Robust DoA Estimation Using Denoising Autoencoder and Deep Neural Networks

As one of the most critical technology in array signal processing, direction of arrival (DoA) estimation has received a great deal of attention in many areas. Traditional methods perform well when the signal-to-noise ratio (SNR) is high and the receiving array is perfect, which are quite different f...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 10; s. 52551 - 52564
Hlavní autori:	Chen, Dawei, Shi, Shuo, Gu, Xuemai, Shim, Byonghyo
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Array signal processing Arrays Artificial neural networks Covariance matrices deep neural networks denoising autoencoder Direction of arrival Direction-of-arrival estimation DoA Estimation Feature extraction Machine learning Mutual coupling Neural networks Noise reduction Robustness Signal processing Signal to noise ratio SNR
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	As one of the most critical technology in array signal processing, direction of arrival (DoA) estimation has received a great deal of attention in many areas. Traditional methods perform well when the signal-to-noise ratio (SNR) is high and the receiving array is perfect, which are quite different from the situation in some real applications (e.g., the marine communication scenario). To get satisfying performance of DoA estimation when SNR is low and the array is inaccurate (mutual coupling exist), this paper introduces a scheme consisting of denoising autoencoder (DAE) and deep neural networks (DNN), referred to as DAE-DNN scheme. DAE is used to reconstruct a clean "repaired" input from its corrupted version to increase the robustness, and then divide the input into multiple parts in different sub-areas. DNN is used to learn the mapping between the received signals and the refined grids of angle in each sub-areas, then the outputs of each sub-areas are concatenated to perform the final DoA estimation. By simulations in different SNR regimes, we study the performance of DAE-DNN in terms of the different snapshots, batch size, learning rate, and epoch. Our results demonstrate that the proposed DAE-DNN scheme outperforms traditional methods in accuracy and robustness.
AbstractList	As one of the most critical technology in array signal processing, direction of arrival (DoA) estimation has received a great deal of attention in many areas. Traditional methods perform well when the signal-to-noise ratio (SNR) is high and the receiving array is perfect, which are quite different from the situation in some real applications (e.g., the marine communication scenario). To get satisfying performance of DoA estimation when SNR is low and the array is inaccurate (mutual coupling exist), this paper introduces a scheme consisting of denoising autoencoder (DAE) and deep neural networks (DNN), referred to as DAE-DNN scheme. DAE is used to reconstruct a clean "repaired" input from its corrupted version to increase the robustness, and then divide the input into multiple parts in different sub-areas. DNN is used to learn the mapping between the received signals and the refined grids of angle in each sub-areas, then the outputs of each sub-areas are concatenated to perform the final DoA estimation. By simulations in different SNR regimes, we study the performance of DAE-DNN in terms of the different snapshots, batch size, learning rate, and epoch. Our results demonstrate that the proposed DAE-DNN scheme outperforms traditional methods in accuracy and robustness.
