Cargando…

Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals

In recent years, with the growing popularity of complex signal approximation via deep neural networks, people have begun to pay close attention to the spectral bias of neural networks—a problem that occurs when a neural network is used to fit broadband signals. An important direction taken to overco...

Descripción completa

Detalles Bibliográficos
Autores principales: Zeng, Zhi, Shi, Pengpeng, Ma, Fulei, Qi, Peihan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9573465/
https://www.ncbi.nlm.nih.gov/pubmed/36236446
http://dx.doi.org/10.3390/s22197347
_version_ 1784810876911484928
author Zeng, Zhi
Shi, Pengpeng
Ma, Fulei
Qi, Peihan
author_facet Zeng, Zhi
Shi, Pengpeng
Ma, Fulei
Qi, Peihan
author_sort Zeng, Zhi
collection PubMed
description In recent years, with the growing popularity of complex signal approximation via deep neural networks, people have begun to pay close attention to the spectral bias of neural networks—a problem that occurs when a neural network is used to fit broadband signals. An important direction taken to overcome this problem is the use of frequency selection-based fitting techniques, of which the representative work is called the PhaseDNN method, whose core idea is the use of bandpass filters to extract frequency bands with high energy concentration and fit them by different neural networks. Despite the method’s high accuracy, we found in a large number of experiments that the method is less efficient for fitting broadband signals with smooth spectrums. In order to substantially improve its efficiency, a novel candidate—the parallel frequency function-deep neural network (PFF-DNN)—is proposed by utilizing frequency domain analysis of broadband signals and the spectral bias nature of neural networks. A substantial improvement in efficiency was observed in the extensive numerical experiments. Thus, the PFF-DNN method is expected to become an alternative solution for broadband signal fitting.
format Online
Article
Text
id pubmed-9573465
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95734652022-10-17 Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals Zeng, Zhi Shi, Pengpeng Ma, Fulei Qi, Peihan Sensors (Basel) Article In recent years, with the growing popularity of complex signal approximation via deep neural networks, people have begun to pay close attention to the spectral bias of neural networks—a problem that occurs when a neural network is used to fit broadband signals. An important direction taken to overcome this problem is the use of frequency selection-based fitting techniques, of which the representative work is called the PhaseDNN method, whose core idea is the use of bandpass filters to extract frequency bands with high energy concentration and fit them by different neural networks. Despite the method’s high accuracy, we found in a large number of experiments that the method is less efficient for fitting broadband signals with smooth spectrums. In order to substantially improve its efficiency, a novel candidate—the parallel frequency function-deep neural network (PFF-DNN)—is proposed by utilizing frequency domain analysis of broadband signals and the spectral bias nature of neural networks. A substantial improvement in efficiency was observed in the extensive numerical experiments. Thus, the PFF-DNN method is expected to become an alternative solution for broadband signal fitting. MDPI 2022-09-28 /pmc/articles/PMC9573465/ /pubmed/36236446 http://dx.doi.org/10.3390/s22197347 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zeng, Zhi
Shi, Pengpeng
Ma, Fulei
Qi, Peihan
Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title_full Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title_fullStr Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title_full_unstemmed Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title_short Parallel Frequency Function-Deep Neural Network for Efficient Approximation of Complex Broadband Signals
title_sort parallel frequency function-deep neural network for efficient approximation of complex broadband signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9573465/
https://www.ncbi.nlm.nih.gov/pubmed/36236446
http://dx.doi.org/10.3390/s22197347
work_keys_str_mv AT zengzhi parallelfrequencyfunctiondeepneuralnetworkforefficientapproximationofcomplexbroadbandsignals
AT shipengpeng parallelfrequencyfunctiondeepneuralnetworkforefficientapproximationofcomplexbroadbandsignals
AT mafulei parallelfrequencyfunctiondeepneuralnetworkforefficientapproximationofcomplexbroadbandsignals
AT qipeihan parallelfrequencyfunctiondeepneuralnetworkforefficientapproximationofcomplexbroadbandsignals