摘要
提出一种基于粗糙集的近似质量求取属性约简的算法。该算法以集合近似的质量为迭代准则 ,以所有条件属性为初始约简集合 ,通过逐步缩减来求取约简 ,保证了所求取的约简对问题的分类能力不会减弱。同时给出了该算法的时间复杂度分析 。
The rough set thoery is studied, and an algorithm for finding attribute-oriented reduct based on approximation quality of rough set is presented. With all the condition attributes as the initial reduct, this algorithm takes the approximation quality of rough set as the iterative criterion to assure that the classification ability of the resulted reduct does not decline. The time complexity of the algorithm is analyzed and an example is investigated to verify this algorithm. The results show this algorithm can find the attribute-oriented reduct effectively with less computational effort.
出处
《控制与决策》
EI
CSCD
北大核心
2003年第3期313-316,共4页
Control and Decision
基金
国家自然科学基金重点项目 ( 60 2 3 40 10 )
航空科学基金资助项目 ( 0 2 E5 2 0 2 5 )
关键词
粗糙集
决策表
集合近似
约简
近似质量
Algorithms
Approximation theory
Classification (of information)
Mathematical techniques
