NICOP - Context-aware Intent Recognition

Abstract

Context-aware Intent Recognition:This proposal addresses an importance topic for a wide range of Navy "surveillance" applications ranging from vessels movements to information flows in computer networks. While the community has made significant process in the lower levels of individual sensors and sensors fusion, less attention and less progress has been made in developing automated procedures based upon strong algorithmic formulations that can deduce significant activity from the observation of individual actions. This proposal attempts to do so use incorporating a range of mathematical formulations and moreover, contextual information. It is very important to start to include contextual information in the multiple level information fusion and reasoning and inference processes. CI could help to explain observations, refine ambiguous results and constrain processing. The proposer will attempt to incorporate context based reasoning using a combination of logic and probabilistic based methods to develop a hybrid architecture. This proposal has been discussed with ONR Code 311 and has financial support from two ONR PO: Pejda Neskovic and Behzad Kamgar-Parsi and additional interest by Gary Toth. This multiple PO interest shows that this effort is bridging the gap between the sometime stove piped methods and interests. The desire outcome is that this proposal is funded and that significant results are achieved that will give the Navy enhanced capabilities to reason against a wide range of threat scenarios--both physical and cyber. v

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 03, 2017
Source ID
N629091712011

Entities

People

  • Lauro Snidaro

Organizations

  • Office of Naval Research
  • United States Navy

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Distributed Systems and Data Platform Development
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • Cyber