Deep Tensor 2-D DOA Estimation for URA

Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)

Authors

Date

2024

Department

Department of Information and Communications Engineering

Major/Subject

Mcode

Degree programme

Language

en

Pages

16

Series

IEEE Transactions on Signal Processing, Volume 72, pp. 4065-4080

Abstract

Direction-of-arrival (DOA) estimation using deep neural networks has shown great potential for applications in complicated environments. However, conventional matrix-based deep neural networks vectorize multi-dimensional signal statistics into an excessively long input, necessitating a large number of parameters in neural layers. These parameters require substantial computational resources for training. To address the problem, we propose a resource-efficient tensorized neural network for deep tensor two-dimensional DOA estimation. In this network, the covariance tensor corresponding to the uniform rectangular array (URA) is propagated to hidden state tensors that encapsulate essential signal features. To reduce the number of trainable parameters, the feedforward propagation is formulated as inverse Tucker decomposition, compressing the parameters into inverse Tucker factors. An effective tensorized backpropagation procedure is then designed to train the compressed parameters, and the Tucker rank sequences are tuned through Bayesian optimization to ensure satisfactory network performance. Our simulation results demonstrate the superiority of the proposed tensorized deep neural network over its matrix-based counterpart. In a scenario with a 10× 10 URA and 2 sources, the proposed network reduces the number of trained parameters by more than 122,000 times. Consequently, it achieves faster training speed and utilizes less GPU memory, while maintains comparable estimation accuracy and angular resolution even under non-ideal conditions and in varying scenarios.

Description

Publisher Copyright: IEEE

Keywords

Artificial neural networks, Deep neural network, Direction-of-arrival estimation, direction-of-arrival estimation, Estimation, Neural networks, tensorized neural network, Tensors, Training, Tucker decomposition, Vectors

Other note

DOI

10.1109/TSP.2024.3449117

Citation

Zheng, H, Shi, Z, Zhou, C, Vorobyov, S A & Gu, Y 2024, 'Deep Tensor 2-D DOA Estimation for URA', IEEE Transactions on Signal Processing, vol. 72, pp. 4065-4080. https://doi.org/10.1109/TSP.2024.3449117

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202501171311

Collections

[article-cris] Palvelut / Services