Government

Machine Analytics has built cloud based big data analytics for the Army.

In the era of net-centric warfare and cloud computing, the Army’s intelligence and operational information sources are highly distributed and diverse. What if we facilitate intelligence analysts to search and analyze distributed data sources across various systems and organizations in natural language without having them to know the format or locations of individual data sources? This is what we have demonstrated under MADSAT, a recently completed Army-funded project. Key benefits of MADSAT are increasing productivity, reducing time and cost, and ability to provide more accurate intelligence analysis for warfighters using all available distributed autonomous data sources, including cloud-based data sources.

MADSAT employs intelligent agent-based technology that generates and transports analytics computations to distributed autonomous data sources within a limited tactical network to aid the decision making process. MADSAT is built on: 1) agent-based, distributed execution of optimized query plans; 2) data modeling for integrating heterogeneous, distributed data sources; 3) distributed fusion for complex analytics; and 4) integrated web-based and customized user interfaces. MADSAT translates a search query to a set of sub-queries via a combination of planning and traditional database query optimization techniques.

MADSAT employs in-house text analytics tool aText for analyst natural language query translation and predictive analytics tool iDAS for complex analytics for situation assessment and threat prediction.