Fresh Approaches to Battlefield Strategy, Cyber-Terrorism, and Homeland Security
The research team at The National Center for Multisource Information Fusion (CMIF) is developing methods of enhancing national security and improving the accuracy of intelligence gathering. Information fusion works by combining evidence and intelligence gathered from a wide variety of sources, which when considered separately often yield conflicting and ambiguous results. The system combines and organizes the information from such sources as remote satellite, sensors, and individual personnel, and then incorporates it in a seamless flow to a central command center, where decisions can be more effectively rendered. The command center can monitor a constant flow of real-time data, using estimation algorithms or artificial intelligence (AI) techniques to produce far better estimates than those based on any single type of information.
CMIF has recently been awarded two grants from the Office of Naval Research (ONR). One, $500,000 two-year grant currently underway (May 2006-May 2008), involves using higher-level fusion methods to develop an information integration mechanism that will simplify human decision–making in solving operational problems. This mechanism would be an advanced, multi-intelligent system that can organize the information into a hierarchy. Because of the increasing proliferation of sensors on all platforms, human decision makers are being overwhelmed with data. CMIF researchers propose a novel approach in the near “real-time” ranking/formulation of hypotheses in asymmetric warfare scenarios (urban warfare, for example).
The team is gearing up for an upcoming ONR-funded project, to run from April 2007 to May 2010, to develop what they call “Modal Integrity and Discovery Suite” (MInDS). The $3,000,000 grant will allow researchers to support “Situational Awareness” and Impact Assessment” in a given scenario in a way that would allow human decision-makers to perform efficient and accurate “Detect and Engage” naval procedures.
The objective of this project is to identify, track, and offer solutions for abnormalities. Such abnormalities could encompass inconsistencies between multiple SME inputs or between model instances and other relationships (political, military, economic, social, information, or infrastructure dimensions). Other problems that could be addressed by MInDS include uncertainty about the information itself or its provenance, as well as a host of other discoverable irregularities, both within a model and as it is affected by external information sources.
