基于Rough set理论的气象状况分类算法研究

Research on Weather Condition Classification Based on Rough Set Theory

根据粗糙集理论,提出一种基于决策表相容性的属性约简算法。对一幅经典的天气观测状况决策表进行属性约简,把表示观测状况的各参数作为决策表的属性,运用粗糙集理论对该原始决策表进行约简,以提取天气状况的重要属性,删除分析过程中的冗余属性和属性值,约简后的属性可为决策提供支持。分析表明,粗糙集理论应用于这类决策可得到更清晰、简明的判断规则。

Rough set theory is a mathematical tool to study the processing of incomplete and uncertain knowledge. Attribute reduction is one of its hot research topics. On the basis of rough sets theory, this paper proposed a kind of attribute reduction algorithm based on the decision- making table＇s compatibility, this algorithm enhance the efficiency high. In the attribute reductions of a classical weather observation condition decision-making table, the parameters expressing observation condition were taken as the attribute of policy-making table,and rough set theory was used to reduce this primitive policy-making table so as to withdraw the important attribute of weather conditions and to deletes the redundant attribute and the attribute value in analysis process. The reduced attribute may provide the support for decision＇making. It was shown that the application of rough set theory in this kind of decision-making may obtain clear and concise judgment rule.