On the Ability of Deep Learning to Detect Signals with Unknown Parameters

TL;DR

This paper evaluates deep learning methods for detecting signals with unknown parameters in noisy environments, comparing their performance to traditional statistical approaches and the matched filter.

Contribution

It introduces DNN-based detection approaches for signals with unknown parameters and compares their effectiveness to classical methods across multiple signal models.

Findings

DNNs outperform traditional methods in detection probability.

Unified training improves detection across different signal types.

Deep learning approaches approach the performance of the matched filter.

Abstract

In many signal processing applications, including communications, sonar, radar, and localization, a fundamental problem is the detection of a signal of interest in background noise, known as signal detection [1] [2]. A simple version of this problem is the detection of a signal of interest with unknown parameters in Additive White Gaussian Noise (AWGN). When the parameters defining the signal are not known, an optimal detector (in the Neyman-Pearson sense) does not exist. An upper bound on the performance of any detector is the matched filter, which implies perfect sample by sample knowledge of the signal of interest. In recent years Deep Neural Networks (DNNs) have proven to be very effective at hypothesis testing problems such as object detection and image classification. This paper examines the application of DNN-based approaches to the signal detection problem at the raw I/Q level and compares them to statistically based approaches as well as the Matched Filter. These methods aim to maximize the Probability of Detection Pd while maintaining a constant Probability of False Alarm PF A. Two Machine Learning (ML) algorithms are trained and assessed on this signal detection problem, across three signal of interest models. A model was also trained on a unified dataset and assessed across all signals of interest.