Accuracy Improvement in DOA Estimation with Deep Learning

DOI HANDLE Web Site 被引用文献2件 参考文献17件 オープンアクセス
  • KASE Yuya
    Graduate School/Faculty of Information Science and Technology, Hokkaido University
  • NISHIMURA Toshihiko
    Graduate School/Faculty of Information Science and Technology, Hokkaido University
  • OHGANE Takeo
    Graduate School/Faculty of Information Science and Technology, Hokkaido University
  • OGAWA Yasutaka
    Graduate School/Faculty of Information Science and Technology, Hokkaido University
  • SATO Takanori
    Graduate School/Faculty of Information Science and Technology, Hokkaido University
  • KISHIYAMA Yoshihisa
    Research Laboratories, NTT DOCOMO, INC.

この論文をさがす

抄録

<p>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.</p>

収録刊行物

被引用文献 (2)*注記

もっと見る

参考文献 (17)*注記

もっと見る

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