Method to determine α in rough set model based on connection degree  

作　　者：Li Huaxiong Zhou Xianzhong Huang Bing 

机构地区：[1]School of Management and Engineering, Nanjing Univ., Nanjing 210093, P. R. China [2]State Key Lab. for Novel Software Technology, Nanjing Univ., Nanjing 210093, P. R. China [3]School of Information Science, Nanjing Audit Univ., Nanjing 210029, P. R. China

出　　处：《Journal of Systems Engineering and Electronics》2009年第1期98-105,共8页系统工程与电子技术（英文版）

基　　金：supported by the National Natural Science Foundation of China (70571032)

摘　　要：An improvement of tolerance relation is proposed in regard to rough set model based on connection degree by which reflexivity of relation can be assured without loss of information. Then, a method to determine optimal identity degree based on relative positive region is proposed so that the identity degree can be computed in an objective method without any preliminary or additional information about data, which is consistent with the notion of objectivity in rough set theory and data mining theory. Subsequently, an algorithm is proposed, and in two examples, the global optimum identity degree is found out. Finally, in regard to optimum connection degree, the method of rules extraction for connection degree rough set model based on generalization function is presented by which the rules extracted from a decision table are enumerated.An improvement of tolerance relation is proposed in regard to rough set model based on connection degree by which reflexivity of relation can be assured without loss of information. Then, a method to determine optimal identity degree based on relative positive region is proposed so that the identity degree can be computed in an objective method without any preliminary or additional information about data, which is consistent with the notion of objectivity in rough set theory and data mining theory. Subsequently, an algorithm is proposed, and in two examples, the global optimum identity degree is found out. Finally, in regard to optimum connection degree, the method of rules extraction for connection degree rough set model based on generalization function is presented by which the rules extracted from a decision table are enumerated.

关 键 词：rough set data mining connection degree identity degree set pair relative positive region. 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] O153.1[自动化与计算机技术—控制科学与工程]