An Evidence theory and data fusion based classification method for decision making

Abstract

As the characteristics of evidence theory that can effectively deal with uncertain information, this paper proposes a decision fusion method based on binary classification model and evidence theory. We use Logistic Regression and SVM models to solve the binary classification problems separately, then use evidence theory for decision confusion. And there is a comparison between the single classification model and the classification model with evidence theory for decision fusion. The experimental results show the performance of decision confusion that the classification model with the evidence theory has higher prediction accuracy than the single classification model.

Topics & Concepts