Reverse Modeling and Autonomous Extrapolation of RF Threats

This paper addresses the investigation of the basic components ofreverse modeling and autonomous extrapolation of radiofrequency (RF) threats in electronic warfare settings. To designand test our system, we first model RF threats using theradioactive parameters received. The enemy radar simulated witha transponder or emitter transmits electronic signals; next, thesensors of the system intercept those signals as radioactiveparameters. We generate the attributes of RF threats duringcommunication between the electronic emissions of RF threatsand the receivers of our system in various electronic warfarescenarios. We then utilize the data acquired through our systemto reversely model RFthreats. Our system carries out the reverseextrapolation process for the purpose of identifying andclassifying threats by using profiles compiled through a series ofmachine learning algorithms, i.e., naive Bayesian classifier,decision tree, and k-means clustering algorithms. Thiscompilation technique, which is based upon the inductive threatmodel, could be used to analyze and predict what a real-timethreat is. We summarize empirical results that demonstrate oursystem capabilities of reversely modeling and autonomouslyextrapolating RF threats in simulated electronic warfare settings

Reverse Modeling and Autonomous Extrapolation of RF Threats Keywords:

Autonomous reverse extrapolation of threats , DataMining using machine learning algorithms , Modeling andgenerating attributes of threats , Simulated electronic warfaresettings