Machine Learning-based Cognitive EW for C4ISR Automation

A. Walker
Vadum, Inc., United States

Keywords: cognitive EW, machine learning, radar countermeasures, battle damage assessment, situational awareness

Vadum has developed a suite of cognitive EW capabilities leveraging online and offline machine learning techniques to provide a decisive edge to the warfighter navigating a complex EW battlespace. Adaptive Radar Countermeasures (ARC) provides real-time characterization of unknown radar threats based on online threat model construction using physics and information-based inferences. These model construction techniques and inferences are also employed by Reactive Electronic Countermeasures (REAM) with the objective of jamming unknown hostile threats. EW Battle Damage Assessment (EW-BDA) provides real-time estimates of BDA to an Electronic Warfare Officer (EWO) on RF links within a threat network under attack by monitoring and analyzing link communication patterns. EW Spectral Situational Awareness (EW-SSA) provides an EWO real-time, explainable feedback on spectrum state and spectral anomalies by inferring and analyzing the dynamic electronic order of battle. Vadum cognitive EW capabilities involve real-time analysis of streaming sensor data using cutting-edge machine learning techniques for the purposes of threat identification and capability determination under ES and EA conditions. These capabilities provide an analyst automated and powerful C4ISR tools to help maximize mission success, reduce fratricide and support rapid development and update to Course of Action within the Military Decision Making Process.