Jointly Optimizing Client Selection and Resource Management in Wireless Federated Learning for Internet of Things
Federated learning (FL) has been proposed to efficiently and privacy-preserving distributed machine learning architecture for the Internet of Things (IoT). In a wireless FL system, clients in IoT devices train their local models over the local data sets. The derived local models are uploaded to an F...
Uloženo v:
| Vydáno v: | IEEE internet of things journal Ročník 9; číslo 6; s. 4385 - 4395 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Piscataway
IEEE
15.03.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 2327-4662, 2327-4662 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Federated learning (FL) has been proposed to efficiently and privacy-preserving distributed machine learning architecture for the Internet of Things (IoT). In a wireless FL system, clients in IoT devices train their local models over the local data sets. The derived local models are uploaded to an FL server to generate a global model, broadcasted to the clients in the next global iteration for further training. Owing to the heterogeneous feature of the clients, client selection is critical to determine the overall training time. Traditionally, the objective of client selection is to select the maximum number of clients who can derive and upload their local models before the deadline in each global iteration. However, selecting more clients increases the energy consumption of the clients. Moreover, selecting the maximum number of clients is unnecessary as having fewer clients in early global iterations and more clients in later global iterations have been proved to achieve higher model accuracy. Hence, this article proposes to dynamically adjust and optimize the tradeoff between maximizing the number of selected clients and minimizing the total energy consumption of the clients by selecting suitable clients and allocating appropriate resources in terms of CPU frequency and transmission power. We formulate the joint client selection and resource management problem and design the energy and latency-aware resource management and client selection (ELASTIC) algorithm to efficiently solve the problem. Extensive simulations are conducted to demonstrate the performance of ELASTIC. |
|---|---|
| AbstractList | Federated learning (FL) has been proposed to efficiently and privacy-preserving distributed machine learning architecture for the Internet of Things (IoT). In a wireless FL system, clients in IoT devices train their local models over the local data sets. The derived local models are uploaded to an FL server to generate a global model, broadcasted to the clients in the next global iteration for further training. Owing to the heterogeneous feature of the clients, client selection is critical to determine the overall training time. Traditionally, the objective of client selection is to select the maximum number of clients who can derive and upload their local models before the deadline in each global iteration. However, selecting more clients increases the energy consumption of the clients. Moreover, selecting the maximum number of clients is unnecessary as having fewer clients in early global iterations and more clients in later global iterations have been proved to achieve