Multi-Domain Integration and Correlation Engine

William Dron, Andrew Hunter, Ali Sydney, Siddharth Pal, John Hancock, Lisa Scott, Tarek Abdelzaher, Jiawei Han, Sibel Adali, Benjamin Horne

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As Machine Learning becomes more prominent in the military, we are faced with a different take on the old problem of how to collect data relevant to some military mission need. We can now embrace the paradigm of too much data where previously we needed to focus on data reduction because humans can only process a finite amount of information. Commanders, analysts, and intelligence officers are often tasked with understanding the current situation in a mission area to create a common operating picture in order to complete their mission objectives. Data pertaining to missions can often be scraped from multiple domains, including patrol reports, newswire, and RF sensors, image sensors, and various other sensor types in the field. In this paper, we describe a system called the Multi-Domain Integration and Correlation Engine (MD-ICE), which ingests data which ingests data from two domains: textual open source information (newswire and social media)and sensor network information, and processes it using tools from various machine learning research areas. MD-ICE manipulates the resulting data into a machine readable unified format to allow for labelling and inference of inter-domain correlations. The goal of MD-ICE is to utilize these information domains to better understand situational context, where open source information provides semantic context (i.e. what type of event, who is involved, etc...)and the sensor network information provides the fine-grain detail (how many people involved, exact area of the event, etc...). This understanding of situational context in turn can, with further research, help commanders reach their mission objectives faster through better situational understanding and prediction of future needs.

Original languageEnglish (US)
Title of host publication2018 IEEE Military Communications Conference, MILCOM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1074-1079
Number of pages6
ISBN (Electronic)9781538671856
DOIs
StatePublished - Jan 2 2019
Event2018 IEEE Military Communications Conference, MILCOM 2018 - Los Angeles, United States
Duration: Oct 29 2018Oct 31 2018

Publication series

NameProceedings - IEEE Military Communications Conference MILCOM
Volume2019-October

Conference

Conference2018 IEEE Military Communications Conference, MILCOM 2018
CountryUnited States
CityLos Angeles
Period10/29/1810/31/18

Keywords

  • Entity extraction
  • Integration
  • Machine learning
  • Multi domain battle
  • Multimodal
  • Natural language processing
  • Network monitoring
  • Open source
  • Phrase mining
  • Sensor networks
  • Signal processing
  • Social media
  • Social sensing
  • Source selection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Multi-Domain Integration and Correlation Engine'. Together they form a unique fingerprint.

  • Cite this

    Dron, W., Hunter, A., Sydney, A., Pal, S., Hancock, J., Scott, L., Abdelzaher, T., Han, J., Adali, S., & Horne, B. (2019). Multi-Domain Integration and Correlation Engine. In 2018 IEEE Military Communications Conference, MILCOM 2018 (pp. 1074-1079). [8599706] (Proceedings - IEEE Military Communications Conference MILCOM; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MILCOM.2018.8599706