ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification

TL;DR

This paper introduces the Evidential Lifelong Classifier (ELC), which combines uncertainty quantification with continual learning to improve radar pulse classification, especially under low signal-to-noise conditions.

Contribution

It proposes an evidential approach to model epistemic uncertainty within a lifelong learning framework, enhancing reliability and confidence in radar pulse recognition.

Findings

Selective prediction with evidential uncertainty boosts recall by up to 46% at -20 dB SNR.

ELC outperforms Bayesian Lifelong Classifier in identifying unreliable predictions.

Evidential uncertainty correlates strongly with prediction correctness, improving trustworthiness.

Abstract

Reliable radar pulse classification is essential in Electromagnetic Warfare for situational awareness and decision support. Deep Neural Networks have shown strong performance in radar pulse and RF emitter recognition; however, on their own they struggle to efficiently learn new pulses and lack mechanisms for expressing predictive confidence. This paper integrates Uncertainty Quantification with Lifelong Learning to address both challenges. The proposed approach is an Evidential Lifelong Classifier (ELC), which models epistemic uncertainty using evidence theory. ELC is evaluated against a Bayesian Lifelong Classifier (BLC), which quantifies uncertainty through Shannon entropy. Both integrate Learn-Prune-Share to enable continual learning of new pulses and uncertainty-based selective prediction to reject unreliable predictions. ELC and BLC are evaluated on 2 synthetic radar and 3 RF fingerprinting datasets. Selective prediction based on evidential uncertainty improves recall by up to 46% at -20 dB SNR on synthetic radar pulse datasets, highlighting its effectiveness at identifying unreliable predictions in low-SNR conditions compared to BLC. These findings demonstrate that evidential uncertainty offers a strong correlation between confidence and correctness, improving the trustworthiness of ELC by allowing it to express ignorance.