higher model accuracy. Hence, this article proposes to dynamically adjust and optimize the tradeoff between maximizing the number of selected clients and minimizing the total energy consumption of the clients by selecting suitable clients and allocating appropriate resources in terms of CPU frequency and transmission power. We formulate the joint client selection and resource management problem and design the energy and latency-aware resource management and client selection (ELASTIC) algorithm to efficiently solve the problem. Extensive simulations are conducted to demonstrate the performance of ELASTIC. |
| Author | Devetsikiotis, Michael Ansari, Nirwan Albelaihi, Rana Yu, Liangkun Sun, Xiang |
| Author_xml | – sequence: 1 givenname: Liangkun orcidid: 0000-0003-4062-2499 surname: Yu fullname: Yu, Liangkun email: liangkun@unm.edu organization: SECNet Lab, University of New Mexico, Albuquerque, NM, USA – sequence: 2 givenname: Rana surname: Albelaihi fullname: Albelaihi, Rana email: ralbelaihi@unm.edu organization: SECNet Lab, University of New Mexico, Albuquerque, NM, USA – sequence: 3 givenname: Xiang orcidid: 0000-0002-6954-7018 surname: Sun fullname: Sun, Xiang email: sunxiang@unm.edu organization: SECNet Lab, University of New Mexico, Albuquerque, NM, USA – sequence: 4 givenname: Nirwan orcidid: 0000-0001-8541-3565 surname: Ansari fullname: Ansari, Nirwan email: nirwan.ansari@njit.edu organization: Department of Electrical and Computer Engineering, Advanced Networking Laboratory, New Jersey Institute of Technology, Newark, NJ, USA – sequence: 5 givenname: Michael orcidid: 0000-0001-5053-4105 surname: Devetsikiotis fullname: Devetsikiotis, Michael email: mdevets@unm.edu organization: Department of Electrical and Computer Engineering, University of New Mexico, Albuquerque, NM, USA |
| BookMark | eNp9kEFPwjAUgBuDiYj8AOOliWewXdnWHg0RhWBIFONxebZvWDI6aMsBf71bIMZ48NSm-b730u-SdFztkJBrzoacM3U3my6Ww4QlfCg4EzlPz0g3EUk-GGVZ0vl1vyD9ENaMsUZLucq6ZDerrYvVgS620W7sl3UrOq4sukhfsUIdbe0oOENfMNR7r5E-g4MVblrCOvpufYOFQCdo0ENEQ-cI3rVzytrTqYvoHUZal3T52byGK3JeQhWwfzp75G3ysBw_DeaLx-n4fj7QIlVxYCQYo1EBSKO51gpkqVCPIBFKApdpxk1qlIaGUKbUUgn5kY2MzHIQQhjRI7fHuVtf7_YYYrFuPuCalUWSiXwkZK5YQ_EjpX0dgsey2Hq7AX8oOCvauEUbt2jjFqe4jZP_cbSN0JaKHmz1r3lzNC0i_mxSKVN5ysU3mNSLHA |
| CODEN | IITJAU |
| CitedBy_id | crossref_primary_10_1109_TCOMM_2024_3420733 crossref_primary_10_1109_TCOMM_2024_3443731 crossref_primary_10_1109_JIOT_2024_3462722 crossref_primary_10_1016_j_comnet_2024_110914 crossref_primary_10_1109_JSAC_2022_3229436 crossref_primary_10_1109_JSYST_2022_3206404 crossref_primary_10_1109_TMC_2025_3541191 crossref_primary_10_1109_TMC_2024_3484493 crossref_primary_10_1016_j_future_2025_108114 crossref_primary_10_1007_s10922_024_09857_1 crossref_primary_10_1109_JPROC_2024_3437365 crossref_primary_10_1016_j_resourpol_2023_104250 crossref_primary_10_1109_JIOT_2023_3324666 crossref_primary_10_1145_3638052 crossref_primary_10_1016_j_sysarc_2024_103280 crossref_primary_10_1109_JIOT_2023_3265564 crossref_primary_10_1016_j_future_2024_03_019 crossref_primary_10_3390_fi17030109 crossref_primary_10_1002_spe_3300 crossref_primary_10_1109_JIOT_2022_3194546 crossref_primary_10_1109_JIOT_2025_3545006 crossref_primary_10_1016_j_jfranklin_2025_107857 crossref_primary_10_1109_JIOT_2024_3514864 crossref_primary_10_1109_JIOT_2025_3563614 