The Dempster-Shafer combination rule as a tool to classifier combination

摘要

In this paper we present Dempster-Shafer theory as a framework within which the results of a Bayesian and a fuzzy classifier can be combined to produce a better final classification. We deal with the case when the two original classifiers use different classes for the outcome, and we also present a method by which different reliability is associated with different expert rules used.