Signal Cueing in a Complex Environment

It is no longer feasible to know in advance how, when, where, and with which signals an adversary may transmit. Instead, new and unusual “anomalous” uses of spectrum must be identified and evaluated alongside traditional SOIs to protect against threats. Multiple Cue Generators are needed to address this diverse range of signals. These new demands have driven a re-evaluation of sensor system architecture and the methods used to indicate the presence of a SOI. If one views a sensor system as a cascade of signal processing steps, the very first step of determining that a SOI is present initiates a chain of events that infer downstream resources will need to be allocated to turn the SOI observation into actionable information. Producing a SOI ‘report’ is a cue for the system to perform further processing. Modern sensors must embrace a modular approach to flexible and adaptive characterization of wideband RF signal data via sets of Cue Generators (CGs) that have a wide range of possible detection methods and objectives while often operating in a complementary parallel fashion. The objective of this effort is to design and develop a parallel system of adaptive machine learning (ML) cue generators that ensures multi-signal and multi-function electromagnetic spectrum monitoring (ESM) systems with the parallel system will properly respond to signal classes with different probabilities of occurrence and importance.