crossref_primary_10_1109_TCOMM_2023_3253718 crossref_primary_10_3390_electronics12071706 crossref_primary_10_1016_j_eswa_2025_128590 crossref_primary_10_1109_TMC_2021_3136611 crossref_primary_10_1016_j_comnet_2024_110358 crossref_primary_10_1109_JIOT_2023_3264463 crossref_primary_10_1109_COMST_2023_3316615 crossref_primary_10_3390_s23167235 crossref_primary_10_3390_s23020806 crossref_primary_10_1109_JIOT_2022_3194833 crossref_primary_10_1109_ACCESS_2024_3482388 crossref_primary_10_3390_s23177358 crossref_primary_10_1109_OJVT_2025_3573647 crossref_primary_10_1016_j_future_2025_108138 crossref_primary_10_3390_rs16091640 crossref_primary_10_1016_j_ipm_2022_103150 crossref_primary_10_3390_e25081183 crossref_primary_10_1109_JIOT_2024_3425757 crossref_primary_10_3390_math10203751 crossref_primary_10_1016_j_comnet_2025_111233 crossref_primary_10_1109_JIOT_2024_3421991 crossref_primary_10_1016_j_iot_2024_101287 crossref_primary_10_1109_JIOT_2024_3370964 crossref_primary_10_1109_JIOT_2023_3279983 crossref_primary_10_1109_JIOT_2025_3558910 crossref_primary_10_1016_j_ins_2024_121552 crossref_primary_10_1016_j_ins_2024_120344 crossref_primary_10_1109_JIOT_2022_3188556 crossref_primary_10_1109_ACCESS_2023_3280411 crossref_primary_10_1109_TMC_2025_3570018 crossref_primary_10_3390_fi15110352 crossref_primary_10_3390_electronics13234744 crossref_primary_10_1109_JIOT_2024_3350241 crossref_primary_10_1109_TCC_2023_3285534 crossref_primary_10_1007_s11831_023_10011_4 crossref_primary_10_3390_electronics13234585 crossref_primary_10_1016_j_cosrev_2024_100697 crossref_primary_10_1109_ACCESS_2022_3216710 crossref_primary_10_1109_JPROC_2024_3417528 crossref_primary_10_1109_TVT_2023_3333329 crossref_primary_10_3390_math12060920 crossref_primary_10_1109_JIOT_2022_3233595 crossref_primary_10_1109_JIOT_2024_3414472 crossref_primary_10_1109_JIOT_2023_3301019 crossref_primary_10_1109_COMST_2024_3352910 crossref_primary_10_1109_TMC_2025_3532204 |
| Cites_doi | 10.1109/TWC.2020.3042530 10.1109/JIOT.2019.2914947 10.1109/COMST.2015.2388550 10.1109/TWC.2019.2961673 10.1109/MSP.2020.2975749 10.1109/TCOMM.2019.2944169 10.1109/RTSS46320.2019.00043 10.1109/TWC.2021.3052681 10.1109/ICC40277.2020.9149138 10.1109/JSAC.2015.2478718 10.1109/TVT.2019.2915270 10.1109/INFOCOM.2019.8737464 10.1007/978-3-642-73778-7_148 10.1145/990308.990310 10.1109/TWC.2020.3024629 10.1109/MCOM.2016.1600492CM 10.1109/WCSP49889.2020.9299815 10.1109/COMST.2021.3075439 10.1017/S0962492901000071 10.1109/MCOM.001.2000410 10.1109/LCOMM.2017.2690678 10.1109/JIOT.2021.3080078 10.1109/COMST.2019.2924243 10.1109/ICC.2019.8761315 10.1109/4.126534 10.1093/imanum/8.1.141 10.1109/TWC.2020.3031503 10.1109/TWC.2020.3037554 10.1109/ACCESS.2021.3050172 10.1109/ACCESS.2021.3056919 10.1109/JIOT.2020.3022590 10.1109/JSAC.2019.2904348 10.1109/ICC40277.2020.9148625 |
| 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 RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/JIOT.2021.3103715 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2327-4662 |
| EndPage | 4395 |
| ExternalDocumentID | 10_1109_JIOT_2021_3103715 9509751 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Science Foundation grantid: OIA-1757207 funderid: 10.13039/100000001 |
