Zhao, Ying

Accurate, relevant and timely combat identification (CID) enables the warfighter to locate and identify critical airborne targets with high precision. An effective CID capability optimizes the use of long-range weapons, aids in fratricide reduction, enhances battlefield situational awareness, and reduces exposure of U.S. forces to enemy fire. The traditional information systems cannot meet the requirement for the Common Tactical Air Picture (CT AP) and CID. Big Data Architecture and Analytics (BDAA) show promise to enhance CID dramatically. In the past year, we identified/assessed the current CT AP, identified key elements and the best combination of platforms, sensors, networks, and data in a common tactical air picture. We also researched and provided potential BDAA solutions and evidence that BDAA has the potential to improve CTAP and CID as follows: 1) object recognition and classification by continuous monitoring time and space, collecting and processing data in a cloud and in parallel; 2) associate learning to correlation of data attributes for linking and fusing cross-domain and heterogeneous data sources by machine learning; 3) apply the knowledge by BDAA to the real-time battlespace match and search. We propose a follow-on study to build on results obtained from the initial 2015 study by building a use case, to illustrate practical applications of BDAA to support CID, CTAP, decision making and resource management as inputs to Battle Management Aids (BMA).
NPS Naval Research Program
NPS Naval Research Program
Navy
2017