变精度粗集模型中变精度值的估计  

Estimation of the Variable Precision Value based on Variable Precision Rough Set Model

作　　者：程玉胜[1] 张佑生[1] 胡学钢[1] 

机构地区：[1]合肥工业大学计算机与信息学院

出　　处：《重庆大学学报（自然科学版）》2006年第9期122-125,共4页Journal of Chongqing University

基　　金：国家自然科学基金资助项目(60575023);安徽省高校省级自然科学基金项目(2006kj040B);高等学校博士学科点专项科研基金项目(20050359012)

摘　　要：变精度粗集模型是一种有参数的粗集扩充模型.目前,基于变精度粗集模型知识约简和学习的各种算法中,参数β值都是作为领域的先验知识而被直接引入.而β值不同,约简的结果一般也不同,因此有必要寻求一种方法,实现从原始数据集本身出发完成对β值的估计和选择,从而摆脱β先验知识对结果的影响.结合决策表确定性度量和决策表相对辨识性方法,分别研究了β值的估计和选择以及参数β值对约简结果的影响.通过实例进行了分析,结果表明在利用变精度粗集模型提高系统容错度时,β值选择是必要的.The variable precision rough set model is parametric and there are many types of knowledge reduction in the area of rough sets such as distribution reduction and assignment reduction. Among the present various algorithms of knowledge reduction based on variable precision rough set model, β is always introduced directly as prior domain knowledge. In some applications, it is not clear how to set the parameter. For that reason, it is necessary to seek an approach to realize the estimation and choosing of β from the original data set, avoiding the influence of β apriority upon the resuit. Based on certainty measure and the relative discernibility in measurement of decision table, two methods are developed to estimate and to choose the β value. It is necessary to choose β value by analyzing the influences of the result of knowledge reduction based on variable precision rough set model.

关 键 词：变精度粗集模型 知识约简 决策表 确定性度量 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]