Model-aided Deep Neural Network for Source Number Detection

TL;DR

This paper introduces deep neural networks, ERNet and ECNet, to improve source number detection in array signal processing, especially under challenging conditions like low SNR or few snapshots, outperforming traditional methods.

Contribution

The paper proposes novel DNN architectures for source number detection, extending to coherent sources with spatial smoothing, demonstrating superior performance over classical techniques.

Findings

ERNet and ECNet outperform AIC and MDL in accuracy.

Networks generalize well across different scenarios.

Effective for both coherent and non-coherent sources.

Abstract

Source number detection is a critical problem in array signal processing. Conventional model-driven methods e.g., Akaikes information criterion (AIC) and minimum description length (MDL), suffer from severe performance degradation when the number of snapshots is small or the signal-to-noise ratio (SNR) is low. In this paper, we exploit the model-aided based deep neural network (DNN) to estimate the source number. Specifically, we first propose the eigenvalue based regression network (ERNet) and classification network (ECNet) to estimate the number of non-coherent sources, where the eigenvalues of the received signal covariance matrix and the source number are used as the input and the supervise label of the networks, respectively. Then, we extend the ERNet and ECNet for estimating the number of coherent sources, where the forward-backward spatial smoothing (FBSS) scheme is adopted to improve the performance of ERNet and ECNet. Numerical results demonstrate the outstanding performance of ERNet and ECNet over the conventional AIC and MDL methods as well as their excellent generalization capability, which also shows their great potentials for practical applications.