How Reduced Data Precision and Degree of Parallelism Impact the Reliability of Convolutional Neural Networks on FPGAs
Convolutional neural networks (CNNs) are becoming attractive alternatives to traditional image-processing algorithms in self-driving vehicles for automotive, military, and aerospace applications. The high computational demand of state-of-the-art CNN architectures requires the use of hardware acceler...
Saved in:
| Published in: | IEEE transactions on nuclear science Vol. 68; no. 5; pp. 865 - 872 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
New York
IEEE
01.05.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0018-9499, 1558-1578 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Convolutional neural networks (CNNs) are becoming attractive alternatives to traditional image-processing algorithms in self-driving vehicles for automotive, military, and aerospace applications. The high computational demand of state-of-the-art CNN architectures requires the use of hardware acceleration on parallel devices. Field-programmable gate arrays (FPGAs) offer a great level of design flexibility, low power consumption, and are relatively low cost, which make them very good candidates for efficiently accelerating neural networks. Unfortunately, the configuration memories of SRAM-based FPGAs are sensitive to radiation-induced errors, which can compromise the circuit implemented on the programmable fabric and the overall reliability of the system. Through neutron beam experiments, we evaluate how lossless quantization processes and subsequent data precision reduction impact the area, performance, radiation sensitivity, and failure rate of neural networks on FPGAs. Our results show that an 8-bit integer design can deliver over six times more fault-free executions than a 32-bit floating-point implementation. Moreover, we discuss the tradeoffs associated with varying degrees of parallelism in a neural network accelerator. We show that, although increased parallelism increases radiation sensitivity, the performance gains generally outweigh it in terms of global failure rate. |
|---|---|
| AbstractList | Convolutional neural networks (CNNs) are becoming attractive alternatives to traditional image-processing algorithms in self-driving vehicles for automotive, military, and aerospace applications. The high computational demand of state-of-the-art CNN architectures requires the use of hardware acceleration on parallel devices. Field-programmable gate arrays (FPGAs) offer a great level of design flexibility, low power consumption, and are relatively low cost, which make them very good candidates for efficiently accelerating neural networks. Unfortunately, the configuration memories of SRAM-based FPGAs are sensitive to radiation-induced errors, which can compromise the circuit implemented on the programmable fabric and the overall reliability of the system. Through neutron beam experiments, we evaluate how lossless quantization processes and subsequent data precision reduction impact the area, performance, radiation sensitivity, and failure rate of neural networks on FPGAs. Our results show that an 8-bit integer design can deliver over six times more fault-free executions than a 32-bit floating-point implementation. Moreover, we discuss the tradeoffs associated with varying degrees of parallelism in a neural network accelerator. We show that, although increased parallelism increases radiation sensitivity, the performance gains generally outweigh it in terms of global failure rate. |
