Bayesian fusion: Modeling and application

Abstract

Bayesian statistics leads to a powerful fusion methodology, especially for the fusion of heterogeneous information sources. If fusion problems are handled under consideration of the full expressiveness and the full range of methods provided by Bayesian statistics, the Bayesian fusion methodology possesses an impressive wide range of applications. We discuss this by having a closer look at selected aspects of Bayesian modeling. Thereby, also parallels to other methods used for information fusion will be drawn. With regard to the practical tractability of Bayesian fusion problems, selected approaches to deal with its potentially high complexity are discussed.