Deep Neural Networks Based End-to-End DOA Estimation System

Daniel Akira ANDO; Yuya KASE; Toshihiko NISHIMURA; Takanori SATO; Takeo OHGANE; Yasutaka OGAWA; Junichiro HAGIWARA

doi:10.1587/transcom.2023CEP0006

Open Access
Deep Neural Networks Based End-to-End DOA Estimation System

Daniel Akira ANDO, Yuya KASE, Toshihiko NISHIMURA, Takanori SATO, Takeo OHGANE, Yasutaka OGAWA, Junichiro HAGIWARA

Full Text Views

132

Cite this

Free PDF (3MB)

Summary :

Direction of arrival (DOA) estimation is an antenna array signal processing technique used in, for instance, radar and sonar systems, source localization, and channel state information retrieval. As new applications and use cases appear with the development of next generation mobile communications systems, DOA estimation performance must be continually increased in order to support the nonstop growing demand for wireless technologies. In previous works, we verified that a deep neural network (DNN) trained offline is a strong candidate tool with the promise of achieving great on-grid DOA estimation performance, even compared to traditional algorithms. In this paper, we propose new techniques for further DOA estimation accuracy enhancement incorporating signal-to-noise ratio (SNR) prediction and an end-to-end DOA estimation system, which consists of three components: source number estimator, DOA angular spectrum grid estimator, and DOA detector. Here, we expand the performance of the DOA detector and angular spectrum estimator, and present a new solution for source number estimation based on DNN with very simple design. The proposed DNN system applied with said enhancement techniques has shown great estimation performance regarding the success rate metric for the case of two radio wave sources although not fully satisfactory results are obtained for the case of three sources.

Publication: IEICE TRANSACTIONS on Communications Vol.E106-B No.12 pp.1350-1362

Publication Date: 2023/12/01

Publicized: 2023/09/11

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2023CEP0006

Type of Manuscript: Special Section PAPER (Special Section on Emerging Communication Technologies in Conjunction with Main Topics of ICETC 2022)

Category

Authors

Daniel Akira ANDO
  Hokkaido University
Yuya KASE
  Hokkaido University
Toshihiko NISHIMURA
  Hokkaido University
Takanori SATO
  Hokkaido University
Takeo OHGANE
  Hokkaido University
Yasutaka OGAWA
  Hokkaido University
Junichiro HAGIWARA
  Hokkaido University

Keyword

antenna array, DOA estimation, SNR estimation, source number estimation, deep neural network

Cite this

Copy

Daniel Akira ANDO, Yuya KASE, Toshihiko NISHIMURA, Takanori SATO, Takeo OHGANE, Yasutaka OGAWA, Junichiro HAGIWARA, "Deep Neural Networks Based End-to-End DOA Estimation System" in IEICE TRANSACTIONS on Communications, vol. E106-B, no. 12, pp. 1350-1362, December 2023, doi: 10.1587/transcom.2023CEP0006.
Abstract: Direction of arrival (DOA) estimation is an antenna array signal processing technique used in, for instance, radar and sonar systems, source localization, and channel state information retrieval. As new applications and use cases appear with the development of next generation mobile communications systems, DOA estimation performance must be continually increased in order to support the nonstop growing demand for wireless technologies. In previous works, we verified that a deep neural network (DNN) trained offline is a strong candidate tool with the promise of achieving great on-grid DOA estimation performance, even compared to traditional algorithms. In this paper, we propose new techniques for further DOA estimation accuracy enhancement incorporating signal-to-noise ratio (SNR) prediction and an end-to-end DOA estimation system, which consists of three components: source number estimator, DOA angular spectrum grid estimator, and DOA detector. Here, we expand the performance of the DOA detector and angular spectrum estimator, and present a new solution for source number estimation based on DNN with very simple design. The proposed DNN system applied with said enhancement techniques has shown great estimation performance regarding the success rate metric for the case of two radio wave sources although not fully satisfactory results are obtained for the case of three sources.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2023CEP0006/_p

Copy

@ARTICLE{e106-b_12_1350,
author={Daniel Akira ANDO, Yuya KASE, Toshihiko NISHIMURA, Takanori SATO, Takeo OHGANE, Yasutaka OGAWA, Junichiro HAGIWARA, },
journal={IEICE TRANSACTIONS on Communications},
title={Deep Neural Networks Based End-to-End DOA Estimation System},
year={2023},
volume={E106-B},
number={12},
pages={1350-1362},
abstract={Direction of arrival (DOA) estimation is an antenna array signal processing technique used in, for instance, radar and sonar systems, source localization, and channel state information retrieval. As new applications and use cases appear with the development of next generation mobile communications systems, DOA estimation performance must be continually increased in order to support the nonstop growing demand for wireless technologies. In previous works, we verified that a deep neural network (DNN) trained offline is a strong candidate tool with the promise of achieving great on-grid DOA estimation performance, even compared to traditional algorithms. In this paper, we propose new techniques for further DOA estimation accuracy enhancement incorporating signal-to-noise ratio (SNR) prediction and an end-to-end DOA estimation system, which consists of three components: source number estimator, DOA angular spectrum grid estimator, and DOA detector. Here, we expand the performance of the DOA detector and angular spectrum estimator, and present a new solution for source number estimation based on DNN with very simple design. The proposed DNN system applied with said enhancement techniques has shown great estimation performance regarding the success rate metric for the case of two radio wave sources although not fully satisfactory results are obtained for the case of three sources.},
keywords={},
doi={10.1587/transcom.2023CEP0006},
ISSN={1745-1345},
month={December},}

Copy

TY - JOUR
TI - Deep Neural Networks Based End-to-End DOA Estimation System
T2 - IEICE TRANSACTIONS on Communications
SP - 1350
EP - 1362
AU - Daniel Akira ANDO
AU - Yuya KASE
AU - Toshihiko NISHIMURA
AU - Takanori SATO
AU - Takeo OHGANE
AU - Yasutaka OGAWA
AU - Junichiro HAGIWARA
PY - 2023
DO - 10.1587/transcom.2023CEP0006
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 12
JA - IEICE TRANSACTIONS on Communications
Y1 - December 2023
AB - Direction of arrival (DOA) estimation is an antenna array signal processing technique used in, for instance, radar and sonar systems, source localization, and channel state information retrieval. As new applications and use cases appear with the development of next generation mobile communications systems, DOA estimation performance must be continually increased in order to support the nonstop growing demand for wireless technologies. In previous works, we verified that a deep neural network (DNN) trained offline is a strong candidate tool with the promise of achieving great on-grid DOA estimation performance, even compared to traditional algorithms. In this paper, we propose new techniques for further DOA estimation accuracy enhancement incorporating signal-to-noise ratio (SNR) prediction and an end-to-end DOA estimation system, which consists of three components: source number estimator, DOA angular spectrum grid estimator, and DOA detector. Here, we expand the performance of the DOA detector and angular spectrum estimator, and present a new solution for source number estimation based on DNN with very simple design. The proposed DNN system applied with said enhancement techniques has shown great estimation performance regarding the success rate metric for the case of two radio wave sources although not fully satisfactory results are obtained for the case of three sources.
ER -