|Links:||Full Text (PDF, 477 kB)Oldenbourg Wissenschaftsverlag: tm - Technisches Messen|
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.