Author	Gu, Xuemai Chen, Dawei Shi, Shuo Shim, Byonghyo
Author_xml	– sequence: 1 givenname: Dawei orcidid: 0000-0002-4950-9153 surname: Chen fullname: Chen, Dawei organization: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China – sequence: 2 givenname: Shuo orcidid: 0000-0002-5671-266X surname: Shi fullname: Shi, Shuo organization: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China – sequence: 3 givenname: Xuemai orcidid: 0000-0002-6011-9885 surname: Gu fullname: Gu, Xuemai email: guxuemai@hit.edu.cn organization: School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China – sequence: 4 givenname: Byonghyo orcidid: 0000-0001-5051-1763 surname: Shim fullname: Shim, Byonghyo organization: School of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea
BookMark	eNqFUU1LxDAQDaLg5y_wUvC8a9I0aXJc1vULUfDjHKbpVLKuzZqkiP_euBURL85lhpl57w3z9sl273sk5JjRKWNUn87m88XDw7SkZTnlTFZK11tkr2RST7jgcvtXvUuOYlzSHCq3RL1Hru99M8RUnPlZsYjJvUJyvi-eouufizPsvdtUsyF57K1vMRTQt3mC6-IWhwCrnNK7Dy_xkOx0sIp49J0PyNP54nF-Obm5u7iaz24mtqIqTRQw3emOW1BN0ylLOyERsaKtEFJLACqhYqJGqmvQNQfNuZUKQdZWCYH8gFyNvK2HpVmHfHP4MB6c2TR8eDYQkrMrNCBEq7iC1rKuUhQalKxjtFWNaoTSVeY6GbnWwb8NGJNZ-iH0-XxTSqmZ0JzpvMXHLRt8jAG7H1VGzZcHZvTAfHlgvj3IKP0HZV3avDcFcKt_sMcj1uXX_KjputJlLfknCtOV3Q
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_LWC_2025_3572346 crossref_primary_10_1109_ACCESS_2025_3547146 crossref_primary_10_1109_ACCESS_2022_3172478 crossref_primary_10_1109_ACCESS_2023_3309643 crossref_primary_10_3390_app15031123 crossref_primary_10_1016_j_aeue_2024_155132 crossref_primary_10_1109_ACCESS_2024_3477920 crossref_primary_10_1109_TVT_2024_3496119 crossref_primary_10_1109_ACCESS_2025_3550949 crossref_primary_10_3390_s24010091
Cites_doi	10.1109/TWC.2013.012513.120966 10.1109/PROC.1969.7278 10.1109/TMECH.2017.2759301 10.1016/j.sigpro.2011.08.017 10.1109/TCOMM.2020.2969184 10.1109/TVT.2019.2919737 10.1049/iet-rsn.2016.0446 10.1109/29.32276 10.1109/TBME.2016.2613960 10.1002/0471221104 10.1109/ACCESS.2019.2914731 10.1109/COMST.2019.2926625 10.1109/LCOMM.2018.2884457 10.1109/TAP.2018.2874430 10.1109/TAES.2012.6129676 10.1109/78.469863 10.1109/TSP.2009.2037074 10.1109/TASLP.2017.2738559 10.1109/COMST.2017.2664421 10.1109/TIM.2018.2868490 10.1109/JSAC.2019.2904352 10.1109/MCOM.001.1900664 10.1109/8.855496 10.1109/5.622504 10.1109/TWC.2019.2919280 10.1109/LSP.2012.2204435 10.1109/JIOT.2018.2876695 10.1109/LCOMM.2020.3029197 10.1145/1390156.1390294 10.1109/TAP.1986.1143830 10.1109/TVT.2018.2851783 10.1109/MCOM.2019.1800610 10.1109/ICC.2012.6363665 10.1016/j.sigpro.2012.06.013 10.26599/TST.2018.9010002
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2022.3164897
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 Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	52564
ExternalDocumentID	oai_doaj_org_article_a55d838adc1f480abe61f10d8b8b5894 10_1109_ACCESS_2022_3164897 9749276
Genre	orig-research
GrantInformation_xml	– fundername: Korean Government through the Ministry of Science, ICT and Future Planning (MSIP) grantid: 2020R1A2C2102198 funderid: 10.13039/501100003621 – fundername: Ministry of Science and ICT (MSIT) through the Information Technology Research Center (ITRC) Program supervised by the Institute for Information & Communications Technology Promotion (IITP) grantid: IITP-2019-2017-0-01637 – fundername: National Research Foundation (NRF) funderid: 10.13039/501100003725 – fundername: National Natural Science Foundation of China grantid: 62171158 funderid: 10.13039/501100001809
