Fuselets - An agent based architecture for fusion of heterogeneous information and data

Conference paper


Jürgen Beyerer
Michael Heizmann
Jennifer Sander


Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2006, Belur V. Dasarathy (ed.), Proceedings of SPIE 6242, 2006.



A new architecture for fusing information and data from heterogeneous sources is proposed. The approach takes criminalistics as a model. In analogy to the work of detectives, who investigate crimes, software agents are instantiated that pursue clues and try to consolidate or to dismiss hypotheses. Like their human pendants, they can, if questions beyond their competencies arise, consult expert agents. Within the context of a certain task, region, and time interval, specialized operations are applied to each relevant information source, e.g. IMINT, SIGINT, ACINT, ..., HUMINT, databases etc. in order to establish hit lists of first clues. Each clue is described by its pertinent facts, uncertainties, and dependencies in form of a local degree-of-belief (DoB) distribution in a Bayesian sense. For each clue, an agent is instantiated which cooperates with other agents and experts. Expert agents support the use of different information sources. Consultation of experts capable of accessing certain information sources results in changes of the DoB of the pertinent clue. According to the significance of concentration of their DoB distribution, clues are abandoned or pursued further to formulate task specific hypotheses. Communication between the agents serves to find out whether different clues belong to the same cause and thus can be combined. At the end of the investigation process, the different hypotheses are evaluated by a jury and a final report is created that constitutes the fusion result. The approach proposed avoids calculating global DoB distributions by adopting a local Bayesian approximation and thus reduces the complexity of the problem essentially. Different information sources are transformed into DoB distributions using the maximum entropy paradigm and considering known facts as constraints. Nominal, ordinal, and cardinal quantities can be treated within this framework equally. The architecture is scalable by tailoring the number of agents according to the available computer resources, to the priority of tasks, and to the tolerable maximum duration of the fusion process. Furthermore, the architecture allows cooperative work of human and automated agents and experts, if not all subtasks can be accomplished automatically.