基于信息熵的一种属性约简算法

Rough Set Based Attribute Reduction Algorithm

文章针对Rough Set理论的核心内容之一属性约简进行了研究。结合信息论的有关知识，研究了在属性约简过程中决策属性集相对条件属性集的条件熵的变化规律，在此基础上提出了新的属性约简算法。实验分析表明，在多数情况下这种算法都能够得到决策表的最小约简，同时还对算法复杂度做了简单的分析。

： In this paper，the authors discuss the reduction of knowledge in rough set theory．First，the changing tendency of the conditional entropy of decision attributes given condition attributes is studied from the viewpoint of information．Then，a new reduction algorithm based on conditional entropy is developed．Furthermore，the complexity of the algorithm is analyzed simply．Simulation results show that the algorithm can find the minimal reduction in most cases．