摘要
通过分析乐观决策粗糙集和悲观决策粗糙集的不足之处,提出一种δ-可变多重代价矩阵的融合规则,进而建立一种可变多重代价决策粗糙集模型。引入非线性映射sigmoid函数,将可变域拓展到实数域范畴。研究了可变多重代价决策粗糙集、乐观决策粗糙集和悲观决策粗糙集的性质和关系,分析了它们之间的度量和代价关系。实例分析结果验证了该模型的可行性。
By analyzing the limitations of the optimistic multi-cost decision-theoretic rough set and pessimistic multicost decision-theoretic rough set,the fusion rules of variable precision multi-cost matrix was proposed and its decisiontheoretic rough set was established.By introducing nonlinear mapping function called sigmoid,variable domain expands to real number domain.Furthermore,the properties and relations of these kinds of rough sets were discussed and the measure and cost relations of them were analyzed.Finally,The experimental results show the effectiveness of the model.
出处
《计算机科学》
CSCD
北大核心
2017年第6期245-249,共5页
Computer Science
关键词
决策粗糙集
可变精度
多重代价
Decision-theoretic rough set
Variable precision
Multi-cost
