Noise Learning-Based Denoising Autoencoder

This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by subtracting the regenerated noise from the noisy input. Hence, nlDAE i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters Vol. 25; no. 9; pp. 2983 - 2987
Main Authors: Lee, Woong-Hee, Ozger, Mustafa, Challita, Ursula, Sung, Ki Won
Format: Journal Article
Language:English
Published: New York IEEE 01.09.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:1089-7798, 1558-2558, 1558-2558
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by subtracting the regenerated noise from the noisy input. Hence, nlDAE is more effective than DAE when the noise is simpler to regenerate than the original data. To validate the performance of nlDAE, we provide three case studies: signal restoration, symbol demodulation, and precise localization. Numerical results suggest that nlDAE requires smaller latent space dimension and smaller training dataset compared to DAE.
AbstractList This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by subtracting the regenerated noise from the noisy input. Hence, nlDAE is more effective than DAE when the noise is simpler to regenerate than the original data. To validate the performance of nlDAE, we provide three case studies: signal restoration, symbol demodulation, and precise localization. Numerical results suggest that nlDAE requires smaller latent space dimension and smaller training dataset compared to DAE.
Author Sung, Ki Won
Lee, Woong-Hee
Challita, Ursula
Ozger, Mustafa
Author_xml – sequence: 1
  givenname: Woong-Hee
  orcidid: 0000-0002-1064-5123
  surname: Lee
  fullname: Lee, Woong-Hee
  email: woongheelee@korea.ac.kr
  organization: Department of Control and Instrumentation Engineering, Korea University, Sejong-si, Republic of Korea
– sequence: 2
  givenname: Mustafa
  orcidid: 0000-0001-8517-7996
  surname: Ozger
  fullname: Ozger, Mustafa
  email: ozger@kth.se
  organization: School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
– sequence: 3
  givenname: Ursula
  orcidid: 0000-0002-6625-1529
  surname: Challita
  fullname: Challita, Ursula
  email: ursula.challita@ericsson.com
  organization: Ericsson Research, Stockholm, Sweden
– sequence: 4
  givenname: Ki Won
  orcidid: 0000-0001-7642-3067
  surname: Sung
  fullname: Sung, Ki Won
  email: sungkw@kth.se
  organization: School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
BackLink https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-302636$$DView record from Swedish Publication Index (Kungliga Tekniska Högskolan)
BookMark eNp9kD1PwzAQhi1UJNrCH4ClEhtSin1u4mQsLV9SShdgtRznUlxKXOxEiH-PS6oODCz3pfe5O70D0qttjYScMzpmjGbX-Wy5WIyBAhtzmrGU0iPSZ3GcRhBCL9Q0zSIhsvSEDLxfU0pTiFmfXD1Z43GUo3K1qVfRjfJYjuZYh3HoR9O2sVhrW6I7JceV2ng82-chebm7fZ49RPny_nE2zSPNhWiiTLGKJYVGCJlDypjWEwUlJlWIXAkNFdNVEU9ACywUV0kpMi2KgCsogA9J1O31X7htC7l15kO5b2mVkXPzOpXWreR78yY5hYQnQX_Z6bfOfrboG7m2ravDixJiwQBYIlhQQafSznrvsDrsZVTuPJS_Hsqdh3LvYYDSP5A2jWqMrRunzOZ_9KJDDSIebmWTBFKe8R8N7YCi
CODEN ICLEF6
CitedBy_id crossref_primary_10_1088_1742_6596_2822_1_012084
crossref_primary_10_3390_s24227257
crossref_primary_10_1109_LCOMM_2023_3272972
crossref_primary_10_1109_LCOMM_2025_3578081
crossref_primary_10_3390_app13063534
crossref_primary_10_3390_pr9081266
crossref_primary_10_1109_ACCESS_2022_3164714
crossref_primary_10_1177_10775463251342614
crossref_primary_10_1109_TNS_2024_3454701
crossref_primary_10_1007_s11277_022_09693_z
crossref_primary_10_1109_ACCESS_2024_3366899
crossref_primary_10_1016_j_oceaneng_2024_117280
crossref_primary_10_1007_s11277_022_09965_8
crossref_primary_10_1109_ACCESS_2025_3529853
crossref_primary_10_1109_TCCN_2022_3195511
crossref_primary_10_3389_fpls_2023_1158933
crossref_primary_10_1080_03772063_2025_2547999
crossref_primary_10_1109_TIM_2025_3545981
crossref_primary_10_3390_electronics13061029
crossref_primary_10_1016_j_compbiomed_2023_107440
crossref_primary_10_1109_ACCESS_2025_3583069
crossref_primary_10_1109_TNSRE_2024_3450854
crossref_primary_10_1109_TIM_2022_3212551
crossref_primary_10_1016_j_medengphy_2025_104406
