基于决策表的粗糙集属性约简算法改进及应用

Improvement and Application of Rough Set Attribute Reduction Algorithm Based on Decision Table

针对决策属性集合中只存在两个决策集合的情况,为简化决策属性的表达和计算复杂度,提高约简效率,提出一种改进粗糙集决策表的属性约简算法。该算法以条件属性对决策属性的支持度为基础,采用新的约简规则,基于可分辨矩阵的启发式算法,根据属性重要度改进属性约简算法。以高新技术企业智力资本测量指标体系为例,得到了高新技术企业智力资本的最小约简集。结果表明,该约简算法能够得到一个完备的最小约简集,并能显著提高求解约简集的效率。

Aiming at the existence of only two decision sets in the decision attribute set,in order to simplify the expression and computational complexity of decision attributes and improve the efficiency of reduction,an attribute reduction algorithm for improving the rough set decision table is proposed. The algorithm is based on the support of the condition attribute to the decision attribute,adopts the new reduction rule,and the heuristic algorithm based on the discrimination matrix and improves the attribute reduction algorithm according to the attribute importance. Taking the high-tech enterprise intellectual capital measurement index system as an example,the article obtains the minimum reduction set of intellectual capital of high-tech enterprises. The results show that the reduction algorithm can obtain a complete minimum reduction set and can significantly improve the efficiency of solving the reduction set.