HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

Accuracy Improvement in DOA Estimation with Deep Learning

Files in This Item:
E105.B_2021EBT0001.pdf8.15 MBPDFView/Open
Please use this identifier to cite or link to this item:

Title: Accuracy Improvement in DOA Estimation with Deep Learning
Authors: Kase, Yuya Browse this author
Nishimura, Toshihiko Browse this author →KAKEN DB
Ohgane, Takeo Browse this author →KAKEN DB
Ogawa, Yasutaka Browse this author →KAKEN DB
Sato, Takanori Browse this author
Kishiyama, Yoshihisa Browse this author
Keywords: DOA estimation
deep learning
machine learning
Issue Date: May-2022
Publisher: IEICE - Institute of the Electronics, Information and Communication Engineers
Journal Title: IEICE transactions on communications
Volume: E105B
Issue: 5
Start Page: 588
End Page: 599
Publisher DOI: 10.1587/transcom.2021EBT0001
Abstract: Direction of arrival (DOA) estimation of wireless signals is demanded in many applications. In addition to classical methods such as MUSIC and ESPRIT, non-linear algorithms such as compressed sensing have become common subjects of study recently. Deep learning or machine learning is also known as a non-linear algorithm and has been applied in various fields. Generally, DOA estimation using deep learning is classified as on-grid estimation. A major problem of on-grid estimation is that the accuracy may be degraded when the DOA is near the boundary. To reduce such estimation errors, we propose a method of combining two DNNs whose grids are offset by one half of the grid size. Simulation results show that our proposal outperforms MUSIC which is a typical off-grid estimation method. Furthermore, it is shown that the DNN specially trained for a close DOA case achieves very high accuracy for that case compared with MUSIC.
Rights: copyright©2022 IEICE
Type: article
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 大鐘 武雄

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 - Hokkaido University