Summary: Information modeling and handling in uncertain environments is an important topic in the field of modern artificial intelligence. In practical applications of classification problems, the data harvested by the agent is usually not precise. Based on multi-valued mapping of probabilities expressed by Basic Probability Assignment (BPA), Dempster-Shafer Theory (DST) has a strong ability to model and handle uncertain information. In this paper, we propose a method of fusing attributes to enhance the quality of uncertain data under the framework of DST. The fusion method is based on proposed uncertainty and dissimilarity measures, which performs consistent transformations on belief information in DST. We simulate uncertain data by adding different noises to precise datasets and classify the improved data using common classifiers. With the increasing uncertainty degree of data, the proposed method has higher accuracy and robustness than other methods.