Please use this identifier to cite or link to this item:
|Title:||A Fast Polarization Estimation Method with Convolutional Neural Networks||Authors:||Onur Y.
|Keywords:||Convolutional neural networks
Cost benefit analysis
Multiple signal classification
Convolutional neural network
|Issue Date:||2022||Publisher:||Institute of Electrical and Electronics Engineers Inc.||Abstract:||In this study, we propose a new method with an artificial intelligence infrastructure to estimate polarization of a radar signal. In modern electronic warfare and radar systems polarization of the return signal now poses essential information. Subspace-based algorithms such as MUSIC and ESPRIT have high computational costs for estimating polarization. Computational cost and performance analysis of the proposed method is conducted via simulations and results are discussed along with the existing solutions such as MUSIC algorithm. Simulation results show that the proposed algorithm reduce the computational cost compared to classical MUSIC. The proposed algorithm also reduce the polarization estimation error in low SNR scenarios. © 2022 IEEE.||Description:||9th IEEE International Workshop on Metrology for AeroSpace, MetroAeroSpace 2022 -- 27 June 2022 through 29 June 2022 -- -- 182210||URI:||https://doi.org/10.1109/MetroAeroSpace54187.2022.9855981
|Appears in Collections:||Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection|
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show full item record
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.