| GroupedDBID | 0R~ 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IFIPE IPLJI JAVBF M43 OCL PQQKQ RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c359t-d8addce9aa8dc1cc9a8f9ec4a2398a18561d5d9ca9aa9dfc8938b64d867a333d3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 94 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000766683600033&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2327-4662 |
| IngestDate | Mon Jun 30 13:41:01 EDT 2025 Tue Nov 18 22:23:49 EST 2025 Sat Nov 29 06:17:00 EST 2025 Wed Aug 27 02:49:22 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 6 |
| 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-c359t-d8addce9aa8dc1cc9a8f9ec4a2398a18561d5d9ca9aa9dfc8938b64d867a333d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0001-5053-4105 0000-0002-6954-7018 0000-0003-4062-2499 0000-0001-8541-3565 |
| PQID | 2637438790 |
| PQPubID | 2040421 |
| PageCount | 11 |
| ParticipantIDs | crossref_primary_10_1109_JIOT_2021_3103715 crossref_citationtrail_10_1109_JIOT_2021_3103715 ieee_primary_9509751 proquest_journals_2637438790 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-03-15 |
| PublicationDateYYYYMMDD | 2022-03-15 |
| PublicationDate_xml | – month: 03 year: 2022 text: 2022-03-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE internet of things journal |
| PublicationTitleAbbrev | JIoT |
| 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 | Li (ref10) 2018 ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref30 ref11 ref33 ref32 ref2 ref1 ref17 ref16 ref19 ref18 Yang (ref28) 2020 Nocedal (ref31) 2006 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref27 McMahan (ref7) ref29 ref8 ref9 ref4 ref3 ref6 ref5 |
| References_xml | – ident: ref20 doi: 10.1109/TWC.2020.3042530 – ident: ref5 doi: 10.1109/JIOT.2019.2914947 – ident: ref6 doi: 10.1109/COMST.2015.2388550 – ident: ref21 doi: 10.1109/TWC.2019.2961673 – ident: ref9 doi: 10.1109/MSP.2020.2975749 – volume-title: Federated optimization in heterogeneous networks year: 2018 ident: ref10 – ident: ref11 doi: 10.1109/TCOMM.2019.2944169 – ident: ref14 doi: 10.1109/RTSS46320.2019.00043 – ident: ref27 doi: 10.1109/TWC.2021.3052681 – ident: ref22 doi: 10.1109/ICC40277.2020.9149138 – ident: ref33 doi: 10.1109/JSAC.2015.2478718 – ident: ref34 doi: 10.1109/TVT.2019.2915270 – ident: ref24 doi: 10.1109/INFOCOM.2019.8737464 – ident: ref36 doi: 10.1007/978-3-642-73778-7_148 – volume-title: Numerical Optimization year: 2006 ident: ref31 – ident: ref37 doi: 10.1145/990308.990310 – ident: ref26 doi: 10.1109/TWC.2020.3024629 – ident: ref2 doi: 10.1109/MCOM.2016.1600492CM – ident: ref16 doi: 10.1109/WCSP49889.2020.9299815 – ident: ref1 doi: 10.1109/COMST.2021.3075439 – ident: ref30 doi: 10.1017/S0962492901000071 – ident: ref8 doi: 10.1109/MCOM.001.2000410 – ident: ref4 doi: 10.1109/LCOMM.2017.2690678 – ident: ref18 doi: 10.1109/JIOT.2021.3080078 – ident: ref3 doi: 10.1109/COMST.2019.2924243 – ident: ref12 doi: 10.1109/ICC.2019.8761315 – start-page: 1273 volume-title: Proc. 20th Int. Conf. Artif. Intell. Stat. ident: ref7 article-title: Communication-efficient learning of deep networks from decentralized data – ident: ref29 doi: 10.1109/4.126534 – ident: ref32 doi: 10.1093/imanum/8.1.141 – ident: ref17 doi: 10.1109/TWC.2020.3031503 – ident: ref25 doi: 10.1109/TWC.2020.3037554 – ident: ref13 doi: 10.1109/ACCESS.2021.3050172 – ident: ref19 doi: 10.1109/ACCESS.2021.3056919 – ident: ref23 doi: 10.1109/JIOT.2020.3022590 – ident: ref35 doi: 10.1109/JSAC.2019.2904348 – ident: ref15 doi: 10.1109/ICC40277.2020.9148625 – volume-title: Delay minimization for federated learning over wireless communication networks year: 2020 ident: ref28 |
