Fuzzy Naive Bayesian for constructing regulated network with weights.

Journal: Bio-medical materials and engineering
Published Date:

Abstract

In the data mining field, classification is a very crucial technology, and the Bayesian classifier has been one of the hotspots in classification research area. However, assumptions of Naive Bayesian and Tree Augmented Naive Bayesian (TAN) are unfair to attribute relations. Therefore, this paper proposes a new algorithm named Fuzzy Naive Bayesian (FNB) using neural network with weighted membership function (NEWFM) to extract regulated relations and weights. Then, we can use regulated relations and weights to construct a regulated network. Finally, we will classify the heart and Haberman datasets by the FNB network to compare with experiments of Naive Bayesian and TAN. The experiment results show that the FNB has a higher classification rate than Naive Bayesian and TAN.

Authors

  • Xi Y Zhou
    IT College, Gachon University, Seongnam, South Korea.
  • Xue W Tian
    Department of Educational Technology, Teachers College, Qingdao University, QingDao, China.
  • Joon S Lim
    IT College, Gachon University, Seongnam, South Korea.