This paper presents concepts and an implementation scheme to improve information exploitation processes and products by adaptive discovery and processing of contextual information.Context is used in data fusion -and in inferencing in general -to provide expectations and to constrain processing. It also is used to infer or refine desired information ("problem variables") on the basis of other available information ("context variables"). Contextual exploitation becomes critical in several classes of inferencing problems in which traditional information sources do not provide sufficient resolution between entity states or when such states are poorly or incompletely modeled.An adaptive evidence-accrual inference method -adapted from developments in target recognition and scene understanding -is presented; whereby context variables are selected on the basis of (a) their utility in refining explicit problem variables, (b) the probability of evaluating these variables to within a given accuracy, given candidate system actions (data collection, mining or processing), and (c) the cost of such actions. The Joint Directors of Laboratories (JDL) Data Fusion Model, with its extension to dual Resource Management functions, has been adapted to accommodate adaptive information exploitation, to include adaptive context exploitation. The interplay of Data Fusion and Resource Management (DF&RM) functionality in exploiting contextual information is illustrated in terms of the dual-node DF&RM architecture. An important advance is in the integration of data mining methods for data search/discovery and for abductive model refinement.
OVERVIEWAs we stated in "Dirty secrets of data fusion" [1]: "Fusion [should not be] a static process: we've started at the wrong end and continue to focus on the wrong end." By this we mean that data fusion has traditionally been construed as a data-driven problem: do the best you can with whatever information is presented by sensors or other sources. Only recently has there been much realization of the importance of goal-drive, adaptive information exploitation: i.e. relating one's present information state to a desired information state and managing available resources to approach the desired state in a cost-effective manner.Our goal in this paper is to develop a model and an implementation scheme for seeking, discovering, selecting and fusing contextual information as part of a goal-driven information exploitation process. We show how such a method can be applied generally to information exploitation systems, such as ISR (Intelligence, Surveillance and Reconnaissance) systems.Section 2 provides a formal working definition for 'context' as applied to information exploitation. Section 3 considers the distinctive issues and the applicability of various techniques to diverse categories of information exploitation problems. Section 4 defines an implementation for adaptive evidence accrual and exploitation, to include goal-driven discovery and use of context. Section 5 considers the issues of adaptive evidenc...