Bayes'sche Methodik zur lokalen Fusion heterogener Informationsquellen

Journal paper


Jürgen Beyerer
Jennifer Sander
Stefan Werling


tm Technisches Messen 74 Nr. 3, Oldenbourg Verlag, München, 2007.



In fusing heterogeneous information sources, their different abstraction levels and formalizations have to be coped with. Essential requirements on a fusion methodology are its abilities to transform, fuse, and focus. It is shown that the Bayesian fusion methodology as Degree-of-Belief interpretation covers all these areas. With a view to reduce high computational costs, a local approach for the Bayesian fusion of information is subsequently be presented. In analogy to criminalistic investigation, this approach can be realized via agent-based fusion architecture.