CaltechAUTHORS
  A Caltech Library Service

Feature Engineering for DOA Estimation using a Convolutional Neural Network, for Sparse Arrays

Kulkarni, Pranav and Vaidyanathan, P. P. (2021) Feature Engineering for DOA Estimation using a Convolutional Neural Network, for Sparse Arrays. In: 2021 55th Asilomar Conference on Signals, Systems, and Computers. IEEE , Piscataway, NJ, pp. 246-250. ISBN 978-1-6654-5828-3. https://resolver.caltech.edu/CaltechAUTHORS:20220317-376187000

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20220317-376187000

Abstract

In the past few years, there has been an emerging use of deep neural networks for improving the direction of arrival (DOA) estimation performance. This paper demonstrates how such methods can be applied for sparse arrays such as nested arrays, by adapting a recent method based on convolutional neural network (CNN). Many possible alternative inputs (proxy spectra) to the network are suggested here, and experiments show that even simple modifications of the input lead to improved DOA estimation performance without changing the network structure. Additionally, the experiments also show that, with the modified input proxy spectra it is possible to identify more sources than the number of physical sensors, as one would expect with nested arrays. This opens up further avenues of using coarray principles in conjunction with machine learning methods.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/IEEECONF53345.2021.9723112DOIArticle
ORCID:
AuthorORCID
Kulkarni, Pranav0000-0002-1461-0948
Vaidyanathan, P. P.0000-0003-3003-7042
Additional Information:© 2021 IEEE. This work was supported in parts by the ONR grant N00014-21-1-2521, and the California Institute of Technology
Funders:
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-21-1-2521
CaltechUNSPECIFIED
Subject Keywords:Direction of arrival (DOA) estimation, deep neural networks, convolutional neural network, sparse arrays, co-array
DOI:10.1109/ieeeconf53345.2021.9723112
Record Number:CaltechAUTHORS:20220317-376187000
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20220317-376187000
Official Citation:P. Kulkarni and P. P. Vaidyanathan, "Feature Engineering for DOA Estimation using a Convolutional Neural Network, for Sparse Arrays," 2021 55th Asilomar Conference on Signals, Systems, and Computers, 2021, pp. 246-250, doi: 10.1109/IEEECONF53345.2021.9723112
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:113936
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:18 Mar 2022 21:35
Last Modified:18 Mar 2022 21:35

Repository Staff Only: item control page