Accuracy Improvement in DOA Estimation with Deep Learning
Accuracy Improvement in DOA Estimation with Deep Learning
复制标题
DOI：
10.1587/transcom.2021ebt0001
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Yuya Kase;T. Nishimura;T. Ohgane;Y. Ogawa;Takanori Sato;Y. Kishiyama
中科院分区：
文献类型：
--
作者：
Yuya Kase;T. Nishimura;T. Ohgane;Y. Ogawa;Takanori Sato;Y. Kishiyama
在许多应用中都需要对无线信号的到达方向进行估计。除了MUSIC和ESPRIT等经典方法外，压缩感知等非线性算法也成为近年来研究的常见课题。深度学习或机器学习也被称为非线性算法，并已应用于各个领域。一般来说，使用深度学习的DOA估计被归类为网格上估计。在网格上估计的一个主要问题是当DOA接近边界时，精度可能会下降。减少
SUMMARY 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