A new classification method based on the negation of a basic probability assignment in the evidence theory

In the practical application of classification, how to handle uncertain information for efficient classification is a hot topic. In this paper, in the frame of Dempster–Shafer evidence theory, a new classification method based on the negation of basic probability assignment (BPA) is proposed to implement an effective classification. The proposed method addresses the issue that the values of samples’ attributes cannot clearly point out a certain class in classification problems. For uncertain information modeling, the negation of BPA is adopted to obtain more valuable information in the body of evidence. To measure the uncertain information represented by the negation of BPA, the belief entropy is used for calculating the uncertain degree of each body of evidence. Finally, Dempster's combination rule is used for data fusion to identify and recognize the unknown class. The effectiveness and efficiency of the new classification method are validated according to experiments on several UCI data sets. In addition, the classification experiment on the data sets with the changing proportion of the training set verifies that the method is robust and feasible.