A policy-based approach to automated data reduction for intelligence, surveillance, and reconnaissance systems

Department of Defense (DoD) intelligence, surveillance, and reconnaissance (ISR) assets; including manned and unmanned airborne, space-borne, maritime, and terrestrial systems; play critical roles in support of current and future military operations. However, military services and defense agencies face an ever growing challenge of effectively processing, exploiting, and disseminating ISR data from multiple, diverse senor platforms for end-users who collaborate and share information within a net-centric enterprise environment. Adding to the physical limitations of transport and infrastructure are personnel shortages with respect to the number of operator and analytical staff possessing the required skill sets to effectively exploit collected ISR information. This shortage raises the risk that important information may not be available to war fighters in a timely manner that assures mission success. The Multifactor Analytics Information Engine (MAIE) directly addresses the aforementioned issues by reducing the flood of sensor data to only actionable information that is directly applicable to the mission-at-hand. MAIE focuses on target discovery, communication capacity management, and automation techniques that enable ISR system operators and analysts to derive the knowledge they need to meet end-user mission requirements. A primary feature of the MAIE approach is the use of on-board processing, close to the sensor on the platform where the data originates. This processing includes screening and then compressing the data using established algorithms before transmission to the operations center for dissemination and exploitation. A major contribution of MAIE is its novel approach for automatically selecting these algorithms based on premeditated mission plans and dynamically occurring mission events. We implement a policy-based management system driven by a rules-based, event-correlation engine to select the most appropriate algorithms to reduce sensor data to only mis- ion-required exploitation products. By doing so, MAIE greatly improves productivity of operators and analysts to enable them to meet end-user time-critical needs while using fewer resources.