Dr. Mark Rahmes has 20 years of experience at Harris Corporation as an Electrical/Computer Engineer and Research Scientist. He earned his BSEE from The Citadel, MSEE from Duke University and PhD in Operations Research from Florida Tech. Mark is a retired U.S. Navy Reserve Captain and served 22 years as a Commanding Officer, Engineering Duty Officer and Surface Warfare Officer. He currently has 37 patents granted. Mark has published 26 conference papers. At Harris Corporation, Mark serves in the capacity of a Principal Investigator, Chief Software Engineer, and Research Scientist on various programs while advancing image processing research and development. Mark is a member of Tau Beta Pi and Phi Kappa Phi National Honor Societies.

We describe a multi-disciplinary system model for determining decision making strategies based upon the ability to perform data mining and pattern discovery utilizing open source actionable information to prepare for specific events or situations from multiple information sources. We focus on combining detection theory with game theory for classifying ships in Arctic Ocean to verify ship reporting. More specifically, detection theory is used to determine probability of deciding if a ship or certain ship class is present or not. We use game theory to fuse information for optimal decision making on ship classification. Hierarchy game theory framework enables complex modeling of data in probabilistic modeling. However, applicability to big data is complicated by the difficulties of inference in complex probabilistic models, and by computational constraints. We provide a framework for fusing sensor inputs to help compare if the information of a ship matches its AIS reporting requirements using mixed probabilities from game theory. Our method can be further applied to optimizing other choke point scenarios where a decision is needed for classification of ground assets or signals. We model impact on decision making on accuracy by adding more parameters or sensors to the decision making process as sensitivity analysis.