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c408t-8a19f9f3ca8bbf8c0f56eee40d55696aa06a4157e097a973a933c68ea67c855e3
IEDL.DBID	RIE
ISICitedReferencesCount	17
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000802070200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:43:04 EDT 2025 Mon Jun 30 04:20:31 EDT 2025 Sat Nov 29 06:32:01 EST 2025 Tue Nov 18 22:32:58 EST 2025 Wed Aug 27 02:36:19 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c408t-8a19f9f3ca8bbf8c0f56eee40d55696aa06a4157e097a973a933c68ea67c855e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-5051-1763 0000-0002-5671-266X 0000-0002-6011-9885 0000-0002-4950-9153
OpenAccessLink	https://ieeexplore.ieee.org/document/9749276
PQID	2669159319
PQPubID	4845423
PageCount	14
ParticipantIDs	proquest_journals_2669159319 doaj_primary_oai_doaj_org_article_a55d838adc1f480abe61f10d8b8b5894 ieee_primary_9749276 crossref_primary_10_1109_ACCESS_2022_3164897 crossref_citationtrail_10_1109_ACCESS_2022_3164897
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101 2022-01-01
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2022
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	ref13 ref12 ref34 ref15 ref37 ref14 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 Vincent (ref35) 2010; 11 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 Abadi (ref36) 2016
References_xml	– ident: ref5 doi: 10.1109/TWC.2013.012513.120966 – ident: ref8 doi: 10.1109/PROC.1969.7278 – ident: ref21 doi: 10.1109/TMECH.2017.2759301 – ident: ref13 doi: 10.1016/j.sigpro.2011.08.017 – volume: 11 start-page: 3371 year: 2010 ident: ref35 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – ident: ref32 doi: 10.1109/TCOMM.2020.2969184 – ident: ref6 doi: 10.1109/TVT.2019.2919737 – ident: ref4 doi: 10.1049/iet-rsn.2016.0446 – volume-title: arXiv:1603.04467 year: 2016 ident: ref36 article-title: TensorFlow: Large-scale machine learning on heterogeneous distributed systems – ident: ref10 doi: 10.1109/29.32276 – ident: ref25 doi: 10.1109/TBME.2016.2613960 – ident: ref11 doi: 10.1002/0471221104 – ident: ref22 doi: 10.1109/ACCESS.2019.2914731 – ident: ref28 doi: 10.1109/COMST.2019.2926625 – ident: ref16 doi: 10.1109/LCOMM.2018.2884457 – ident: ref34 doi: 10.1109/TAP.2018.2874430 – ident: ref37 doi: 10.1109/TAES.2012.6129676 – ident: ref7 doi: 10.1109/78.469863 – ident: ref15 doi: 10.1109/TSP.2009.2037074 – ident: ref18 doi: 10.1109/TASLP.2017.2738559 – ident: ref2 doi: 10.1109/COMST.2017.2664421 – ident: ref23 doi: 10.1109/TIM.2018.2868490 – ident: ref31 doi: 10.1109/JSAC.2019.2904352 – ident: ref27 doi: 10.1109/MCOM.001.1900664 – ident: ref26 doi: 10.1109/8.855496 – ident: ref1 doi: 10.1109/5.622504 – ident: ref3 doi: 10.1109/TWC.2019.2919280 – ident: ref12 doi: 10.1109/LSP.2012.2204435 – ident: ref24 doi: 10.1109/JIOT.2018.2876695 – ident: ref17 doi: 10.1109/LCOMM.2020.3029197 – ident: ref19 doi: 10.1145/1390156.1390294 – ident: ref9 doi: 10.1109/TAP.1986.1143830 – ident: ref30 doi: 10.1109/TVT.2018.2851783 – ident: ref29 doi: 10.1109/MCOM.2019.1800610 – ident: ref33 doi: 10.1109/ICC.2012.6363665 – ident: ref14 doi: 10.1016/j.sigpro.2012.06.013 – ident: ref20 doi: 10.26599/TST.2018.9010002
