Abstract: Attribute reduction is one of the key problems in rough set theory, and determination of core attribute is the basis to solve the problem of attribute reduction. First, by using the tree structure knowledge expression in the decision table, an approach for computing positive and negative regions was introduced. Next, according to changes of positive and negative regions in tree structure decision table relative to the conditional attribute set, an algorithm for computing core attributes was developed. An efficiency of the proposed methods was illustrated by time and space complexities analysis and experimental result in a weather decision table.

Key words: rough set, decision table, attribute reduction, core attribute

摘要： 属性约简是粗糙集理论研究的一个核心问题，而核属性的确定往往是决策表中属性约简的基础。结合决策表的树型结构表示，给出了决策表中正域和非正域的计算方法，并从核属性的定义出发，计算树型决策表中正域和非正域相对于属性全集正域和非正域的变化，提出了一种计算决策表中核属性的方法。对其时间和空间复杂度的分析，以及对一个气象决策表例子的实验结果，证明了这些方法的有效性。

关键词: 粗糙集, 决策表, 属性约简, 核属性