| Author | Rech, P. Brunhaver, J. Leavitt, J. Neuman, B. Libano, F. Wirthlin, M. |
| Author_xml | – sequence: 1 givenname: F. orcidid: 0000-0002-0638-1102 surname: Libano fullname: Libano, F. email: flibano@asu.edu organization: School of Electrical, Computer and Energy Engineering (ECEE), Arizona State University (ASU), Tempe, AZ, USA – sequence: 2 givenname: P. orcidid: 0000-0002-0821-1879 surname: Rech fullname: Rech, P. email: prech@inf.ufrgs.br organization: Institute of Informatics, Federal University of Rio Grande do Sul (UFRGS), Porto Alegre, Brazil – sequence: 3 givenname: B. surname: Neuman fullname: Neuman, B. email: bneuman@lanl.gov organization: Los Alamos National Laboratory (LANL), Los Alamos, NM, USA – sequence: 4 givenname: J. surname: Leavitt fullname: Leavitt, J. email: jleavitt@byu.edu organization: Department of Electrical and Computer Engineering, Brigham Young University (BYU), Provo, UT, USA – sequence: 5 givenname: M. orcidid: 0000-0003-0328-6713 surname: Wirthlin fullname: Wirthlin, M. email: wirthlin@byu.edu organization: Department of Electrical and Computer Engineering, Brigham Young University (BYU), Provo, UT, USA – sequence: 6 givenname: J. surname: Brunhaver fullname: Brunhaver, J. email: jbrunhaver@asu.edu organization: School of Electrical, Computer and Energy Engineering (ECEE), Arizona State University (ASU), Tempe, AZ, USA |
| BookMark | eNp9kEtLxDAUhYMoOD72gpuA6455NE26lPEJooOPdUnTW41mmjFJFf-9GUdcuHB1uJfzHe49O2hz8AMgdEDJlFJSHz_c3E8ZYXTKiSCSyA00oUKoggqpNtGEEKqKuqzrbbQT40seS0HEBI2X_gPfQTca6PCpThrPAxgbrR-wHvIKngIA9j2e66CdA2fjAl8tltoknJ4hs87q1jqbPleumR_evRtT5rXDNzCGb0kfPrxGnEPP5xcncQ9t9dpF2P_RXfR4fvYwuyyuby-uZifXheFCpgK41JXuVMkqVrWCMCXaupdUVrzsKDWlYp0wRHZV26pKGt4KaHsGldbAe9LzXXS0zl0G_zZCTM2LH0O-LDZMMFWXOZlnV7V2meBjDNA3xia9eiEFbV1DSbOquMkVN6uKm5-KM0j-gMtgFzp8_occrhELAL_2mtOalop_AfvjiPw |
| CODEN | IETNAE |
| CitedBy_id | crossref_primary_10_1016_j_cosrev_2024_100682 crossref_primary_10_1109_MDAT_2023_3241116 crossref_primary_10_1109_TNS_2024_3377596 crossref_primary_10_1109_TNS_2024_3491503 crossref_primary_10_1016_j_microrel_2025_115859 crossref_primary_10_1145_3638242 crossref_primary_10_1109_TCASAI_2025_3552735 crossref_primary_10_1109_TNS_2023_3262448 crossref_primary_10_1109_TNS_2022_3224538 crossref_primary_10_1016_j_microrel_2024_115392 crossref_primary_10_1016_j_sysarc_2023_102872 crossref_primary_10_1016_j_microrel_2023_115092 crossref_primary_10_1109_TNS_2021_3131346 crossref_primary_10_3390_electronics13224461 crossref_primary_10_1109_TNS_2025_3595388 crossref_primary_10_1016_j_microrel_2023_114974 crossref_primary_10_1109_MDAT_2022_3174181 crossref_primary_10_1016_j_jpdc_2023_104746 crossref_primary_10_3390_electronics13050879 crossref_primary_10_1109_JETCAS_2024_3460792 crossref_primary_10_1109_TNS_2025_3585859 crossref_primary_10_1109_TDMR_2023_3235767 crossref_primary_10_1109_TVLSI_2021_3138491 crossref_primary_10_1109_TCSI_2023_3300899 crossref_primary_10_1049_ipr2_13206 crossref_primary_10_1109_TNS_2022_3176485 crossref_primary_10_1109_TVLSI_2024_3443834 |
