基于距离测度的模糊粗糙集属性约简

Attribute reduction with fuzzy rough set based on distance measures

属性约简是模糊粗糙集理论的重要研究内容.本文引进了基于距离的模糊相似关系,建立了距离测度下的模糊粗糙模型,从而得到条件属性和决策属性之间的依赖函数,通过此函数构造了前向搜索属性约简算法.并利用了UCI标准数据集与现有算法进行比较,从而验证了该算法的可行性和有效性.

Attribute reduction is one of the most important topics in fuzzy rough set theory .This paper first introduces fuzzy similar relation based on distance ,presents a new fuzzy rough set model based on distance meas-ures.Then,the dependency between condition attribute and decision attribute is proposed ,by which a greedy for-ward algorithm for attribute reduction is designed .The data sets selected from UCI are used to compare the pro-posed algorithm with some existing algorithms ,and the experimental results show that the proposed reduction algo-rithm is feasible and effective .