Research Summaries

Back Data Mining SIGINT Collections at Very Large Scale

Fiscal Year 2019
Division Graduate School of Engineering & Applied Science
Department Electrical & Computer Engineering
Investigator(s) Kragh, Frank E.
Sponsor Department of Defense Space (DoD)
Summary The overall objective of our work is to automatically sort a very large volume of SIGINT collects so human analysts can be alerted to collects of the highest potential intelligence value while also enabling the human analysts to conduct data mining, including machine learning (ML) algorithms on the data to gain more intelligence value from the data. During the period of performance we will develop a distributed database architecture, prototype software for signal analysis, the analyst's dashboard, and machine learning algorithms and process SIGINT data on clusters of computers using this prototype software. The massive size of the data makes traditional single node analysis of the data very impractical. The researchers have expertise in signal analysis, large-scale cluster computing, and machine learning, thereby enabling us to provide an architecture and an initial solution to the problem of sorting a very high volume of SIGINT collects.
Keywords Big Data Data Mining
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal