Architectural Design Considerations for Context-Aware Support in RECON Intelligence Analysis


  1. Morris, A.
  2. Ross, W.
  3. Ulieruy, M.
  4. Lafond, D.
  5. Proulx, R.
  6. Bergeron-Guyard, A.
Corporate Authors
Defence Research and Development Canada, Valcartier Research Centre, Quebec QC (CAN);New Brunswick Univ, Fredericton NB (CAN) Faculty of Computer Science
The REcommending Cases based on cONtext (RECON) system is a prototype adaptive technology designed to support intelligence analysts in overcoming the problem of cognitive overload. Its central objective is to assist these analysts during the collection, processing, and analysis phases of the intelligence cycle through sense-making of both explicit and implicit contextual information. RECON combines machine learning, text-analysis, brain-computer interfaces, and simulation to create an innovative case-based recommendation capability. In developing RECON, multiple considerations have been explored based on key HCI dilemmas that emerge when designing joint-cognitive systems endowed with an adaptive capacity. Herein, eight architectural design considerations are discussed, related to human-modelling, human-machine interaction, and human-machine synergy, which have impacted the system development. The central RECON architecture and its components are also presented, including a context-sensitive cognitive model based on COCOM. This work aims to provide these core architectural components and their design considerations as a contribution toward aiding developers in designing, customizing, and improving future adaptive contextmanagement systems.
adaptive system;human computer interaction;context awareness case-based recommendation;brain-computer interface;information relevance;trust;modeling;virtual assistant;complex systems
Report Number
DRDC-RDDC-2015-P135 — External Literature
Date of publication
09 Dec 2015
Number of Pages
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: