基于信息量的一种属性约简算法

An attribute reduction algorithm based on the information quantity

提出了决策属性集相对于条件属性集的条件信息量的概念,证明了其在属性约简过程中的变化规律是单调递减的,并提出了一种新的属性约简启发式算法,该算法的时间复杂度为O(C3U2).通过例子分析,表明该算法是有效的.

Reduction of knowledge is one of the important topics in the research on the rough set theory. This paper presents the concept of the information quantity of decision attributes with relation to given condition attributes and proves that its changing tendency is decreasing. Then, a new reduction algorithm based on information quantity is developed, with the time complexity of this algorithm being O(C3U2). An example shows that this algorithm is effective.