| Cites_doi | 10.1109/SBCCI.2018.8533235 10.1109/DFT.2019.8875362 10.1109/ETS.2019.8791554 10.1109/TNS.2017.2784367 10.1145/3195970.3195997 10.1109/JPROC.2015.2404212 10.1109/FCCM.2019.00077 10.1109/ICComm.2012.6262539 10.1109/ISPASS.2015.7095801 10.1109/TNS.2018.2884460 10.1109/TDMR.2011.2168959 10.1109/DSN-W.2017.47 10.1109/5.726791 10.1109/JPROC.2006.887327 10.1109/INDUSCON.2016.7874605 10.1109/ACCESS.2018.2877890 10.1109/ISCID.2018.00029 10.1109/ISOCC47750.2019.9027715 10.1109/TNS.2015.2508981 10.1109/DSN.2014.49 10.1109/JSTARS.2019.2936771 10.1109/HPCA.2019.00041 10.1109/TNS.2020.2983662 10.1145/3079856.3080246 10.1109/TR.2018.2878387 10.1109/TMI.2016.2528162 |
| 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 RIA RIE AAYXX CITATION 7QF 7QL 7QQ 7SC 7SE 7SP 7SR 7T7 7TA 7TB 7U5 7U9 8BQ 8FD C1K F28 FR3 H8D H94 JG9 JQ2 KR7 L7M L~C L~D M7N P64 |
| DOI | 10.1109/TNS.2021.3050707 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Aluminium Industry Abstracts Bacteriology Abstracts (Microbiology B) Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts Virology and AIDS Abstracts METADEX Technology Research Database Environmental Sciences and Pollution Management ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database AIDS and Cancer Research Abstracts Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Algology Mycology and Protozoology Abstracts (Microbiology C) Biotechnology and BioEngineering Abstracts |
| DatabaseTitle | CrossRef Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Environmental Sciences and Pollution Management Aerospace Database Engineered Materials Abstracts Bacteriology Abstracts (Microbiology B) Algology Mycology and Protozoology Abstracts (Microbiology C) AIDS and Cancer Research Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Virology and AIDS Abstracts Electronics & Communications Abstracts Ceramic Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts |
| DatabaseTitleList | Materials Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-1578 |
| EndPage | 872 |
| ExternalDocumentID | 10_1109_TNS_2021_3050707 9319148 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: CAPES Foundation of the Ministry of Education – fundername: Department of Energy of the United States – fundername: CNPq Research Council of the Ministry of Science and Technology |
| GroupedDBID | .DC .GJ 0R~ 29I 3O- 4.4 53G 5GY 5RE 5VS 6IK 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ACPRK AENEX AETEA AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 VOH AAYXX CITATION 7QF 7QL 7QQ 7SC 7SE 7SP 7SR 7T7 7TA 7TB 7U5 7U9 8BQ 8FD C1K F28 FR3 H8D H94 JG9 JQ2 KR7 L7M L~C L~D M7N P64 |
| ID | FETCH-LOGICAL-c357t-e37a6ad842626b50285b9f717634d11c482d5c07d6bb867c3b5ebf2e6aae3f0f3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 37 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000655537500052&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0018-9499 |
| IngestDate | Mon Jun 30 10:11:33 EDT 2025 Sat Nov 29 05:53:25 EST 2025 Tue Nov 18 22:33:35 EST 2025 Wed Aug 27 02:30:25 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c357t-e37a6ad842626b50285b9f717634d11c482d5c07d6bb867c3b5ebf2e6aae3f0f3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-0328-6713 0000-0002-0821-1879 0000-0002-0638-1102 |
| PQID | 2528944263 |
