Fusion agents - realizing Bayesian fusion via a local approach

Bayesian theory delivers a powerful theoretical platform for the mathematical description and execution of fusion tasks, especially if the information delivering sources are of heterogeneous nature. However, the complexity of Bayesian fusion tasks increases exponentially with the number of sources. A new agent based architecture that is modelled on a successful operating process of the real world, namely criminalistic investigation, circumvents the high computational costs by realizing a local fusion approach. In analogy to criminalists, software agents shall be appointed to perform heterogeneous fusion tasks. In this paper, we give an overview over this concept and the potentials that are provided by it. Then, we focus on translating the proposed ideas into a formal mathematical notation