Incorporating fuzzy sets into dempster-shafer theory for decision fusion

Abstract

© 2018 Pushpa Publishing House, Allahabad, India. Decision fusion is one of the popular methods in the classification research area. The Dempster’s rule of combination is one of the decision fusion methods used frequently in many research areas. However, there are so many uncertainties in classifier output. Hence, we introduce a fuzzy Dempster’s rule of combination where we fuzzify the basic probability assignment and compute the fuzzy combination. We run the experiment with 4 classifiers, i.e., linear discriminant analysis, K-nearest neighbors, Naïve Bayes, and multilayer perceptron. Therefore, there are 6 combinations in the experiment. We compare our fusion result with that from the Dempster’s rule of combination. All of our results are comparable or better than those from the Dempster’s rule of combination.