Data fusion has been defined as a process dealing with the association, correlation, and combination of data and information from multiple sources to achieve refined position and identity estimates for entities, and complete and timely assessments of related situations and threats, and their significance. This process (sometimes labeled a “technology”) is pervasive, i.e. capable of broad, multi-domain application. Indeed, data fusion has found extensive application in the commercial/industrial sector as well, in areas such as robotics and process control, and for numerous applications requiring intelligent, autonomous processes and capabilities. One of the purposes of this paper is to describe the evolving standard description of the data fusion process ascribed to by the U.S. Joint Directors of Laboratories (JDL) Data Fusion Subpanel (a Department of Defense organization), as well as components of the attendant lexicon and taxonomy. While the specific definitions of a “situation assessment (SA)” and a “threat assessment (TA)” have proven to be problem-dependent for most defense applications, these notions generally encompass a large quantity of knowledge which reflect the (dynamic) constituency-dependency relationships among objects of various classes as well as events and activities of interest. Formulation of hypotheses about situations and threats is a process having the following properties: • it employs many types of knowledge • it must consider multiple, asynchronous activities • multiple types of dynamic and static data must be processed • numerous sub-networks of interest in the situation/threat picture (numerous constituency-dependency relationships) exist—this leads to feedforward/backward inferencing requirements • information-processing strategies are required to produce estimates of aggregated force structures (given individual unit positions and identities), as well as aggregated behaviors (given individual events or activities) • the situational or threat state is often ephemeral and thus temporal reasoning capabilities must be part of the process The paper expands on the processes and techniques involved in SA and TA analysis, and describes, from various points of view, why the blackboard paradigm is properly applicable to problems of SA and TA analysis. This assessment includes various trade-off factors (features, benefits, and disadvantages or complexities) in applying blackboard concepts to data fusion related reasoning processes. Specific research and development by the authors and synthesis of the results of a survey on data fusion applications (shown within) has led to the formulation of a recommended generic, ideal blackboard architecture for these defense problems described in the paper.
Real-Time Data Fusion Applications in Embedded Sensor Network using TATAS