Broadband Direction of Arrival Estimation Based on Convolutional Neural Network

Wenli ZHU; Min ZHANG; Chenxi WU; Lingqing ZENG

doi:10.1587/transcom.2018EBP3357

IEICE TRANSACTIONS on Communications

Open Access
Broadband Direction of Arrival Estimation Based on Convolutional Neural Network

Wenli ZHU, Min ZHANG, Chenxi WU, Lingqing ZENG

Full Text Views

49

Cite this

Free PDF (1.5MB)

Summary :

A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of far-field electromagnetic signals is presented. The proposed algorithm performs a nonlinear inverse mapping from received signal to angle of arrival. The signal model used for algorithm is based on the circular antenna array geometry, and the phase component extracted from the spatial covariance matrix is used as the input of the CNN network. A CNN model including three convolutional layers is then established to approximate the nonlinear mapping. The performance of the CNN model is evaluated in a noisy environment for various values of signal-to-noise ratio (SNR). The results demonstrate that the proposed CNN model with the phase component of the spatial covariance matrix as the input is able to achieve fast and accurate broadband DOA estimation and attains perfect performance at lower SNR values.

Publication: IEICE TRANSACTIONS on Communications Vol.E103-B No.3 pp.148-154

Publication Date: 2020/03/01

Publicized: 2019/08/27

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2018EBP3357

Type of Manuscript: PAPER

Category: Fundamental Theories for Communications

Authors

Wenli ZHU
  National University of Defense Technology
Min ZHANG
  National University of Defense Technology
Chenxi WU
  National University of Defense Technology
Lingqing ZENG

Keyword

deep learning, direction of arrival, convolutional neural network, uniform circle array

Cite this

Copy

Wenli ZHU, Min ZHANG, Chenxi WU, Lingqing ZENG, "Broadband Direction of Arrival Estimation Based on Convolutional Neural Network" in IEICE TRANSACTIONS on Communications, vol. E103-B, no. 3, pp. 148-154, March 2020, doi: 10.1587/transcom.2018EBP3357.
Abstract: A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of far-field electromagnetic signals is presented. The proposed algorithm performs a nonlinear inverse mapping from received signal to angle of arrival. The signal model used for algorithm is based on the circular antenna array geometry, and the phase component extracted from the spatial covariance matrix is used as the input of the CNN network. A CNN model including three convolutional layers is then established to approximate the nonlinear mapping. The performance of the CNN model is evaluated in a noisy environment for various values of signal-to-noise ratio (SNR). The results demonstrate that the proposed CNN model with the phase component of the spatial covariance matrix as the input is able to achieve fast and accurate broadband DOA estimation and attains perfect performance at lower SNR values.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018EBP3357/_p

Copy

@ARTICLE{e103-b_3_148,
author={Wenli ZHU, Min ZHANG, Chenxi WU, Lingqing ZENG, },
journal={IEICE TRANSACTIONS on Communications},
title={Broadband Direction of Arrival Estimation Based on Convolutional Neural Network},
year={2020},
volume={E103-B},
number={3},
pages={148-154},
abstract={A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of far-field electromagnetic signals is presented. The proposed algorithm performs a nonlinear inverse mapping from received signal to angle of arrival. The signal model used for algorithm is based on the circular antenna array geometry, and the phase component extracted from the spatial covariance matrix is used as the input of the CNN network. A CNN model including three convolutional layers is then established to approximate the nonlinear mapping. The performance of the CNN model is evaluated in a noisy environment for various values of signal-to-noise ratio (SNR). The results demonstrate that the proposed CNN model with the phase component of the spatial covariance matrix as the input is able to achieve fast and accurate broadband DOA estimation and attains perfect performance at lower SNR values.},
keywords={},
doi={10.1587/transcom.2018EBP3357},
ISSN={1745-1345},
month={March},}

Copy

TY - JOUR
TI - Broadband Direction of Arrival Estimation Based on Convolutional Neural Network
T2 - IEICE TRANSACTIONS on Communications
SP - 148
EP - 154
AU - Wenli ZHU
AU - Min ZHANG
AU - Chenxi WU
AU - Lingqing ZENG
PY - 2020
DO - 10.1587/transcom.2018EBP3357
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E103-B
IS - 3
JA - IEICE TRANSACTIONS on Communications
Y1 - March 2020
AB - A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of far-field electromagnetic signals is presented. The proposed algorithm performs a nonlinear inverse mapping from received signal to angle of arrival. The signal model used for algorithm is based on the circular antenna array geometry, and the phase component extracted from the spatial covariance matrix is used as the input of the CNN network. A CNN model including three convolutional layers is then established to approximate the nonlinear mapping. The performance of the CNN model is evaluated in a noisy environment for various values of signal-to-noise ratio (SNR). The results demonstrate that the proposed CNN model with the phase component of the spatial covariance matrix as the input is able to achieve fast and accurate broadband DOA estimation and attains perfect performance at lower SNR values.
ER -

IEICE TRANSACTIONS on Communications