Fusing probabilistic information on maximum entropy

Abstract

We present a method to fuse pieces of probabilistic information stemming from different sources which is based on information theoretical optimization techniques. We use the well-known principle of maximum entropy to process information most faithfully, while interactions between the different knowledge bases are precluded. The so-defined fusion operator satisfies basic demands, such as commutativity and the Pareto principle. A detailed analysis shows it to merge the corresponding epistemic states. Furthermore, it induces a numerical fusion operator that computes the information theoretical mean of probabilities.