crossref_primary_10_1002_itl2_70022
crossref_primary_10_3390_app132312734
crossref_primary_10_3390_app15052656
crossref_primary_10_1109_LCOMM_2024_3362509
crossref_primary_10_1109_TVT_2023_3348803
crossref_primary_10_1109_ACCESS_2024_3519580
crossref_primary_10_1016_j_joes_2023_12_004
crossref_primary_10_1007_s00034_025_03262_y
crossref_primary_10_1007_s11277_024_10912_y
crossref_primary_10_1007_s40766_025_00073_4
crossref_primary_10_3390_s22031260
crossref_primary_10_1016_j_adhoc_2024_103412
crossref_primary_10_1109_TCE_2025_3562388
crossref_primary_10_1109_ACCESS_2023_3323038
crossref_primary_10_1038_s41467_024_54704_1
crossref_primary_10_3390_sym14020395
crossref_primary_10_3390_smartcities8050153
Cites_doi 10.1109/COMST.2019.2924243
10.1145/1390156.1390294
10.1109/TBC.2002.804034
10.1109/COMST.2019.2926625
10.1109/MCOM.001.1900664
10.1109/MCOM.2019.1800610
10.1109/MSP.2015.2398954
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
ADTPV
AOWAS
D8V
DOI 10.1109/LCOMM.2021.3091800
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
SwePub
SwePub Articles
SWEPUB Kungliga Tekniska Högskolan
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList

Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2558
EndPage 2987
ExternalDocumentID oai_DiVA_org_kth_302636
10_1109_LCOMM_2021_3091800
9462839
Genre orig-research
GrantInformation_xml – fundername: BK21 FOUR (Fostering Outstanding Universities for Research) funded by the Ministry of Education (MOE, Korea) and National Research Foundation of Korea (NRF)
  funderid: 10.13039/501100003725
– fundername: European Union Horizon 2020 Research and Innovation Programme under the EU/KR PriMO-5G project
  grantid: 815191
  funderid: 10.13039/501100000780
– fundername: Korea University Grant
  funderid: 10.13039/501100002642
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
AZLTO
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
HZ~
H~9
IES
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TN5
VH1
AAYXX
CITATION
7SP
8FD
L7M
ADTPV
AOWAS
D8V
ID FETCH-LOGICAL-c377t-9a1f16bce21f132811cc4a2de6fa2d3a7c2f1cfb542c7eba3a6d79c7bc37a2b23
IEDL.DBID RIE
ISICitedReferencesCount 49
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000694697800046&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1089-7798
1558-2558
IngestDate Tue Nov 04 17:20:17 EST 2025
Mon Jun 30 10:12:13 EDT 2025
Sat Nov 29 03:56:07 EST 2025
Tue Nov 18 21:33:22 EST 2025
Wed Aug 27 02:27:34 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 9
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c377t-9a1f16bce21f132811cc4a2de6fa2d3a7c2f1cfb542c7eba3a6d79c7bc37a2b23
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7642-3067
0000-0002-1064-5123
0000-0002-6625-1529
0000-0001-8517-7996
OpenAccessLink https://ieeexplore.ieee.org/document/9462839
PQID 2571221671
PQPubID 85419
PageCount 5
ParticipantIDs ieee_primary_9462839
swepub_primary_oai_DiVA_org_kth_302636
proquest_journals_2571221671
crossref_primary_10_1109_LCOMM_2021_3091800
crossref_citationtrail_10_1109_LCOMM_2021_3091800
PublicationCentury 2000
PublicationDate 2021-09-01
PublicationDateYYYYMMDD 2021-09-01
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE communications letters
PublicationTitleAbbrev LCOMM
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref8
bengio (ref6) 2013
ref9
ref4
ref3
ref5
marsh (ref7) 2013
ref2
ref1
References_xml – start-page: 899
  year: 2013
  ident: ref6
  article-title: Generalized denoising auto-encoders as generative models
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref4
  doi: 10.1109/COMST.2019.2924243
– ident: ref5
  doi: 10.1145/1390156.1390294
– ident: ref8
  doi: 10.1109/TBC.2002.804034
– ident: ref2
  doi: 10.1109/COMST.2019.2926625
– ident: ref1
  doi: 10.1109/MCOM.001.1900664
– ident: ref3
  doi: 10.1109/MCOM.2019.1800610
– year: 2013
  ident: ref7
  publication-title: Introduction to continuous entropy
– ident: ref9
  doi: 10.1109/MSP.2015.2398954
SSID ssj0008251
Score 2.5335813
Snippet This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE...
