A Comparative Study of Class Rebalancing Methods for Security Bug Report Classification

Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product's security risk. However, the class imbalance problem exists for SBR prediction since the number of SBRs is often limited, and this issue has not been thoroughly investigated in previous studi...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on reliability Vol. 70; no. 4; pp. 1658 - 1670
Main Authors:	Zheng, Wei, Xun, Yuxing, Wu, Xiaoxue, Deng, Zhi, Chen, Xiang, Sui, Yulei
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.12.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Class imbalance problem class rebalancing methods Classification classification algorithms Comparative studies Computer bugs Debugging Dimensionality reduction Empirical analysis Impact analysis Performance enhancement Prediction algorithms Predictive models Security security bug report (SBRs) classification Software algorithms State-of-the-art reviews
ISSN:	0018-9529, 1558-1721
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product's security risk. However, the class imbalance problem exists for SBR prediction since the number of SBRs is often limited, and this issue has not been thoroughly investigated in previous studies. In our study, we choose six real-world projects of different sizes with over 120 000 bug reports in total as our empirical subjects. We first analyze the impact of the class imbalance issue on SBR prediction and confirm its negative impact on prediction performance. Then we perform a comparative study of six state-of-the-art class rebalancing methods combined with five popular classification algorithms for SBR prediction. By comparing with the baseline method Farsec, using the class rebalancing methods can improve the performance in 78% of cases in the worst case. Moreover, the combination of the Rose and random forest classification algorithm can construct the model with the best performance, which increases the performance by 267% in the best case and 75% on average in terms of F1-score . Finally, we summarize eight main findings based on our empirical studies' results, which can provide guidelines for choosing appropriate class rebalancing methods and classifiers for SBR prediction in practice.
AbstractList	Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product’s security risk. However, the class imbalance problem exists for SBR prediction since the number of SBRs is often limited, and this issue has not been thoroughly investigated in previous studies. In our study, we choose six real-world projects of different sizes with over 120 000 bug reports in total as our empirical subjects. We first analyze the impact of the class imbalance issue on SBR prediction and confirm its negative impact on prediction performance. Then we perform a comparative study of six state-of-the-art class rebalancing methods combined with five popular classification algorithms for SBR prediction. By comparing with the baseline method Farsec, using the class rebalancing methods can improve the performance in 78% of cases in the worst case. Moreover, the combination of the Rose and random forest classification algorithm can construct the model with the best performance, which increases the performance by 267% in the best case and 75% on average in terms of F1-score . Finally, we summarize eight main findings based on our empirical studies’ results, which can provide guidelines for choosing appropriate class rebalancing methods and classifiers for SBR prediction in practice.
