改进粗糙集的指标权重确定方法

Method for Determining Index Weight of Improved Rough Set

针对基于粗糙集信息量确定指标权重的方法忽视属性自身重要性,且在确定指标权重时出现为0的问题,提出一种新的指标权重确定方法。通过改进已有属性重要度的确定方法,确立非冗余属性和冗余属性的高级和低级优先级队列,给出优先度的计算方法。在此基础上,完成指标权重的确定。通过算例分析证明,新的指标权重确定方法综合考虑属性自身及其在整体中的重要性,克服了指标权重为0的问题。

Aiming to the method of determining the index weight based on the information of the rough set ignores the importance of the attribute itself,and it is 0 when determining the index weight.This paper proposes a new method for determining the index weight.Through improving the determination method of existing attributes importance,this paper establishes the high-level and low-level priority queues of non-redundant attributes and redundant attributes and gives the priority calculation method.On this basis,this paper completes the determination of index weight.The case study proves that the new index weight determination method considers the attribute itself and its importance in the whole,and overcomes the problem that the index weight is 0.