一种基于信息粒度的动态属性约简求解算法

Dynamic Algorithm for Computing Attribute Reduction Based on Information Granularity

动态属性约简是粗糙集理论的重要研究内容之一。针对动态决策表构造了一种基于信息粒度的动态属性约简模型,详细分析了决策表中出现新属性动态增加时信息粒度的增量式计算方法;在此基础上,以信息粒度作为启发信息,设计了一种动态属性约简求解算法,该算法能有效利用原决策表的属性约简结果和信息粒度来降低算法的计算复杂度,并使得约简结果具有较好传承性;最后通过算例分析和实验比较进一步验证了本算法的可行性和有效性。

Dynamic attribute reduction is one of the important issues in rough set theory.A dynamic attribute reduction model based on information granularity was constructed in dynamic decision table,and an incremental approach for computing information granularity was discussed in detail when some new attribute set is added into decision table.On this basis,a dynamic attribute reduction algorithm was proposed by using information granularity as the heuristic information.The proposed algorithm can use attribute reduction and information granularity of original decision table,which can effectively reduce the computational complexity,so that the attribute reduction has better inheritance.Finally,the example and experimental comparison indicate the feasibility and validity of the proposed algorithm.