Adaptive Toolkit for Pattern Discovery (ATPD)

This project will design, configure, and demonstrate an Adaptive Toolkit for Pattern Discovery (ATPD). We propose a novel approach that combines emerging machine learning techniques with advanced rule-based methods to (i) automate the discovery of complex system-of-systems data utilization patterns and (ii) apply the learned usage patterns to dynamically update enterprise knowledge models being used for enterprise integration applications. The research seeks to validate the research hypothesis: information access and usage patterns may provide important heuristics for positioning new concepts and relations to the enterprise knowledge repository. It is envisioned that the proposed ATPD capability will be used to (a) monitor information use across systems, (b) discover usage patterns, (c) analyze patterns for potential new (and useful) concepts and relations, and (d) offer intelligent assistance to enterprise knowledge modelers about the integration of newly learned concepts into the evolving reference knowledge models. The Phase I effort established the technical viability of the research by demonstrating a proof-of-concept ATPD system and integrating the ATPD with the Air Force Knowledge Management Framework (KMF). The Phase II project will harden the ATPD technology and build a focused and field-able ATPD application at 45th Space Wing, Cape Canaveral Air Force Station (CCAFS).