Author	Wu, Xiaoxue Xun, Yuxing Zheng, Wei Sui, Yulei Deng, Zhi Chen, Xiang
Author_xml	– sequence: 1 givenname: Wei orcidid: 0000-0001-7969-1630 surname: Zheng fullname: Zheng, Wei email: wzheng@nwpu.edu.cn organization: National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, MIIT Key Laboratory of Big Data Storage and Management, Northwestern Polytechnical University, Xi'an, China – sequence: 2 givenname: Yuxing orcidid: 0000-0002-3409-934X surname: Xun fullname: Xun, Yuxing email: xingyu666@mail.nwpu.edu.cn organization: School of Software, Northwestern Polytechnical University, Xi'an, China – sequence: 3 givenname: Xiaoxue orcidid: 0000-0002-7567-3643 surname: Wu fullname: Wu, Xiaoxue email: wuxiaoxue00@gmail.com organization: College of Information Engineering (College of Artificial Intelligence), Yangzhou University, Yangzhou, China – sequence: 4 givenname: Zhi surname: Deng fullname: Deng, Zhi email: dengcai@mail.nwpu.edu.cn organization: School of Computer Science and Technology, Northwestern Polytechnical University, Xi'an, China – sequence: 5 givenname: Xiang orcidid: 0000-0002-1180-3891 surname: Chen fullname: Chen, Xiang email: xchencs@ntu.edu.cn organization: School of Information Science and Technology, Nantong University, Nantong, China – sequence: 6 givenname: Yulei surname: Sui fullname: Sui, Yulei email: yulei.sui@uts.edu.au organization: School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia
BookMark	eNp9kM9LwzAcxYMouE3PHrwEPHfLz7Y5zuEvmAjbxGPJ0mRmdE1NUmH_vd06PHjw9OXB-7zH9w3Bee1qDcANRmOMkZisFmOCCB5TjHNE0jMwwJznCc4IPgcDhHCeCE7EJRiGsO0kYyIfgI8pnLldI72M9lvDZWzLPXQGzioZAlzotaxkrWy9ga86froyQOM8XGrVehv38L7ddKbG-dgT1ljVJbn6ClwYWQV9fboj8P74sJo9J_O3p5fZdJ4oynlMsGayzDQTJKWcEblWnFKVaslMRkotaS4kkyrTeWZ4TpFYC8EwMQZxiTg2dATu-tzGu69Wh1hsXevrrrIgKTrmEty5Jr1LeReC16ZovN1Jvy8wKg7rFatFcVivOK3XEfwPoWw8fha9tNU_3G3PWa31b4vgOUeE0B_SLn1V
CODEN	IERQAD
CitedBy_id	crossref_primary_10_1155_2022_1499736 crossref_primary_10_1016_j_asoc_2022_109869 crossref_primary_10_1080_00207721_2022_2153635 crossref_primary_10_1016_j_suscom_2022_100812 crossref_primary_10_1002_smr_2758 crossref_primary_10_1155_2022_7419736 crossref_primary_10_1371_journal_pone_0282514 crossref_primary_10_1155_2022_9620555 crossref_primary_10_1080_17455030_2022_2076176 crossref_primary_10_3390_math12142201 crossref_primary_10_1016_j_knosys_2022_108293 crossref_primary_10_1155_2022_8217774 crossref_primary_10_3390_sym15020296 crossref_primary_10_1017_jmo_2022_62 crossref_primary_10_3389_fncom_2022_981739 crossref_primary_10_1016_j_knosys_2023_111258 crossref_primary_10_1002_ett_4632 crossref_primary_10_1093_jcde_qwac075 crossref_primary_10_1093_jcde_qwad002 crossref_primary_10_1093_jcde_qwac111 crossref_primary_10_1111_risa_14179 crossref_primary_10_1109_ACCESS_2024_3451125 crossref_primary_10_1007_s00500_023_09571_1 crossref_primary_10_3390_app122312179 crossref_primary_10_1016_j_infsof_2025_107778 crossref_primary_10_32604_cmc_2022_031583 crossref_primary_10_3390_mi14122204 crossref_primary_10_1109_JIOT_2023_3237661 crossref_primary_10_4018_JOEUC_306270 crossref_primary_10_1155_2022_5121762 crossref_primary_10_3390_electronics11172773 crossref_primary_10_3390_math11153278 crossref_primary_10_1177_03611981231223750 crossref_primary_10_1016_j_compbiomed_2022_106501 