DARPA Wants More From Military Sensor Data

Defense research agency funds wants to bridge the language gap between military sensor data and what human analysts can discern.

The Defense Advanced Research Projects Agency (DARPA) has awarded a grant to Stevens Institute of Technology to help it develop a mathematical language to better communicate information that military sensors collect.

Stevens will aim to manage all sensor and surveillance data collected by the Department of Defense for DARPA's Mathematics of Sensing, Exploitation, and Execution (MSEE) program, the institute said in a statement. To do this, the institute will use cognitive linguistics tactics to try to create a language to bridge the semantic gap between raw sensor data and the level of analysis humans can provide, it said.


More Government Insights

Webcasts

More >>

White Papers

More >>

Reports

More >>

Its work will aim to do this by teaching sensors to linguistically identify primitive concepts--like things, places, and actions--directly within their data streams. In that way, the systems can then produce a language that functions across sensing platforms and can be made coherent to humans, according to the institute.

[ Army intelligence to stop roadside bombs came from an unexpected source. Learn more: Social Network Analytics Saves Lives In Iraq. ]

Data from a range of devices and systems--such as radar systems, video surveillance, and audio recordings--will be included in the work. The institute did not disclose the financial terms of the grant.

Dr. Hong Man and Dr. Yu-Dong Yao, both of the institute's department of electrical and computer engineering, will lead Stevens' work on the project. They believe that by adding a linguistic framework to the information from sensor systems they can enable the sensors to not only understand and communicate threats, but also respond to them.

"The scope of the problem naturally draws one's attention to the scientific specialty of cognitive linguistics for inspiring insights into the nature of semantic representation as the intersection between human languages (i.e., queries) and technical languages (i.e., sensor data processing outputs)," said Dr. Man in a statement.

DARPA started work on the MSEE program in September after first putting out a request for proposals last January.

In addition to Stevens Institute, DARPA has awarded other MSEE grants to Brown University, the Massachusetts Institute of Technology, Duke University, University of California Berkeley, and two teams at the University of California Los Angeles, an agency spokesperson said via email.

DARPA also has two MSEE-related, but separately funded, projects underway at the University of Vermont and the University of Rhode Island, and will soon set up a website to provide more information on those efforts, the spokesperson said.

DARPA also is engaged in other projects to try to get the most out of military sensors. Through its Adaptable Sensor System (ADAPT) program, for instance, the agency is working on a commercial development model to facilitate more rapid delivery and configuration of sensors. DARPA recently put out a call for mobile application developers to use mobile apps to enhance its ADAPT program.

Our annual Federal Government IT Priorities Survey shows how agencies are managing the many mandates competing for their limited resources. Also in the new issue of InformationWeek Government: NASA veterans launch cloud startups, and U.S. Marshals Service completes tech revamp. Download the issue now. (Free registration required.)


Related Reading




Currently we allow the following HTML tags in comments:

Single tags

These tags can be used alone and don't need an ending tag.

<br> Defines a single line break

<hr> Defines a horizontal line

Matching tags

These require an ending tag - e.g. <i>italic text</i>

<a> Defines an anchor

<b> Defines bold text

<big> Defines big text

<blockquote> Defines a long quotation

<caption> Defines a table caption

<cite> Defines a citation

<code> Defines computer code text

<em> Defines emphasized text

<fieldset> Defines a border around elements in a form

<h1> This is heading 1

<h2> This is heading 2

<h3> This is heading 3

<h4> This is heading 4

<h5> This is heading 5

<h6> This is heading 6

<i> Defines italic text

<p> Defines a paragraph

<pre> Defines preformatted text

<q> Defines a short quotation

<samp> Defines sample computer code text

<small> Defines small text

<span> Defines a section in a document

<s> Defines strikethrough text

<strike> Defines strikethrough text

<strong> Defines strong text

<sub> Defines subscripted text

<sup> Defines superscripted text

<u> Defines underlined text

InformationWeek encourages readers to engage in spirited, healthy debate, including taking us to task. However, InformationWeek moderates all comments posted to our site, and reserves the right to modify or remove any content that it determines to be derogatory, offensive, inflammatory, vulgar, irrelevant/off-topic, racist or obvious marketing/SPAM. InformationWeek further reserves the right to disable the profile of any commenter participating in said activities.

Disqus Tips To upload an avatar photo, first complete your Disqus profile. | View the list of supported HTML tags you can use to style comments. | Please read our commenting policy.
Subscribe to RSS

Resource Links