Belief functions induced by random fuzzy sets: A general framework for representing uncertain and fuzzy evidence

We revisit Zadeh's notion of "evidence the second kind" and show that it provides foundation for a general theory epistemic random fuzzy sets, which generalizes both Dempster-Shafer belief functions possibility theory. In this perspective, deals with generated by while induced sets. The more allows us to represent combine evidence is uncertain fuzzy. demonstrate application formalism statistical inference, makes possible reconcile possibilistic interpretation likelihood Bayesian inference.