Instinctive analytics for coalition operations

Abstract The success of future military coalition operations—be they combat or humanitarian—will increasingly depend on a system's ability to share data and processing services (e.g. aggregation, summarization, fusion), and automatically compose services in support of complex tasks at the network edge. We call such an infrastructure instinctive—i.e., an infrastructure that reacts instinctively to address the analytics task at hand. However, developing such an infrastructure is made complex for the coalition environment due to its dynamism both in terms of user requirements and service availability. In order to address the above challenge, in this paper, we highlight our research vision and sketch some initial solutions into the problem domain. Specifically, we propose means to (1) automatically infer formal task requirements from mission specifications; (2) discover data, services, and their features automatically to satisfy the identified requirements; (3) create and augment shared domain models automatically; (4) efficiently offload services to the network edge and across coalition boundaries adhering to their computational properties and costs; and (5) optimally allocate and adjust services while respecting the constraints of operating environment and service fit. We envision that the research will result in a framework which enables self-description, discover, and assemble capabilities to both data and services in support of coalition mission goals.
  • Chris Simpkin (Cardiff)
  • Geeth de Mel (IBM UK)
  • Graham Bent (IBM UK)
  • Hana Khamfroush (PSU)
  • Ian Taylor (Cardiff)
  • Jorge Ortiz (IBM US)
  • Sebastian Stein (Southampton)
  • Swati Rallapalli (IBM US)
  • Ting He (PSU)
  • Tom La Porta (PSU)
Date Apr-2017
Venue SPIE - Defense + Commercial Sensing 2017