The Research Of Classification Based On Rough Sets And Naive Bayes

Knowledge Discovery in Databases (KDD for short) is a new important rsearch topic in Artificial Intelligence and Database domain.it is the process of mining the interesting, potentially useful, valid and understandable knowledge in data. Classification is one of the important problems in KDD.Rough Set theory proposed by polish mathematician pawlak, which used to represent the uncertain knowledge. Rough Set theory has become a main method for KDD due to its unique advantage in knowledge discovery. Naive Bayes Classifier based on bayesian Learning theory and maximum a posteriori probablty hypotheses, which is welcomed as its simplicity.This dissertation focuses on the research of classification based on Rough sets and Naive bayes,the contributions of this dissertation are as follows:Extended rough set models are analyed and a new extension of rough set based on the importance of attributes is presented.MAIR algorithm based on Entropy theory is presented, which takes into account the influence of the dependency of condition feature and decision-making feature towards reduction, and gives the most approximately independency reduction results.Therefore, a Native Bayes Classifier method based on Rough Set was introduced on the basis of MAIR. It has been demonstrated perfect performance by experiment.