SSID	ssj0000816957
Score	2.391354
Snippet	As one of the most critical technology in array signal processing, direction of arrival (DoA) estimation has received a great deal of attention in many areas....
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	52551
SubjectTerms	Array signal processing Arrays Artificial neural networks Covariance matrices deep neural networks denoising autoencoder Direction of arrival Direction-of-arrival estimation DoA Estimation Feature extraction Machine learning Mutual coupling Neural networks Noise reduction Robustness Signal processing Signal to noise ratio SNR
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHvQg6iquL3rwaDF9JJkc11URkUVExVtI8wBBWtnt-vudpN1lQdCLt9KmafLNJDMTpt8Qcp45aiDzNgVburQUWqQ65LraMhdecJ77SDz_-iAmE3h7k48rpb5CTlhHD9wBd6kZs1CAtibzJVBdOZ75jFqooGIgIxMoej0rwVTcgyHjkomeZiij8nI0HuOMMCDMc4xTeQmB5mnFFEXG_r7Eyo99ORqb2x2y3XuJyagb3S5Zc_Ue2VrhDhyQ-6emms_a5LoZJTe4TrtfEJOYApBcu7p5j1ejedsErkrrpomuLT5xn0lg5MDuJ10K-GyfvNzePI_v0r4wQmpKCm0KOpNe-sJoqCoPhnrGcdgltYxxybWmXKNhFo5KoaUotCwKw8FpLgww5ooDsl43tTskiQaHaDjGAe20oJUuaCVM6VCEknkqhiRfYKRMzxoeild8qBg9UKk6YFUAVvXADsnF8qXPjjTj9-ZXAfxl08B4HW-gHqheD9RfejAkgyC6ZScYJ8lc8CE5WYhS9atzptApkejG4e5z9B-fPiabYTrdwcwJWW-nc3dKNsxX-z6bnkXF_AZj3OPI priority: 102 providerName: Directory of Open Access Journals
Title	Robust DoA Estimation Using Denoising Autoencoder and Deep Neural Networks
URI	https://ieeexplore.ieee.org/document/9749276 https://www.proquest.com/docview/2669159319 https://doaj.org/article/a55d838adc1f480abe61f10d8b8b5894
Volume	10
WOSCitedRecordID	wos000802070200001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FQc48CqIhVLlwLGhTuLH-Lhst0IIVggB6i1y7LFUCSXVbpYjvx3bcaNKICQukZXY1sRf7Jlxxt8AvKmIWay8K9FxKrkyqjQx1tXxWnklZe0T8fz3j2qzwasr_fkAzuazMESUgs_obSymf_lusPu4VXYebF9dK3kIh0qp6azWvJ8SE0hooTKxUMX0-XK1Cu8QXMC6Dp6p5BiJne4on8TRn5Oq_LESJ_Vy-ej_BHsMD7MZWSwn3J_AAfVP4cEdcsFj-PBl6Pa7sbgYlsU6TOTpjGKRYgSKC-qH61Ra7schklk62hamd-EJ3RSRsiN0v5lixHfP4Nvl-uvqfZkzJ5SWMxxLNJX22jfWYNd5tMwLGYTmzAkhtTSGSRM0tyKmldGqMbpprEQyUlkUgprncNQPPb2AwiCFwSMhMShyxTrTsE5ZTgFjLTxTC6hvh7S1mVY8Zrf40Sb3gul2wqGNOLQZhwWczY1uJlaNf1d_F7Gaq0ZK7HQjgNDmGdYaIRw2aJytPEdmOpKVr5jDDjuBmi_gOAI3d5IxW8DJLfJtnr67NlgtOth5YXl6-fdWr-B-FHDaizmBo3G7p9dwz_4cr3fb0-TYh-unX-vT9JX-BsLT4rE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQceLWIhQI5cGyok_h5XLatCiwrhArqzXLssVQJJdVutr-_tuNGlUBI3KzEtmx_Gc_YmfkG4EOFxMrKu1I6iiUVRpQm-ro6WgsvOK99Ip7_tRSrlby4UN934HCKhUHE5HyGH2Mx_ct3vd3Gq7KjYPuqWvB7cJ9RWldjtNZ0oxJTSCgmMrVQRdTRfLEIswiHwLoOZ1NOZaR2uqN-Ekt_Tqvyx16cFMzp0_8b2jN4kg3JYj4i_xx2sHsBj-_QC-7Blx99u90MxXE_L06CKI9RikXyEiiOsesvU2m-HfpIZ-lwXZjOhTd4VUTSjtD9avQS3-zDz9OT88VZmXMnlJYSOZTSVMor31gj29ZLSzzjYdCUOMa44sYQboLuFkiUMEo0RjWN5RINF1Yyhs1L2O36Dl9BYSSGxUPGZVDlgrSmIa2wFAPKinkiZlDfLqm2mVg85rf4rdMBgyg94qAjDjrjMIPDqdHVyKvx7-qfIlZT1UiKnR4EEHSWMW0Yc7KRxtnKU0lMi7zyFXGylS2Tis5gLwI3dZIxm8HBLfI6C_BGB7tFBUsvbFCv_97qPTw8O_-21MvPq69v4FEc7HgzcwC7w3qLb-GBvR4uN-t36Su9AQNa49I
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=Robust+DoA+Estimation+Using+Denoising+Autoencoder+and+Deep+Neural+Networks&rft.jtitle=IEEE+access&rft.au=Chen%2C+Dawei&rft.au=Shi%2C+Shuo&rft.au=Gu%2C+Xuemai&rft.au=Shim%2C+Byonghyo&rft.date=2022&rft.pub=IEEE&rft.eissn=2169-3536&rft.volume=10&rft.spage=52551&rft.epage=52564&rft_id=info:doi/10.1109%2FACCESS.2022.3164897&rft.externalDocID=9749276
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon