摘要
提出了一种基于粗糙集的不完备数据填补方法.本算法以突出信息表的决策规则为主要目的,选取重要断点为主要手段,以分类质量作为迭代约束条件.实验和数值实例表明,本算法不但不会产生冲突规则,而且能够进一步突出决策规则.
A new algorithm for filling up in complete data was presented according to rough sets. In this method, the main purpose was emphasizing the decision rules, the main means was selecting the important breaking points, and the iterative constraint was the quality of classification. Numerical illustration and database experiments show that the algorithm did not generate conflict rules,but highlighted them.
出处
《北京科技大学学报》
EI
CAS
CSCD
北大核心
2005年第3期364-366,共3页
Journal of University of Science and Technology Beijing
基金
内蒙古自治区高等学校科学研究项目(No.NJ02112)
关键词
粗糙集
相关性
等价类
断点
rough sets
correlation
equivalent class
breaking point
