In this paper,the generation of maximally generalized rules in the course of classitication knowledge discovery based on rough sets theory is discussed. Firstly, an algorithm is introduced. Secondly,we propose that th...In this paper,the generation of maximally generalized rules in the course of classitication knowledge discovery based on rough sets theory is discussed. Firstly, an algorithm is introduced. Secondly,we propose that the information-based J-measure is used as another measure of attribute signifi cance value. This measure is used for heuristically selecting the conditions to be removed in the process of extracting a set of maximally generalized rules. Finally,we present an example to illustrate the process of the algorithm.展开更多
文摘In this paper,the generation of maximally generalized rules in the course of classitication knowledge discovery based on rough sets theory is discussed. Firstly, an algorithm is introduced. Secondly,we propose that the information-based J-measure is used as another measure of attribute signifi cance value. This measure is used for heuristically selecting the conditions to be removed in the process of extracting a set of maximally generalized rules. Finally,we present an example to illustrate the process of the algorithm.