Information Integration for Data Fusion

Data fusion has been identified by the Department of Defense as a critical technology for the U.S. defense industry. Data fusion requires combining expertise in two areas — sensors and information integration. Although data fusion is a rapidly growing area, there is little synergy and use of common, reusable, and/or tailorable objects and models, especially across different disciplines, e.g., defense and manufacturing. The LaboratoryDirected Research and Development (LDRD) project had two purposes: (1) to see if a natural language-based information modeling methodology could be used for data fusion problems, and if so, (2) to determine whether this methodology would help identify commonalities across areas and achieve greater synergy. The project confirmed both of the initial hypotheses: (1) that the natural language-based information modeling methodology could be used effectively in data fusion areas and (2) that commonalities could be found that would allow synergy across various data fusion areas. The project found five common objects that are the basis for all of the data fusion areas examined: targets, behaviors, environments, signatures, and sensors. Many of the objects and the specific facts related to these objects were common across several areas and could easily be reused. In some cases, even the terminology remained (Abstract continued to page ii) (Abstract continued from title page)