基于相对粒度的决策表知识约简算法
首发时间:2010-07-05
摘要:本文基于知识粒度的定义,分析决策表中知识的不确定性,给出了决策属性集相对于条件属性集的相对粒度以及属性重要性的概念,进而通过相对粒度定义了决策表的一致性。在此基础上,设计了一种基于相对粒度的决策表知识约简算法,用于约简决策表中的冗余属性和冗余属性值,从而得到决策表的最小知识约简。实例验证表明该算法时间复杂度相对较低,能有效地处理不一致决策表,有利于提高系统的决策效率。
For information in English, please click here
Knowledge Reduction Algorithm Based on Relative Granularity in Decision tables
Abstract:In this paper, the uncertainty of knowledge in decision tables based on theory of knowledge granularity is analyzed. We introduced the concepts of importance of attribute and relative granularity which is used for measuring the discernibility of decision attributes set relatives to condition attributes set in the universe, and then definite consistent decision table by relative granularity. On the basis of this theory, we propose a knowledge reduction algorithm based on relative granularity which is used to reduce the redundant attribute and attribute value, and then attain the smallest knowledge reduction of decision table. By analyzing the example, the algorithm is proved that it\\\\\\\\\\\\\\\'s time complexity is relatively low, it can effectively deal with inconsistent decision tables, and it help to improve the efficiency of the system.
Keywords: Granular Computing (GrC) Decision tables Relative granularity Knowledge Reduction
论文图表:
引用
No.4377684518670127****
同行评议
共计0人参与
勘误表
基于相对粒度的决策表知识约简算法
评论
全部评论0/1000