Assessment of Bistatic Track Likelihood in Passive Radar Using Artificial Neural Networks

This paper proposes a novel method for assessing bistatic track likelihood in passive radar systems using artificial neural networks (ANNs). By combining radar sig-nal processing with machine learning, the approach distinguishes genuine object tracks fromfalse detections. Key contributions include an end-to-end simulationframework that models target dynamics, measurement errors, and false alarms. The results highlight the potential of machine learning to improve the reliability of passive radar and offer a scal-able solution for real-world use, advancing data-driven methods in radar track assess-ment.