Data Fusion Method Based on Improved D-S Evidence Theory

Abstract

As the rapid growth of user-generated data from social networks, wikis and social tagging systems, it is necessary to understand the high-level semantics and user subjective perceptions from such a large volume of data. In the era of big data flooding, how to fuse the emotional computing results from massive data to obtain effective conclusions and decisions has become a problem. This paper combines D-S evidence theory with data fusion and effectively solves the conflict of evidence evidence in D-S evidence theory by introducing the Bhattacharyya distance, the confidence level of evidence and the modified combination rule. The experimental results show that the improved data fusion method can get the data fusion result, and the result has a high accuracy and credibility.