Semantic Communications for Image Recovery and Classification via Deep Joint Source and Channel Coding

With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning, the semantic-aware and task-oriented communications with de...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on wireless communications Jg. 23; H. 8; S. 8388 - 8404
Hauptverfasser:	Lyu, Zhonghao, Zhu, Guangxu, Xu, Jie, Ai, Bo, Cui, Shuguang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.08.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Artificial intelligence Channel coding Classification Clustering Data mining Data recovery deep joint source and channel coding (JSCC) Deep learning Edge artificial intelligence (AI) Error reduction Feature extraction Image coding Image quality Labels Logic gates Machine learning Maximization Optimization semantic communications Semantics Task analysis task-oriented communications
ISSN:	1536-1276, 1558-2248
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning, the semantic-aware and task-oriented communications with deep joint source and channel coding (JSCC) have emerged as new paradigm shifts in 6G from the conventional data-oriented communications with separate source and channel coding (SSCC). However, most existing works focused on the deep JSCC designs for one task of data recovery or AI task execution independently, which cannot be transferred to other unintended tasks. Differently, this paper investigates the JSCC semantic communications to support multi-task services, by performing the image data recovery and classification task execution simultaneously. First, we propose a new end-to-end deep JSCC framework by unifying the coding rate reduction maximization and the mean square error (MSE) minimization in the loss function. Here, the coding rate reduction maximization facilitates the learning of discriminative features for enabling to perform classification tasks directly in the feature space, and the MSE minimization helps the learning of informative features for high-quality image data recovery. Next, to further improve the robustness against variational wireless channels, we propose a new gated deep JSCC design, in which a gated net is incorporated for adaptively pruning the output features to adjust their dimensions based on channel conditions. Finally, we present extensive numerical experiments to validate the performance of our proposed deep JSCC designs as compared to various benchmark schemes. It is shown that our proposed designs simultaneously provide efficient multi-task services, and the proposed gated deep JSCC framework efficiently reduces the communication overhead with only marginal performance loss. It is also shown that performing the classification task on the feature space via coding rate reduction maximization is able to better defend the label corruption than the traditional label-fitting methods.
AbstractList	With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning, the semantic-aware and task-oriented communications with deep joint source and channel coding (JSCC) have emerged as new paradigm shifts in 6G from the conventional data-oriented communications with separate source and channel coding (SSCC). However, most existing works focused on the deep JSCC designs for one task of data recovery or AI task execution independently, which cannot be transferred to other unintended tasks. Differently, this paper investigates the JSCC semantic communications to support multi-task services, by performing the image data recovery and classification task execution simultaneously. First, we propose a new end-to-end deep JSCC framework by unifying the coding rate reduction maximization and the mean square error (MSE) minimization in the loss function. Here, the coding rate reduction maximization facilitates the learning of discriminative features for enabling to perform classification tasks directly in the feature space, and the MSE minimization helps the learning of informative features for high-quality image data recovery. Next, to further improve the robustness against variational wireless channels, we propose a new gated deep JSCC design, in which a gated net is incorporated for adaptively pruning the output features to adjust their dimensions based on channel conditions. Finally, we present extensive numerical experiments to validate the performance of our proposed deep JSCC designs as compared to various benchmark schemes. It is shown that our proposed designs simultaneously provide efficient multi-task services, and the proposed gated deep JSCC framework efficiently reduces the communication overhead with only marginal performance loss. It is also shown that performing the classification task on the feature space via coding rate reduction maximization is able to better defend the label corruption than the traditional label-fitting methods.
