The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
pandangan teks lengkap
82
Anggaran arah ketibaan (DOA) bagi isyarat wayarles mempunyai sejarah yang panjang tetapi masih disiasat untuk meningkatkan ketepatan anggaran. Algoritma bukan linear seperti penderiaan termampat kini digunakan pada anggaran DOA dan mencapai prestasi yang sangat tinggi. Jika beban pengiraan yang besar bagi algoritma penderiaan termampat boleh diterima, adalah mungkin untuk menggunakan rangkaian saraf dalam (DNN) pada anggaran DOA. Dalam makalah ini, kami mengesahkan keupayaan anggaran DOA atas grid DNN di bawah situasi anggaran mudah dan membincangkan kesan data latihan pada reka bentuk DNN. Simulasi menunjukkan bahawa SNR data latihan sangat mempengaruhi prestasi dan bahawa data SNR rawak sesuai untuk mengkonfigurasi DNN tujuan umum. DNN yang diperolehi memberikan prestasi yang agak tinggi dan menunjukkan bahawa DNN yang dilatih menggunakan data latihan yang terhad untuk menutup situasi DOA memberikan prestasi yang sangat tinggi untuk kes DOA yang tertutup.
Yuya KASE
Hokkaido University
Toshihiko NISHIMURA
Hokkaido University
Takeo OHGANE
Hokkaido University
Yasutaka OGAWA
Hokkaido University
Daisuke KITAYAMA
NTT DOCOMO, INC.
Yoshihisa KISHIYAMA
NTT DOCOMO, INC.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Yuya KASE, Toshihiko NISHIMURA, Takeo OHGANE, Yasutaka OGAWA, Daisuke KITAYAMA, Yoshihisa KISHIYAMA, "Fundamental Trial on DOA Estimation with Deep Learning" in IEICE TRANSACTIONS on Communications,
vol. E103-B, no. 10, pp. 1127-1135, October 2020, doi: 10.1587/transcom.2019EBP3260.
Abstract: Direction of arrival (DOA) estimation of wireless signals has a long history but is still being investigated to improve the estimation accuracy. Non-linear algorithms such as compressed sensing are now applied to DOA estimation and achieve very high performance. If the large computational loads of compressed sensing algorithms are acceptable, it may be possible to apply a deep neural network (DNN) to DOA estimation. In this paper, we verify on-grid DOA estimation capability of the DNN under a simple estimation situation and discuss the effect of training data on DNN design. Simulations show that SNR of the training data strongly affects the performance and that the random SNR data is suitable for configuring the general-purpose DNN. The obtained DNN provides reasonably high performance, and it is shown that the DNN trained using the training data restricted to close DOA situations provides very high performance for the close DOA cases.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2019EBP3260/_p
Salinan
@ARTICLE{e103-b_10_1127,
author={Yuya KASE, Toshihiko NISHIMURA, Takeo OHGANE, Yasutaka OGAWA, Daisuke KITAYAMA, Yoshihisa KISHIYAMA, },
journal={IEICE TRANSACTIONS on Communications},
title={Fundamental Trial on DOA Estimation with Deep Learning},
year={2020},
volume={E103-B},
number={10},
pages={1127-1135},
abstract={Direction of arrival (DOA) estimation of wireless signals has a long history but is still being investigated to improve the estimation accuracy. Non-linear algorithms such as compressed sensing are now applied to DOA estimation and achieve very high performance. If the large computational loads of compressed sensing algorithms are acceptable, it may be possible to apply a deep neural network (DNN) to DOA estimation. In this paper, we verify on-grid DOA estimation capability of the DNN under a simple estimation situation and discuss the effect of training data on DNN design. Simulations show that SNR of the training data strongly affects the performance and that the random SNR data is suitable for configuring the general-purpose DNN. The obtained DNN provides reasonably high performance, and it is shown that the DNN trained using the training data restricted to close DOA situations provides very high performance for the close DOA cases.},
keywords={},
doi={10.1587/transcom.2019EBP3260},
ISSN={1745-1345},
month={October},}
Salinan
TY - JOUR
TI - Fundamental Trial on DOA Estimation with Deep Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 1127
EP - 1135
AU - Yuya KASE
AU - Toshihiko NISHIMURA
AU - Takeo OHGANE
AU - Yasutaka OGAWA
AU - Daisuke KITAYAMA
AU - Yoshihisa KISHIYAMA
PY - 2020
DO - 10.1587/transcom.2019EBP3260
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E103-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2020
AB - Direction of arrival (DOA) estimation of wireless signals has a long history but is still being investigated to improve the estimation accuracy. Non-linear algorithms such as compressed sensing are now applied to DOA estimation and achieve very high performance. If the large computational loads of compressed sensing algorithms are acceptable, it may be possible to apply a deep neural network (DNN) to DOA estimation. In this paper, we verify on-grid DOA estimation capability of the DNN under a simple estimation situation and discuss the effect of training data on DNN design. Simulations show that SNR of the training data strongly affects the performance and that the random SNR data is suitable for configuring the general-purpose DNN. The obtained DNN provides reasonably high performance, and it is shown that the DNN trained using the training data restricted to close DOA situations provides very high performance for the close DOA cases.
ER -