
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

Broadband Direction of Arrival Estimation Based on Convolutional Neural Network
Wenli ZHU Min ZHANG Chenxi WU Lingqing ZENG
Publication
IEICE TRANSACTIONS on Communications
Vol.E103B
No.3
pp.148154 Publication Date: 2020/03/01
Online ISSN: 17451345
DOI: 10.1587/transcom.2018EBP3357
Type of Manuscript: PAPER Category: Fundamental Theories for Communications Keyword: deep learning, direction of arrival, convolutional neural network, uniform circle array,
Full Text: FreePDF(1.5MB)
Summary:
A convolutional neural network (CNN) for broadband direction of arrival (DOA) estimation of farfield 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 signaltonoise 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.