| PQPubID | 85457 |
| PageCount | 8 |
| ParticipantIDs | proquest_journals_2528944263 crossref_primary_10_1109_TNS_2021_3050707 crossref_citationtrail_10_1109_TNS_2021_3050707 ieee_primary_9319148 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-05-01 |
| PublicationDateYYYYMMDD | 2021-05-01 |
| PublicationDate_xml | – month: 05 year: 2021 text: 2021-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on nuclear science |
| PublicationTitleAbbrev | TNS |
| 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 | ref13 ref12 (ref4) 2020 (ref38) 2020 ref15 ref36 ref14 ref31 ref30 ref11 ref32 ref10 (ref2) 2020 ref39 ref16 (ref41) 2020 (ref35) 2020 ref19 ref18 (ref7) 2020 (ref34) 2020 (ref37) 2020 (ref27) 2020 (ref17) 2020 ref24 ref23 ref26 (ref29) 2020 ref25 ref20 ref42 ref22 ref21 (ref3) 2020 ref8 ref9 (ref1) 2020 hubara (ref28) 2017; 18 (ref6) 2020 ref5 ref40 (ref33) 2020 |
| References_xml | – year: 2020 ident: ref17 publication-title: 7 Series FPGA Configuration User Guide – ident: ref22 doi: 10.1109/SBCCI.2018.8533235 – ident: ref31 doi: 10.1109/DFT.2019.8875362 – ident: ref24 doi: 10.1109/ETS.2019.8791554 – ident: ref21 doi: 10.1109/TNS.2017.2784367 – ident: ref18 doi: 10.1145/3195970.3195997 – ident: ref16 doi: 10.1109/JPROC.2015.2404212 – ident: ref14 doi: 10.1109/FCCM.2019.00077 – year: 2020 ident: ref33 publication-title: Zynq-7000 SoC – ident: ref9 doi: 10.1109/ICComm.2012.6262539 – ident: ref12 doi: 10.1109/ISPASS.2015.7095801 – ident: ref30 doi: 10.1109/TNS.2018.2884460 – ident: ref39 doi: 10.1109/TDMR.2011.2168959 – ident: ref19 doi: 10.1109/DSN-W.2017.47 – year: 2020 ident: ref6 publication-title: Mars 2020 Mission Perseverance Rover – year: 2020 ident: ref38 publication-title: Device Reliability Report – year: 2020 ident: ref4 publication-title: Autopilot – ident: ref32 doi: 10.1109/5.726791 – year: 2020 ident: ref41 publication-title: Zynq DPU – year: 2020 ident: ref37 publication-title: ISO 26262 – year: 2020 ident: ref35 publication-title: JEDEC Standard JESD89 – ident: ref5 doi: 10.1109/JPROC.2006.887327 – ident: ref15 doi: 10.1109/INDUSCON.2016.7874605 – ident: ref26 doi: 10.1109/ACCESS.2018.2877890 – year: 2020 ident: ref34 publication-title: Zynq ultrascale+ mpsoc – ident: ref10 doi: 10.1109/ISCID.2018.00029 – ident: ref13 doi: 10.1109/ISOCC47750.2019.9027715 – year: 2020 ident: ref7 publication-title: Mars Helicopter – year: 2020 ident: ref2 publication-title: Mercedes-Benz Innovation Autonomous – ident: ref40 doi: 10.1109/TNS.2015.2508981 – ident: ref36 doi: 10.1109/DSN.2014.49 – volume: 18 start-page: 6898 year: 2017 ident: ref28 article-title: Quantized neural networks: Training neural networks with low precision weights and activations publication-title: J Mach Learn Res – year: 2020 ident: ref27 publication-title: Tensorflow Model Optimization Toolkit-Post-training integer quantization – ident: ref11 doi: 10.1109/JSTARS.2019.2936771 – ident: ref23 doi: 10.1109/HPCA.2019.00041 – ident: ref25 doi: 10.1109/TNS.2020.2983662 – ident: ref42 doi: 10.1145/3079856.3080246 – ident: ref20 doi: 10.1109/TR.2018.2878387 – ident: ref8 doi: 10.1109/TMI.2016.2528162 – year: 2020 ident: ref1 publication-title: Automotive Revolution-Perspective Towards 2030 – year: 2020 ident: ref3 publication-title: Autonomous Driving|Intellisafe – year: 2020 ident: ref29 publication-title: TensorFlow Lite |