SourceID swepub
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2983
SubjectTerms Decoding
Demodulation
Encoding
Internet of Things
Learning
Machine learning
noise learning based denoising autoencoder
Noise measurement
Noise reduction
precise localization
Random variables
signal restoration
symbol demodulation
Training
Title Noise Learning-Based Denoising Autoencoder
URI https://ieeexplore.ieee.org/document/9462839
https://www.proquest.com/docview/2571221671
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-302636
Volume 25
WOSCitedRecordID wos000694697800046&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE
  customDbUrl:
  eissn: 1558-2558
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008251
  issn: 1089-7798
  databaseCode: RIE
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLa2iQMceA3EYKAeEAeg25K0SXMcGxMHNjgA2i1q0xQmUIu2jt9PknbVkBASl75kR5Gdxk5ifwY49w1mmSLYJZhT12NSmkPCnquJSah8FhEc22ITbDIJplP-WIPrKhdGKWWDz1THPNqz_DiTS7NV1uUmkZLwOtQZY0WuVjXrmhTMIpiea4-RB6sEmR7v3g8exmO9FMSoQ7R5DEw225oRslVVfjqY66Ch1tCMdv7XxV3YLh1Kp1-MgD2oqXQfttZgBptwOclmC-WUUKqv7o22XLEzVKn-rN-d_jLPDJ5lrOYH8Dy6fRrcuWWNBFcSxnKXhyhBNJIK6zvBAUJSeiGOFU30lYRM4gTJJPI9LJmKtAJozLhkkWYPcYTJITTSLFVH4CQM0ygyB4OUe4EySynJkiRG3PMxo7wFaCU0IUsAcVPH4kPYhUSPCytoYQQtSkG34Kri-SzgM_6kbhqJVpSlMFvQXulGlH_YQuipBmGMKEMtuCj0VfEZyOzh7KUvtGrEe_6m28eU0OPfmz-BTdOJInCsDY18vlSnsCG_8tlifmZH2Tcghs1n
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLZ4ScCBN2I8e0AcgI7FaZPmOAbTENvgMBC3qE1TmEAb2jp-P0nbVUNCSFz6kh1Fdho7if0Z4NS3mGWaoktRMNfjStlDwppriGmofR5RjLNiE7zbDV5exOMcXJa5MFrrLPhMV-1jdpYfD9XEbpVdCZtIScU8LPqehyTP1irnXZuEmYfTC-MzimCaIlMTV-3GQ6djFoNIqtQYyMDms82Yoayuyk8XcxY2NDM1zfX_dXID1gqX0qnnY2AT5vRgC1ZngAa34bw77I-1U4CpvrrXxnbFzo0emM_m3alP0qFFtIz1aAeemre9RsstqiS4inKeuiIkCWGR0mjuFANClPJCjDVLzJWGXGFCVBL5HiquI6MCFnOheGTYQ4yQ7sLCYDjQe-AkHFkU2aNBJrxA28WU4kkSE-H5yJmoAJkKTaoCQtxWsviQ2VKiJmQmaGkFLQtBV-Ci5PnMATT-pN62Ei0pC2FW4HCqG1n8Y2NpJhuCSBgnFTjL9VXyWdDsm_5zXRrVyPf0zbSPjLL935s_geVWr9OW7bvu_QGs2A7lYWSHsJCOJvoIltRX2h-PjrMR9w36atCu
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Noise+Learning-Based+Denoising+Autoencoder&rft.jtitle=IEEE+communications+letters&rft.au=Lee%2C+Woong-Hee&rft.au=Ozger%2C+Mustafa&rft.au=Challita%2C+Ursula&rft.au=Sung%2C+Ki+Won&rft.date=2021-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1089-7798&rft.eissn=1558-2558&rft.volume=25&rft.issue=9&rft.spage=2983&rft_id=info:doi/10.1109%2FLCOMM.2021.3091800&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-7798&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-7798&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-7798&client=summon