Butterfly Neural Filter Applied to Beamforming
The butterfly neural beamformer (NB-Butterfly) is a new adaptive multiple-antenna spatial neural filter inspired on the neural butterfly equalizer (NE-Butterfly), a filter intended to equalize any channel that has real or complex taps, whether linear or nonlinear. Due to the broad use cases of the N...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8765559/ |
id |
doaj-db15fbfa60a44143bfb0f0af5f19b66c |
---|---|
record_format |
Article |
spelling |
doaj-db15fbfa60a44143bfb0f0af5f19b66c2021-04-05T17:09:22ZengIEEEIEEE Access2169-35362019-01-017964559646910.1109/ACCESS.2019.29295908765559Butterfly Neural Filter Applied to BeamformingTiago F. B. de Sousa0Marcelo A. C. Fernandes1https://orcid.org/0000-0001-7536-2506Federal Institute of Rio Grande do Norte, Ceará-Mirim, BrazilDepartment of Computer Engineering and Automation, Federal University of Rio Grande do Norte (UFRN), Natal, BrazilThe butterfly neural beamformer (NB-Butterfly) is a new adaptive multiple-antenna spatial neural filter inspired on the neural butterfly equalizer (NE-Butterfly), a filter intended to equalize any channel that has real or complex taps, whether linear or nonlinear. Due to the broad use cases of the NE-Butterfly, the objective in this paper is to introduce this novel beamforming filter, the NB-Butterfly and analyze its performance by comparing to other neural and linear beamformers, while also presenting an enhanced training strategy that wasn't present in the butterfly neural architecture before, which is called butterfly neural beamformer with joint error (NB-Butterfly-JE). The proposals are evaluated and compared for different types of channels in order to validate their performance in different use cases.https://ieeexplore.ieee.org/document/8765559/Butterfly beamformeradaptive beamformingartificial neural networksneural beamformer |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tiago F. B. de Sousa Marcelo A. C. Fernandes |
spellingShingle |
Tiago F. B. de Sousa Marcelo A. C. Fernandes Butterfly Neural Filter Applied to Beamforming IEEE Access Butterfly beamformer adaptive beamforming artificial neural networks neural beamformer |
author_facet |
Tiago F. B. de Sousa Marcelo A. C. Fernandes |
author_sort |
Tiago F. B. de Sousa |
title |
Butterfly Neural Filter Applied to Beamforming |
title_short |
Butterfly Neural Filter Applied to Beamforming |
title_full |
Butterfly Neural Filter Applied to Beamforming |
title_fullStr |
Butterfly Neural Filter Applied to Beamforming |
title_full_unstemmed |
Butterfly Neural Filter Applied to Beamforming |
title_sort |
butterfly neural filter applied to beamforming |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The butterfly neural beamformer (NB-Butterfly) is a new adaptive multiple-antenna spatial neural filter inspired on the neural butterfly equalizer (NE-Butterfly), a filter intended to equalize any channel that has real or complex taps, whether linear or nonlinear. Due to the broad use cases of the NE-Butterfly, the objective in this paper is to introduce this novel beamforming filter, the NB-Butterfly and analyze its performance by comparing to other neural and linear beamformers, while also presenting an enhanced training strategy that wasn't present in the butterfly neural architecture before, which is called butterfly neural beamformer with joint error (NB-Butterfly-JE). The proposals are evaluated and compared for different types of channels in order to validate their performance in different use cases. |
topic |
Butterfly beamformer adaptive beamforming artificial neural networks neural beamformer |
url |
https://ieeexplore.ieee.org/document/8765559/ |
work_keys_str_mv |
AT tiagofbdesousa butterflyneuralfilterappliedtobeamforming AT marceloacfernandes butterflyneuralfilterappliedtobeamforming |
_version_ |
1721540187252588544 |