| SSID | ssj0001105196 |
| Score | 2.5324178 |
| Snippet | Federated learning (FL) has been proposed to efficiently and privacy-preserving distributed machine learning architecture for the Internet of Things (IoT). In... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 4385 |
| SubjectTerms | Algorithms Client selection Clients Computational modeling Data models Energy consumption Federated learning federated learning (FL) Internet of Things Iterative methods Machine learning Model accuracy Network latency Optimization Resource management Servers Training waiting time Wireless communication |
| Title | Jointly Optimizing Client Selection and Resource Management in Wireless Federated Learning for Internet of Things |
| URI | https://ieeexplore.ieee.org/document/9509751 https://www.proquest.com/docview/2637438790 |
| Volume | 9 |
| WOSCitedRecordID | wos000766683600033&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: 2327-4662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001105196 issn: 2327-4662 databaseCode: RIE dateStart: 20140101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61ePDiW6xWmYMncWt2s4_kKMWiRVrBB70taZKVQt2q3Qr6653spq2gCN72kMCy32bmm8nMfIScmKE0GfdDTxuuvRBB94Z-xD0ZGpZxGlFVygE93iS9Hh8MxG2NnC16YYwxZfGZadnH8i5fT9TMpsrOBXq3xPZLryRJUvVqLfMpviUjsbu49Kk471737zEADPyW1dJKrPDtN9dTaqn8MMClV-ls_O99Nsm6Y49wUcG9RWom3yYbc2UGcAd1h7x2J6O8GH9AHy3C8-gT_RO0x7b1Ee5K4RtEA2SuYZ69h2UZDIxysDWxY7SB0LGzJpCOanCDWJ8AWS5UeURTwCSDSvlzlzx0Lu_bV54TV_AUi0ThaY6WTRkhJdfKV0pIngmjQmkHAkr04rGvIy2UxBVCZwp5DR_GoeZxIhljmu2Rej7JzT4BGmRUoDHQGXKFjAXSaIw7JKPa1xhg8wah8--eKjd53ApgjNMyAqEitVClFqrUQdUgp4stL9XYjb8W71hsFgsdLA3SnIObuoM5TYOYIWfiiaAHv-86JGuB7XCwJXtRk9SLt5k5IqvqvRhN347Lf-4LeMXXpA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fSxwxEB5EhfZFq7Z4Vtt58Em6mmz2R_Io4qH2egqexbcll2Tl4NzTcxXqX-9kN3cKlULf9iGBZb_NzDeTmfkAdt1Qu1LyJLJO2igh0KMhT2WkEydKyVJmGjmg372835fX1-piAX7Me2Gcc03xmdv3j81dvp2YR58qO1Dk3XLfL72UJknM226t14wK93QkC1eXnKmDs9PzAYWAMd_3alq5l75943waNZW_THDjV7qr__dGn2Al8Ec8bAFfgwVXrcPqTJsBw1HdgPuzyaiqx3_wnGzC7eiZPBQejX3zI1420jeEB-rK4ix_j6-FMDiq0FfFjskKYtdPmyBCajGMYr1B4rnYZhJdjZMSW-3Pz3DVPR4cnURBXiEyIlV1ZCXZNuOU1tIabozSslTOJNqPBNTkxzNuU6uMphXKloaYjRxmiZVZroUQVnyBxWpSuU1AFpdMkTmwJbGFUsTaWYo8tGCWWwqxZQfY7LsXJswe9xIY46KJQZgqPFSFh6oIUHVgb77lrh288a_FGx6b-cIASwe2Z-AW4Wg-FHEmiDXJXLGt93d9hw8ng1-9onfa__kVPsa-38EX8KXbsFhPH90OLJunevQw_db8fy_Twtrr |
| 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=Jointly+Optimizing+Client+Selection+and+Resource+Management+in+Wireless+Federated+Learning+for+Internet+of+Things&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Yu%2C+Liangkun&rft.au=Rana+Albelaihi&rft.au=Sun%2C+Xiang&rft.au=Ansari%2C+Nirwan&rft.date=2022-03-15&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2327-4662&rft.volume=9&rft.issue=6&rft.spage=4385&rft_id=info:doi/10.1109%2FJIOT.2021.3103715&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2327-4662&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2327-4662&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2327-4662&client=summon |