基于条件信息熵的粗糙集属性动态约简

Rough set dynamic reduction of attribute based on conditional information entropy

属性约简是粗糙集理论的热点研究内容之一,从信息论出发,提出一种新的信息熵定义.约简算法从条件信息熵出发,迭代选择属性重要性最大的属性,得到信息系统的约简.在此基础上,构造基于条件信息熵的不完备信息系统的动态属性约简算法.在删除单个对象的情况下,新算法通过新的数据集有无删除对象的不可区分对象来判断是否更新原有约简.通过实例说明算法的有效性和可行性.

Attribute reduction is one of the hot topics of rough set theory. Based on information theory, proposes a new definition of information entropy, which starts from the conditional information entropy and iteratively selects the attribute with the greatest importance of attribute, and obtains the reduction of the information system. On this basis, a dynamic attribute reduction algorithm for incomplete information systems based on conditional information entropy is constructed. In the case of deleting a single object, the new algorithm determines whether to update the original reduction through the indistinguishable ohject of the new data set. The effectiveness and feasibility of the algorithm are illustrated by an experiment.