更新带权差别集合的属性约简算法

Complete Algorithm for Attribute Reductions Based on Incremental Updating Weighted Discernibility Set

在面向差别矩阵的约简算法思想的基础上,定义一种新的带权差别集合(WDS)模型,并提出了高效更新带权差别集合的算法,分析了该更新算法的时间和空间复杂度.随后,基于快速更新带权差别集合算法,提出一种增量式属性约简方法.当有新的数据对象被加入决策表,可有效提高属性约简的效率.理论分析和实验结果表明该算法适用于大数据集的约简.

Through carefully analysis of a complete algorithm for attribute reduction based on discernibility matrix,the concept of weighted discernibility set（WDS） was defined and a fast algorithm for attribute reduction with detailed analysis of time and space complexity based on incremental updating weighted discernibility set was proposed.When incremental objects are added into a decision information system,a new attribute reduction can be got by this method quickly.Theoretical analysis and experimental results show that this method was much more efficient in comparison with those existing algorithm.