Air Force intelligence analysts must assess an adversary’s capability to achieve their objectives, including their offensive and defensive systems, state of readiness, training, and conditions such as weather. To effectively assess these capabilities, analysts must integrate a tremendous amount of data from a number of sources. An automated decision support system can help analysts manage and process the information.
Charles River Analytics, a developer of intelligent systems tools, has built an automated decision support system called Assessment of Adversary Capability and Capacity via Intelligence Analysis (ACACIA). The tool will help intelligence analysts determine an adversary’s resources and capacities.
ACACIA organizes and collects relevant factors from various data sources; an analyst creates the “big picture” from answers to individual questions. Where possible, ACACIA determines answers automatically from data sources; in other cases, the analyst provides estimates. ACACIA then processes the answers to help analysts create their assessments.
ACACIA also incorporates expert knowledge to analyze an adversary’s capabilities. This expert knowledge is especially useful for junior analysts, who may be new to the field or inexperienced in intelligence analysis. For instance, when junior analysts pose questions to ACACIA, the system analyzes available data, presents relevant factors, and provides an initial assessment of the adversary’s capabilities and intentions. ACACIA provides this analysis based on a probabilistic model that delivers expert-level reasoning, even in the face of missing and incorrect information.
Analysts can also modify the criteria to analyze data. For instance, if the analyst expects a clear sunny day, but there is a small chance that a thunderstorm might pass through, they can assess how changing weather conditions could affect the situation. Making this analysis possible is a probabilistic model-based “engine” that uses the probabilistic programming language Figaro™. Figaro makes it possible to rapidly construct probabilistic models for a wide variety of situations from a common knowledge base. Figaro enables ACACIA to apply expert-level knowledge to many different situations while using the appropriate knowledge and data for each situation.
It is anticipated that ACACIA will have two major benefits for the Air Force. First, it will significantly reduce the time spent collecting and processing data from many sources. Second, it will improve assessments of an adversary’s capability by junior analysts, so decision-makers will be better prepared to respond to an adversary’s actions.
Charles River Analytics Cambridge, MA 617-491-3474 www.cra.com
For Free Info Click Here