C4iSR: Joint & Common Equipment

DARPA to develop 'semantic engine' to mine open-source, multimedia data

11 April 2017

The US Defense Advanced Research Projects Agency (DARPA) has launched a programme to develop technologies capable of automatically aggregating and mapping pieces of information derived from multiple media sources into a common representation or storyline.

From that storyline, the technology developed under the Active Interpretation of Disparate Alternatives (AIDA) programme should be capable of generating hypotheses about the "true nature and implications of events, situations, and trends of interest", according to a DARPA announcement, which outlined that proposed research should enable "revolutionary advances in science, devices, or systems" and exclude "evolutionary improvements to the existing state of practice".

The technology will be the basis for a "semantic engine" that would provide better understanding of trends and events, separating out irrelevant, conflicting, and deceptive data.

Want to read more? For analysis on this article and access to all our insight content, please enquire about our subscription options:

(147 of 629 words)