A Neural Network-Prepended GLRT Framework for Signal Detection Under Nonlinear Distortions

TL;DR

This paper introduces a neural network-enhanced GLRT framework that improves signal detection in nonlinear environments by pre-processing signals to identify and remove nonlinear distortions, maintaining detection accuracy.

Contribution

The paper proposes a novel neural network-based pre-processing step for the GLRT detector to handle nonlinear distortions in signals, enhancing detection performance while preserving theoretical guarantees.

Findings

Improved detection accuracy on nonlinear signals.

Neural network pre-processing effectively identifies nonlinear samples.

Maintains GLRT's theoretical detection guarantees.

Abstract

Many communications and sensing applications hinge on the detection of a signal in a noisy, interference-heavy environment. Signal processing theory yields techniques such as the generalized likelihood ratio test (GLRT) to perform detection when the received samples correspond to a linear observation model. Numerous practical applications exist, however, where the received signal has passed through a nonlinearity, causing significant performance degradation of the GLRT. In this work, we propose prepending the GLRT detector with a neural network classifier capable of identifying the particular nonlinear time samples in a received signal. We show that pre-processing received nonlinear signals using our trained classifier to eliminate excessively nonlinear samples (i) improves the detection performance of the GLRT on nonlinear signals and (ii) retains the theoretical guarantees provided by the GLRT on linear observation models for accurate signal detection.