Model Order Selection in DoA Scenarios via Cross-Entropy based Machine Learning Techniques

TL;DR

This paper introduces a neural network-based method using cross-entropy for model order selection in DoA scenarios, demonstrating improved accuracy over classical methods, especially with limited data and low SNR.

Contribution

It proposes a novel neural network approach with online training for adaptive model order estimation without explicit array calibration.

Findings

Outperforms classical information criteria in accuracy

Effective with few snapshots and low SNR

Online training enables quick adaptation with minimal data

Abstract

In this paper, we present a machine learning approach for estimating the number of incident wavefronts in a direction of arrival scenario. In contrast to previous works, a multilayer neural network with a cross-entropy objective is trained. Furthermore, we investigate an online training procedure that allows an adaption of the neural network to imperfections of an antenna array without explicitly calibrating the array manifold. We show via simulations that the proposed method outperforms classical model order selection schemes based on information criteria in terms of accuracy, especially for a small number of snapshots and at low signal-to-noise-ratios. Also, the online training procedure enables the neural network to adapt with only a few online training samples, if initialized by offline training on artificial data.