Direction-of-Arrival Estimation in the Low-SNR Regime via a Denoising Autoencoder

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Downloads (Pure)

Abstract

The performance of covariance-based DoA estimation methods is limited in practice, particularly in the low signal-To-noise ratio (SNR) regime, due to the finite number of observations. In this work, we approach the direction-of-Arrival (DoA) estimation in the presence of extreme noise from the Machine Learning (ML) perspective using Deep Learning (DL). First, we derive a relation between the covariance matrix and its sample estimate formulating the problem as a manifold learning task. Next, we train a denoising autoencoder (DAE) that predicts a Hermitian matrix, which is subsequently used for the DoA estimation. Experimental results demonstrate significant performance gains in terms of the root-mean-squared error (RMSE) in the low-SNR regime by using popular covariance-based DoA estimators. Nevertheless, the proposed method runs independent of the DoA estimator, opening up new possibilities for the testing of other methods as well. We believe that the proposed approach has several applications, ranging from wireless array sensors to microphones and transducers used in ultrasound imaging, where the operating environments are characterized by extreme noise.

Original languageEnglish
Title of host publication2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
PublisherIEEE
ISBN (Electronic)9781728154787
DOIs
Publication statusPublished - 3 Aug 2020
Event21st IEEE International Workshop on Signal Processing Advances in Wireless Communications 2020 - Atlanta, United States
Duration: 26 May 202029 May 2020

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications
ISSN (Electronic)1948-3252

Conference

Conference21st IEEE International Workshop on Signal Processing Advances in Wireless Communications 2020
Abbreviated titleSPAWC 2020
CountryUnited States
CityAtlanta
Period26/05/2029/05/20

Keywords

  • array processing with uniform linear arrays ULAs
  • deep learning
  • denoising autoencoder DAE
  • Direction-of-Arrival DoA estimation
  • DoA estimation at low-SNR

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Direction-of-Arrival Estimation in the Low-SNR Regime via a Denoising Autoencoder'. Together they form a unique fingerprint.

Cite this