Date of Award
Dissertation (Access Restricted)
Doctor of Philosophy
David J. Russomanno
Aaron L. Robinson
Amy L. de Jongh Curry
The development of numerous situational awareness sensing environments deployed with ubiquitous sensor systems and algorithms has led to many challenges associated with assigning and coordinating systems to complete high-level missions. These challenges are compounded even further by the lack of requisite knowledge models needed to opportunistically integrate the capabilities of sensor systems and algorithms to satisfy a task. A novel ontological problem-solving framework has been designed and developed that captures knowledge of systems to facilitate automated inference to discover, match and task sensor systems and algorithms by creating synthesized systems in real-time and then assigning the systems to subtasks to satisfy a given mission specification. To facilitate the automated inference, the ontological framework leverages knowledge and data models through the use of knowledge engineering techniques such as ontologies, declarative rules based on description logic, and inference engines. To show proof-of-concept principles, the ontological framework was instantiated in the context of a persistence surveillance sensing environment that includes many different types of profiling sensor systems and innovative algorithms. Even though the ontological framework was instantiated in the context of a persistence surveillance sensing environment, the problem-solving approach may be useful in other heterogeneous sensing environments.
Dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.
Qualls, Joseph Bezeke, "Ontological Problem-Solving Framework for Dynamically Discovering, Matching, and Tasking Sensor Systems and Algorithms" (2011). Electronic Theses and Dissertations. 2270.