| SSID | ssj0014505 |
| Score | 2.4869149 |
| Snippet | Convolutional neural networks (CNNs) are becoming attractive alternatives to traditional image-processing algorithms in self-driving vehicles for automotive,... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 865 |
| SubjectTerms | Algorithms Artificial neural networks Autonomous cars Biological neural networks Computer applications Data reduction Failure rates Field programmable gate arrays Field-programmable gate array (FPGA) Floating point arithmetic Image processing Military applications Network reliability Neural networks Neutron beams Parallel processing parallelism Power consumption Quantization (signal) Radiation Radiation effects reduced precision Reliability Reliability analysis Resource management Sensitivity |
| Title | How Reduced Data Precision and Degree of Parallelism Impact the Reliability of Convolutional Neural Networks on FPGAs |
| URI | https://ieeexplore.ieee.org/document/9319148 https://www.proquest.com/docview/2528944263 |
| Volume | 68 |
| WOSCitedRecordID | wos000655537500052&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 Xplore customDbUrl: eissn: 1558-1578 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014505 issn: 0018-9499 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9swED7asoftod3WjaXthh72Mqgbx7It-zGkzToYIWzt6JvRjzMUOrvESUv_-97JSmjZGAwMNkaShT_JurPuvg_gs4pLnehSRnUtZcSpkJFRzkQyQTKXVZ1rrxn567uazYqrq3K-BcebXBhE9MFneMKXfi_ftXbFv8qGpWQ2smIbtpXK-1ytzY5BmsVBrYAmMJnx6y3JuBxezH6SI5iMTmhsM7vNsyXIa6r88SH2q8t07__69Rp2gxUpxj3sb2ALm7fw6gm34D6sztt78YOJWdGJU73UYr4IejpCN3QLydNG0dZirhcsqHJz3f0W33zSpCCrUHCwck_i_cClJm1zF4YpPZk5PfzJB5F3ghqdzr-Ou3dwOT27mJxHQWMhsjJTywil0rl2BRPT5yYjayMzZU0-Xi5TNxrZtEhcZmPlcmOKXFlpMjQ1Aak1yjqu5XvYadoGP4BIC2sNkn1HR8qOXCxRFS6RyMpEqRvAcP3aKxsIyFkH46byjkhcVgRUxUBVAagBfNnUuO3JN_5Rdp-B2ZQLmAzgaI1sFWZnVyUZ9S5lqvqDv9c6hJfcdh_YeAQ7y8UKP8ILe7e87haf_MB7BHxK1Ls |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9swED7abtDuofvRlabtNj3sZTA3jiVb9mNpm6UsC2FLR9-Mfpyh0NklTjr2308nK2GlYzAw2BjJEv4k6866-z6A9zIuVKIKHlUV5xGlQkZaWh3xBJ25LKtMec3I72M5meTX18V0Az6uc2EQ0Qef4Qld-r1825gl_SrrF5zYyPJNeJIKkcRdttZ6z0CkcdArcFPYGfKrTcm46M8m35wrmAxO3OgmfpsHi5BXVXn0Kfbry_D5__XsBewGO5KddsC_hA2sX8GzP9gF92A5an6yr0TNipadq4Vi03lQ1GGqdrfQ-drImopN1ZwkVW5v2h_s0qdNMmcXMgpX7mi8f1Gps6a-DwPVtUysHv7kw8hb5h46nH46bV_D1fBidjaKgspCZHgqFxFyqTJlc6Kmz3Tq7I1UF5Xz8jIu7GBgRJ7Y1MTSZlrnmTRcp6grB6VSyKu44vuwVTc1HgATuTEanYXnDkGuXMxR5jbhSNpEwvagv3rtpQkU5KSEcVt6VyQuSgdUSUCVAagefFjXuOvoN_5Rdo-AWZcLmPTgeIVsGeZnWyap650gsvrDv9d6B9uj2ZdxOb6cfD6CHWqnC3M8hq3FfIlv4Km5X9y087d-EP4GtWDYAg |
| 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=How+Reduced+Data+Precision+and+Degree+of+Parallelism+Impact+the+Reliability+of+Convolutional+Neural+Networks+on+FPGAs&rft.jtitle=IEEE+transactions+on+nuclear+science&rft.au=Libano%2C+F.&rft.au=Rech%2C+P.&rft.au=Neuman%2C+B.&rft.au=Leavitt%2C+J.&rft.date=2021-05-01&rft.pub=IEEE&rft.issn=0018-9499&rft.volume=68&rft.issue=5&rft.spage=865&rft.epage=872&rft_id=info:doi/10.1109%2FTNS.2021.3050707&rft.externalDocID=9319148 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9499&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9499&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9499&client=summon |