To guarantee the optimal reduct set, a heuristic reduction algorithm is proposed, which considers the distinguishing information between the members of each pair decision classes. Firstly the pairwise positive region ...To guarantee the optimal reduct set, a heuristic reduction algorithm is proposed, which considers the distinguishing information between the members of each pair decision classes. Firstly the pairwise positive region is defined, based on which the pairwise significance measure is calculated between the members of each pair classes. Finally the weighted pairwise significance of attribute is used as the attribute reduction criterion, which indicates the necessity of attributes very well. By introducing the noise tolerance factor, the new algorithm can tolerate noise to some extent. Experimental results show the advantages of our novel heuristic reduction algorithm over the traditional attribute dependency based algorithm.展开更多
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...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.展开更多
基金Sponsored by the Ministerial Level Advanced Research Foundation(11415133)
文摘To guarantee the optimal reduct set, a heuristic reduction algorithm is proposed, which considers the distinguishing information between the members of each pair decision classes. Firstly the pairwise positive region is defined, based on which the pairwise significance measure is calculated between the members of each pair classes. Finally the weighted pairwise significance of attribute is used as the attribute reduction criterion, which indicates the necessity of attributes very well. By introducing the noise tolerance factor, the new algorithm can tolerate noise to some extent. Experimental results show the advantages of our novel heuristic reduction algorithm over the traditional attribute dependency based algorithm.
基金supported by the National Natural Science Foundation of China (70571032)
文摘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.