Abstract: This paper introduces an information theoretic approach to verification of causal models in modular Bayesian fusion systems. We assume distributedfusion systems which are gradually extended by adding new modules, each having a limited domain knowledge captured in local Bayesian networks. However, since dierent modules originate from different, independent design processes important dependencies between the variables in different modules might not correctly be captured in the distributedfusion system. This could have a significant impact on the fusion quality. The introduced
method supports discovery of significant dependencies which are ignored in the distributedfusion system.
Abstract: In this paper, two different methods for information fusion are compared with respect to communication cost. These are the lambda-pi and the junction-tree approach as the probability computing methods in Bayesian networks. The analysis is done within the scope of large distributed networks of computing nodes. The result of this comparison enables us to make astatement about the most appropriate method for reasoning in distributed Bayesian networks. Each node in the network is considered an intelligent agent in a multi-agentsystem.
Abstract: We introduce Distributed perception networks (DPNs), a distributed architecture for efficient and reliable fusion of large quantities of heterogeneous and noisy information. DPNs consist of agents, processing nodes with limited fusion capabilities, which cooperate and can autonomously form arbitrarily large distributed classifiers. DPNs are based on causal models, which often facilitate analysis, design and maintenance of complex information fusion systems. This is possible because
observations obtained from different information sources often result from causal processes which in turn can be modeled with relatively simple, yet mathematically rigorous and compact probabilistic causal models. Such models, in turn, facilitate
decentralized world modeling and information fusion.
Abstract: French coastguard missions have become increasingly varied implying new challenges such as the reduction of the decision cycle and the expansion of available information. Thus, it involves new needs for enhanced decision support. An efficient situation awareness system has to quickly detect and identify suspicious boats. The efficiency of such a system relies on a reliable sensor fusion since a coastguard uses sensors to achieve his mission. We present an innovative approach based on multi-agent negotiation to fuse classifiers, benefiting from the efficiency of existing classification tools and from the flexibility and reliability of a multi-agent system to exploit distributed data across dispersed sources. We developed a first prototype using a basic negotiation protocol in order to validate the feasibility and the interest of our approach. The results obtained are promising and encourage us to continue on this way.
Abstract: Advances in network technologies enable distributed systems, operating in complex physical environments, to co-ordinate their activities over larger areas within shorter time intervals. Some envisioned application domains for such systems are defence, crisis management, traffic management and public safety. In these systems humans and machines will, in close interaction, be adaptive to a changing environment. Various architecture models are proposed for such Networked Adaptive Interactive Hybrid Systems (NAIHS) from different research areas like (networked) sensor fusion, command and control, artificial intelligence, robotics and human machine interaction. In this paper an architecture model is proposed that seeks to combine their merits. The NAIHS model focuses on the ‘hybrid mind’ that is layered in several dimensions
defining specific functional components and their
interactions. Subsequently, the interaction between the human and artificial part of the system is discussed.