crossref_primary_10_3389_fncom_2022_998096 crossref_primary_10_1016_j_ijleo_2022_169431 crossref_primary_10_1109_TR_2023_3234982 crossref_primary_10_1007_s11042_022_13116_3 crossref_primary_10_3390_e24121783 crossref_primary_10_1155_2022_8481452 crossref_primary_10_1002_widm_1520 crossref_primary_10_1016_j_ijleo_2022_169251 crossref_primary_10_1155_2022_9865549 crossref_primary_10_1017_jmo_2022_74 crossref_primary_10_1016_j_infsof_2025_107685 crossref_primary_10_1109_TR_2024_3492380 crossref_primary_10_3390_pr10061214 crossref_primary_10_1109_TSE_2024_3513413
Cites_doi	10.1016/j.jss.2019.110456 10.1109/ICST.2013.24 10.1007/BF02834632 10.1007/s10796-020-10031-6 10.1145/3180155.3180197 10.1007/s10664-021-10010-8 10.1109/TSE.2017.2787653 10.1007/s11390-017-1713-3 10.1109/QRS.2018.00047 10.1023/A:1010933404324 10.1109/ICSE.2015.139 10.1016/j.patcog.2019.02.023 10.1093/oso/9780198538493.001.0001 10.1109/TSE.2018.2864217 10.22266/ijies2019.0430.11 10.1016/j.knosys.2019.06.022 10.1109/TSE.2016.2584050 10.1002/smr.2376 10.1109/TSE.2018.2876537 10.32614/RJ-2014-008 10.1016/j.cose.2021.102248 10.1145/3324916 10.1001/jama.2016.7653 10.1016/j.ins.2019.11.004 10.1007/BF00994018 10.1007/s11469-010-9275-4 10.1109/TSE.2019.2937083 10.1142/S0218194018500237 10.1016/j.infsof.2020.106314 10.1109/TSE.2017.2731766 10.1186/s12864-019-6413-7 10.1016/j.jss.2019.02.025 10.1016/j.inffus.2019.07.006 10.1109/TSE.2021.3063727 10.1007/11538059_91 10.1109/TSE.2018.2791521 10.1016/j.infsof.2017.08.004 10.1016/j.ins.2018.10.029 10.1109/MSR.2010.5463340 10.1109/MSR.2015.78 10.1109/HSI.2012.22 10.1038/nbt1206-1565 10.1515/jisys-2018-0476
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 7SP 8FD L7M
DOI	10.1109/TR.2021.3118026
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-1721
EndPage	1670
ExternalDocumentID	10_1109_TR_2021_3118026 9585022
Genre	orig-research
GrantInformation_xml	– fundername: 2021 Key R&D Program in Shaanxi Province grantid: 2021GY-041
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ OCL P2P RIA RIE RNS TN5 VH1 VJK AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c355t-1e4ad7e49263542abc533c6ea4f72dea389a4ac7e87f58309b99412ff05a051f3
IEDL.DBID	RIE
ISICitedReferencesCount	74
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000724479600028&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9529
IngestDate	Mon Jun 30 05:04:59 EDT 2025 Sat Nov 29 01:54:36 EST 2025 Tue Nov 18 22:10:11 EST 2025 Wed Aug 27 05:09:02 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c355t-1e4ad7e49263542abc533c6ea4f72dea389a4ac7e87f58309b99412ff05a051f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-7969-1630 0000-0002-7567-3643 0000-0002-1180-3891 0000-0002-3409-934X
PQID	2604926321
PQPubID	85456
PageCount	13
ParticipantIDs	crossref_primary_10_1109_TR_2021_3118026 ieee_primary_9585022 crossref_citationtrail_10_1109_TR_2021_3118026 proquest_journals_2604926321
PublicationCentury	2000
PublicationDate	2021-Dec. 2021-12-00 20211201
PublicationDateYYYYMMDD	2021-12-01
PublicationDate_xml	– month: 12 year: 2021 text: 2021-Dec.
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on reliability
PublicationTitleAbbrev	TR
