A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices

Designing a denoising framework for high-mobility environments is challenging due to the limited size of collected data and low latency requirements. In this paper, we introduce a neural network (NN)-assisted denoiser for sparse signals in the frequency domain, referred to as dssNET, based on the lo...

Full description

Saved in:
Bibliographic Details
Main Authors: Wanjei Cho, Seong-Cheol Kim, Woong-Hee Lee
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10806718/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850251946087153664
author Wanjei Cho
Seong-Cheol Kim
Woong-Hee Lee
author_facet Wanjei Cho
Seong-Cheol Kim
Woong-Hee Lee
author_sort Wanjei Cho
collection DOAJ
description Designing a denoising framework for high-mobility environments is challenging due to the limited size of collected data and low latency requirements. In this paper, we introduce a neural network (NN)-assisted denoiser for sparse signals in the frequency domain, referred to as dssNET, based on the low-rank property of the transformed Hankel matrices constructed from sparse signals. The proposed method is based on optimizing the NN model by inputting singular values of the noisy transformed Hankel matrices and outputting the ground truth singular values. Furthermore, we additionally propose the advanced version of dssNET, referred to as selective dssNET (sdssNET), which can be operated more adaptively with the current signal-to-noise ratio (SNR). Notably, the proposed schemes show excellent denoising performance while requiring an extremely small training dataset compared to conventional schemes. Finally, we provide an application of joint-range-and-velocity estimation in automotive radar systems to validate the benefit of our proposed method in practical scenarios.
format Article
id doaj-art-fe80186c432648c6ae67a83c4f112bc8
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-fe80186c432648c6ae67a83c4f112bc82025-08-20T01:57:47ZengIEEEIEEE Access2169-35362024-01-011219299019300010.1109/ACCESS.2024.351958010806718A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel MatricesWanjei Cho0https://orcid.org/0009-0000-5136-4005Seong-Cheol Kim1https://orcid.org/0000-0002-7896-5625Woong-Hee Lee2https://orcid.org/0000-0002-1064-5123Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Republic of KoreaDepartment of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Republic of KoreaDivision of Electronics and Electrical Engineering, Dongguk University-Seoul, Seoul, Republic of KoreaDesigning a denoising framework for high-mobility environments is challenging due to the limited size of collected data and low latency requirements. In this paper, we introduce a neural network (NN)-assisted denoiser for sparse signals in the frequency domain, referred to as dssNET, based on the low-rank property of the transformed Hankel matrices constructed from sparse signals. The proposed method is based on optimizing the NN model by inputting singular values of the noisy transformed Hankel matrices and outputting the ground truth singular values. Furthermore, we additionally propose the advanced version of dssNET, referred to as selective dssNET (sdssNET), which can be operated more adaptively with the current signal-to-noise ratio (SNR). Notably, the proposed schemes show excellent denoising performance while requiring an extremely small training dataset compared to conventional schemes. Finally, we provide an application of joint-range-and-velocity estimation in automotive radar systems to validate the benefit of our proposed method in practical scenarios.https://ieeexplore.ieee.org/document/10806718/Signal denoisingsparse signalsneural networks
spellingShingle Wanjei Cho
Seong-Cheol Kim
Woong-Hee Lee
A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
IEEE Access
Signal denoising
sparse signals
neural networks
title A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
title_full A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
title_fullStr A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
title_full_unstemmed A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
title_short A Neural Network-Assisted Denoiser for Sparse Signals With Low Rank Property of Transformed Hankel Matrices
title_sort neural network assisted denoiser for sparse signals with low rank property of transformed hankel matrices
topic Signal denoising
sparse signals
neural networks
url https://ieeexplore.ieee.org/document/10806718/
work_keys_str_mv AT wanjeicho aneuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices
AT seongcheolkim aneuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices
AT woongheelee aneuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices
AT wanjeicho neuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices
AT seongcheolkim neuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices
AT woongheelee neuralnetworkassisteddenoiserforsparsesignalswithlowrankpropertyoftransformedhankelmatrices