一种改进的无核信息系统属性约简算法

Attribute reduction algorithm for non-core information system

摘要:

针对无核信息系统的特点，基于互信息提出了一种新的启发式属性约简算法，该算法以增加属性后的互信息增量和属性自身的信息熵2项指标作为评价属性重要度的依据。实验结果表明，该算法避免了对于没有核属性的无核信息系统因随机选择初始属性造成计算复杂度增大的问题，并且属性约简效率提高，属性约简后的个数也相对较少。

Abstract:

According to the characteristics of non-core information system, one new heuristic attribute reduction algorithm is proposed based on mutual information, in which the evaluation of attribute importance depends on two indexes, the increment of mutual information and the information entropy. When one attribute is added to the reduction sets, the attribute with the largest attribute importance is selected for the core attribute. This method can solve the problem of increased computational complexity caused by the randomly selected attributes. The simulation experiments indicate that the proposed algorithm is effective, which can not only improve the efficiency of attribute reduction, but also decrease the number of attribute reduction.