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	ref12 ref15 ref14 ref52 ref11 ref10 openstack (ref46) 2009 ref16 ref19 (ref28) 2009 lunardon (ref18) 2014; 6 romano (ref49) 0 he (ref32) 0 ref51 ref50 ref45 ref48 ref47 ref42 ref41 ref44 napierala (ref53) 2012; 6 (ref31) 2011 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref30 ref33 kozik (ref24) 2019; 25 ref2 shu (ref17) 0 ref1 ref39 ref38 xie (ref29) 2017 ref26 ref25 ref20 ref22 (ref23) 2016 ref21 bishop (ref43) 1995 ref27 w -c (ref13) 2019; 477
References_xml	– ident: ref30 doi: 10.1016/j.jss.2019.110456 – ident: ref8 doi: 10.1109/ICST.2013.24 – ident: ref39 doi: 10.1007/BF02834632 – year: 2011 ident: ref31 article-title: LinearSVC in sklearn – ident: ref25 doi: 10.1007/s10796-020-10031-6 – ident: ref14 doi: 10.1145/3180155.3180197 – ident: ref6 doi: 10.1007/s10664-021-10010-8 – ident: ref3 doi: 10.1109/TSE.2017.2787653 – ident: ref27 doi: 10.1007/s11390-017-1713-3 – start-page: 1322 year: 0 ident: ref32 article-title: ADASYN: Adaptive synthetic sampling approach for imbalanced learning publication-title: Proc IEEE Int Joint Conf Neural Netw – ident: ref16 doi: 10.1109/QRS.2018.00047 – ident: ref44 doi: 10.1023/A:1010933404324 – ident: ref10 doi: 10.1109/ICSE.2015.139 – ident: ref21 doi: 10.1016/j.patcog.2019.02.023 – start-page: 1 year: 0 ident: ref49 article-title: Appropriate statistics for ordinal level data: Should we really be using t-test and Cohen'sd for evaluating group differences on the NSSE and other surveys publication-title: Proc Annu Meeting Florida Assoc Inst Res – year: 1995 ident: ref43 publication-title: Neural Networks for Pattern Recognition doi: 10.1093/oso/9780198538493.001.0001 – ident: ref5 doi: 10.1109/TSE.2018.2864217 – ident: ref34 doi: 10.22266/ijies2019.0430.11 – ident: ref37 doi: 10.1016/j.knosys.2019.06.022 – ident: ref38 doi: 10.1109/TSE.2016.2584050 – year: 2017 ident: ref29 article-title: A survey of dimensionality reduction techniques based on random projection – ident: ref9 doi: 10.1002/smr.2376 – ident: ref11 doi: 10.1109/TSE.2018.2876537 – year: 2016 ident: ref23 article-title: imblearn – start-page: 1 year: 0 ident: ref17 article-title: Better security bug report classification via hyperparameter optimization publication-title: Proc IEEE Int Conf Automated Software Engineering – volume: 6 start-page: 79 year: 2014 ident: ref18 article-title: ROSE: A package for binary imbalanced learning publication-title: R Journal doi: 10.32614/RJ-2014-008 – ident: ref1 doi: 10.1016/j.cose.2021.102248 – ident: ref51 doi: 10.1145/3324916 – ident: ref40 doi: 10.1001/jama.2016.7653 – ident: ref22 doi: 10.1016/j.ins.2019.11.004 – ident: ref41 doi: 10.1007/BF00994018 – ident: ref35 doi: 10.1007/s11469-010-9275-4 – ident: ref7 doi: 10.1109/TSE.2019.2937083 – ident: ref20 doi: 10.1142/S0218194018500237 – ident: ref19 doi: 10.1016/j.infsof.2020.106314 – ident: ref12 doi: 10.1109/TSE.2017.2731766 – year: 2009 ident: ref46 – ident: ref48 doi: 10.1186/s12864-019-6413-7 – ident: ref47 doi: 10.1016/j.jss.2019.02.025 – ident: ref36 doi: 10.1016/j.inffus.2019.07.006 – ident: ref4 doi: 10.1109/TSE.2021.3063727 – ident: ref33 doi: 10.1007/11538059_91 – ident: ref50 doi: 10.1109/TSE.2018.2791521 – volume: 6 start-page: 1 year: 2012 ident: ref53 article-title: What is the Bonferroni correction publication-title: AAOS Now – ident: ref52 doi: 10.1016/j.infsof.2017.08.004 – year: 2009 ident: ref28 article-title: Scikit learn – volume: 477 start-page: 47 year: 2019 ident: ref13 article-title: Under-sampling class imbalanced datasets by combining clustering analysis and instance selection publication-title: Inf Sci doi: 10.1016/j.ins.2018.10.029 – volume: 25 start-page: 2 year: 2019 ident: ref24 article-title: Balanced efficient lifelong learning (B-ELLA) for cyber attack detection publication-title: J Universal Comput Sci – ident: ref2 doi: 10.1109/MSR.2010.5463340 – ident: ref45 doi: 10.1109/MSR.2015.78 – ident: ref15 doi: 10.1109/HSI.2012.22 – ident: ref42 doi: 10.1038/nbt1206-1565 – ident: ref26 doi: 10.1515/jisys-2018-0476
