A Multi-Disciplinary Approach to High Level Fusion in Predictive Situational Awareness Paulo Cesar G. Costa Center of Excellence in C4I George Mason University, MS 4B5 Fairfax, VA 22030-444 U.S.A. pcosta@c4i.gmu.edu Kuo-Chu Chang Center of Excellence in C4I George Mason University, MS 4B5 Fairfax, VA 22030-444 U.S.A. kchang@c4i.gmu.edu Kathryn B. Laskey Center of Excellence in C4I George Mason University, MS 4B5 Fairfax, VA 22030-444 U.S.A. klaskey@c4i.gmu.edu Rommel N. Carvalho Center of Excellence in C4I George Mason University, MS 4B5 Fairfax, VA 22030-444 U.S.A. rommel.carvalho@gmail.com Abstract - The change of focus in modern warfare from individual platforms to the network has caused a con- comitant shift in supporting concepts and technologies. Greater emphasis is placed on interoperability and com- poseability. New technologies such as SOA and semanti- cally aware systems have come into the spotlight. This paper argues that just as the problem space demands interoperability of diverse technologies, so must the solu- tion space. In other words, not only are new approaches needed, but they must also come together as a seamlessly interoperable technological tool set. This can be accom- plished only via a consistent multi-disciplinary approach. In this paper, we present some of the major requirements of today’s Predictive Situation Awareness Systems (PSAW), propose our approach as a coordinated mix between state-of-the-art research efforts, and present the architecture for enabling our approach. Keywords: probabilistic reasoning, naval predictive situ- ational awareness, web services, Bayesian networks, MEBN, PR-OWL, probabilistic ontologies, distributed hybrid inference, spatio-temporal hybrid analysis. 1 Introduction Knowledge fusion is the process by which heterogeneous information from multiple sources is merged in a consis- tent, coherent, and synergistic fashion to augment the level of understanding about a given problem or situation. When applied to the domain of military operations, it aims to produce a dynamic, comprehensive, and accurate bat- tlespace picture for the warfighter that integrates tactical data from multiple intelligence sources. Until the recent past, battlespace information systems have usually been self-contained solutions merging data from a finite array of sensors, sending their data via proprietary protocols, and following predefined schemas. As technology evolved at an ever-increasing pace, and as increasing bandwidth and connectivity made possible the exchange of enormous volumes of data, old-style stovepipe systems became obsolete. The new concept of NetCentric Operations changes the focus from individual platforms to the net- work. This change in focus has in turn caused a shift in supporting concepts and technologies. Greater emphasis is placed on requirements such as interoperability and com- poseability. New concepts and technologies such as SOA and semantically aware systems have come into the spot- light. A recurring phenomenon during times of fundamen- tal conceptual and technological change is the attempt to solve new problems with old tools. This is analogous to hanging onto old doctrinal frameworks in the face of new technologies. As a specific example, it is akin to employ- ing stealth fighters with Vietnam-era tactics. Just as new weapons technologies demand changes in doctrine, ad- vances in information processing capability require fun- damentally new fusion technologies for delivering value to the warfighter. These new technologies must be devel- oped with the new realities in mind, and must be tailored to exploit the new capabilities. When faced with today’s increasingly complex problem of distributed knowledge fusion, one has to realize that just as the problem space demands interoperation of diverse areas of knowledge, so must the solution space. In other words, not only are new approaches needed, but they must also act as a seamless technological whole. This can be accomplished only through a consistent, scientifically principled, multi- disciplinary approach. In section 2 we address the requirements for a pre- dictive situation awareness (PSAW) system and the major issues that must be faced when attempting to meet the requirements. Our approach of combining a suite of tech- nologies into an integrated technological tool set is intro- duced in section 3. Finally, section 4 presents PROGNOS (PRobabilistic OntoloGies for Net-centric Operation Systems), a system that applies our multi-disciplinary approach to address the problem of predictive situational awareness within the maritime operations domain. 12th International Conference on Information Fusion Seattle, WA, USA, July 6-9, 2009 978-0-9824438-0-4 ©2009 ISIF 248