摘要
针对传统贝叶斯粗糙集理论只能处理二决策类的不足,提出一种基于多决策类的贝叶斯粗糙集.在此基础上定义一个衡量条件属性对决策属性影响程度的γ依赖度函数,并证明了该函数具有随条件属性的增加而单调递增的性质.最后基于γ依赖度函数的单调特性,提出一种确定属性权重的算法.以某钢厂150 t转炉的实际生产数据为例,仿真结果表明了模型的有效性和实用性.
For the limitation that traditional Bayesian rough set model theory can only deal with the situation of two decision classes, a Bayesian rough set model based on multiple decision classes is proposed, which can deal with the problem of multiple decision classes. On this condition, a γ dependency function is defined to evaluate the condition attributes significance to decision attributes, and is proved that the function is monotonic increase with condition attributes. Finally, an algorithm to compute attribute weight is proposed based on the monotonic property of γ dependency function. The simulation result of the model using the practical data from a steel plant＇s 150 ton converter shows the effectiveness and practicality of this model.
出处
《控制与决策》
EI
CSCD
北大核心
2009年第11期1615-1619,共5页
Control and Decision
基金
国家863计划项目(2007AA04Z158)
国家自然科学基金项目(60674073)
关键词
贝叶斯粗糙集
多决策类
属性权重
γ依赖度函数
Bayesian rough set
Multiple decision classes
Attribute weight
γ dependency function