SSID	ssj0014498
Score	2.5694156
Snippet	Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product's security risk. However, the class imbalance problem... Identifying security bug reports (SBRs) accurately from a bug repository can reduce a software product’s security risk. However, the class imbalance problem...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1658
SubjectTerms	Algorithms Class imbalance problem class rebalancing methods Classification classification algorithms Comparative studies Computer bugs Debugging Dimensionality reduction Empirical analysis Impact analysis Performance enhancement Prediction algorithms Predictive models Security security bug report (SBRs) classification Software algorithms State-of-the-art reviews
Title	A Comparative Study of Class Rebalancing Methods for Security Bug Report Classification
URI	https://ieeexplore.ieee.org/document/9585022 https://www.proquest.com/docview/2604926321
Volume	70
WOSCitedRecordID	wos000724479600028&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 Electronic Library (IEL) customDbUrl: eissn: 1558-1721 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014498 issn: 0018-9529 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED61FQMMvAqiUJAHBgbSxokdx2OpqBigQqVAt8h1bISEWtQHEv8e23EDCBjYEukuie9i-zv7_B3A6VhjHeacBDihNCAc04CHwvSrJGZjyjCWbh3y4Zr1--loxG8rcF6ehVFKueQz1bKXbi8_n8qlXSprc4NtzZxThSpjrDirVe4YEML9qGteRCPuaXxwyNvDgYkDI2zCU0t3lnybgVxJlR_jsJtcelv_-6xt2PQgEnUKr-9ARU12YeMLtWAdHjuo-0nsjWy64DuaauSKYCJjVJvSKI0ounE1pOfIoFd056vZoYvlEyqweaFhE4qcD_fgvnc57F4FvohCIA2UWARYEZEzZXkBY0oiMZYG4MlECaJZlCthAIsgQjKVMk3TOORjzgmOtA6pMB1Wx_tQm0wn6gCQEWaxtOw7id2vTQVV5hYrHDOeJyltQGtl2Ex6hnFb6OIlc5FGyLPhILOeyLwnGnBWKrwW5Bp_i9at4Usxb_MGNFeey3znm2cmRHPNjfDh71pHsG6fXWSlNKG2mC3VMazJt8XzfHbi_qsPWqrIeQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VggQMvAqiUMADAwNp48SO47EgqiLaCpUC3SLXcRASalEfSPx7bMctIGBgS6SznNz58Z3v_B3A6SDDmZ9y4uGIUo9wTD3uCz2vopANKMNY2nPIhxbrdOJ-n98W4HxxF0YpZZPPVNU82lh-OpIzc1RW4xrb6j1nCZYpIQHOb2stYgaEcLfu6q5owB2RD_Z5rdfVnmCAtYNqCM-ib3uQLaryYyW220tj838ftgUbDkaiem73bSio4Q6sfyEXLMFjHV1-UnsjkzD4jkYZsmUwkVarSWqUWhS1bRXpCdL4Fd25enboYvaEcnSetzApRdaKu3DfuOpdNj1XRsGTGkxMPayISJkyzIAhJYEYSA3xZKQEyViQKqEhiyBCMhWzjMahzwecExxkmU-FnrJZuAfF4Wio9gFpYRZKw78TmYhtLKjSr1jhkPE0imkZqnPFJtJxjJtSFy-J9TV8nvS6ibFE4ixRhrNFg9ecXuNv0ZJR_ELM6bwMlbnlEjf9Jol20uzvBvjg91YnsNrstVtJ67pzcwhrpp88R6UCxel4po5gRb5NnyfjYzvGPgDzfMvA
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=A+Comparative+Study+of+Class+Rebalancing+Methods+for+Security+Bug+Report+Classification&rft.jtitle=IEEE+transactions+on+reliability&rft.au=Zheng%2C+Wei&rft.au=Xun%2C+Yuxing&rft.au=Wu%2C+Xiaoxue&rft.au=Deng%2C+Zhi&rft.date=2021-12-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9529&rft.eissn=1558-1721&rft.volume=70&rft.issue=4&rft.spage=1658&rft_id=info:doi/10.1109%2FTR.2021.3118026&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9529&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9529&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9529&client=summon