Author	Lyu, Zhonghao Xu, Jie Zhu, Guangxu Ai, Bo Cui, Shuguang
Author_xml	– sequence: 1 givenname: Zhonghao orcidid: 0000-0002-0980-1395 surname: Lyu fullname: Lyu, Zhonghao email: zhonghaolyu@link.cuhk.edu.cn organization: Future Network of Intelligence Institute (FNii) and the School of Science and Engineering (SSE), The Chinese University of Hong Kong (Shenzhen), Shenzhen, China – sequence: 2 givenname: Guangxu orcidid: 0000-0001-9532-9201 surname: Zhu fullname: Zhu, Guangxu email: gxzhu@sribd.cn organization: Shenzhen Research Institute of Big Data, Shenzhen, China – sequence: 3 givenname: Jie orcidid: 0000-0002-4854-8839 surname: Xu fullname: Xu, Jie email: xujie@cuhk.edu.cn organization: School of Science and Engineering (SSE), Future Network of Intelligence Institute (FNii), The Chinese University of Hong Kong (Shenzhen), Shenzhen, China – sequence: 4 givenname: Bo orcidid: 0000-0001-6850-0595 surname: Ai fullname: Ai, Bo email: boai@bjtu.edu.cn organization: State Key Laboratory of Advanced Rail Autonomous Operation and the School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China – sequence: 5 givenname: Shuguang orcidid: 0000-0003-2608-775X surname: Cui fullname: Cui, Shuguang email: shuguangcui@cuhk.edu.cn organization: School of Science and Engineering (SSE), Future Network of Intelligence Institute (FNii), The Chinese University of Hong Kong (Shenzhen), Shenzhen, China
BookMark	eNp9kDtPwzAURi0EEhTYGRgsMaf4ETv2iMKrqBISDzFGjntdjBq72Gkl_j0p7YAYmO4dvnO_qzNC-yEGQOiMkjGlRF--vNVjRhgfc15qzskeOqJCqIKxUu1vdi4Lyip5iEY5fxBCKynEEXLP0JnQe4vr2HWr4K3pfQwZu5jwpDNzwE9g4xrSFzZhhuuFydm7XQyvvcHXAEv8EH3o8XNcJQvb4LsJARbD2ZkP8xN04Mwiw-luHqPX25uX-r6YPt5N6qtpYZlmfVEpVXJmNW0ttNrptlJla5TgTmgqpVJ2ZpxlxBIubMWl01qKqnJOtQLaVvJjdLG9u0zxcwW5bz6Gl8JQ2XCih46y0psU2aZsijkncM0y-c6kr4aSZmOzGWw2G5vNzuaAyD-I9f2Pgz4Zv_gPPN-CHgB-9XCliGT8G-4ZhBM
CODEN	ITWCAX
CitedBy_id	crossref_primary_10_1016_j_dcan_2025_06_010 crossref_primary_10_1016_j_phycom_2025_102764 crossref_primary_10_1109_TWC_2025_3542798 crossref_primary_10_1109_LWC_2025_3548084 crossref_primary_10_3233_XST_240189 crossref_primary_10_1109_LCOMM_2025_3544882 crossref_primary_10_1109_JSAC_2025_3536557 crossref_primary_10_1109_TMC_2025_3540300 crossref_primary_10_1109_ACCESS_2025_3593341 crossref_primary_10_1109_TWC_2024_3483314 crossref_primary_10_1007_s10922_025_09927_y crossref_primary_10_1109_TWC_2025_3552255 crossref_primary_10_3390_app15094608 crossref_primary_10_1109_TWC_2025_3527014 crossref_primary_10_1016_j_phycom_2025_102836 crossref_primary_10_1109_TCOMM_2025_3541027 crossref_primary_10_1109_TVT_2025_3540603 crossref_primary_10_1007_s40435_025_01849_6 crossref_primary_10_1016_j_neucom_2025_131347 crossref_primary_10_1109_TWC_2024_3510418 crossref_primary_10_1016_j_jfranklin_2025_107598 crossref_primary_10_1109_LWC_2025_3527145
Cites_doi	10.1109/JSTSP.2022.3226836 10.1109/CVPR.2019.00939 10.3390/e24040456 10.1109/TCCN.2019.2919300 10.1109/CVPR.2016.90 10.1109/JSAC.2023.3288231 10.1109/JSAC.2021.3087240 10.1109/LWC.2021.3136045 10.1109/ICRA46639.2022.9811825 10.1109/TWC.2020.2970707 10.1109/TIP.2003.819861 10.1002/0471200611 10.1109/CVPRW.2018.00143 10.1109/GCWkshps58843.2023.10464706 10.1007/s11432-022-3652-2 10.1109/GLOBECOM48099.2022.10000850 10.1109/JSAC.2022.3221991 10.1145/584091.584093 10.1109/JSAC.2022.3180802 10.1109/TPAMI.2007.1085 10.1109/JSAC.2022.3221999 10.1109/JIOT.2021.3103320 10.1109/JSAC.2020.3036955 10.1109/TSP.2021.3071210 10.1109/JSAC.2021.3126087 10.1109/JSAC.2022.3223408 10.1016/j.comnet.2021.107930 10.1109/JSAC.2021.3126076 10.1109/TWC.2022.3191118 10.3390/technologies9010002 10.1109/ICCC52777.2021.9580301
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TWC.2023.3349330
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications 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 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 Computer and Information Systems Abstracts Professional
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	1558-2248
EndPage	8404
ExternalDocumentID	10_1109_TWC_2023_3349330 10388062
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: U2001208; 92267202; 62293482; 62001310; 62221001 funderid: 10.13039/501100001809 – fundername: Basic and Applied Basic Research Foundation of Guangdong Province; Guangdong Basic and Applied Basic Research Foundation grantid: 2022A1515010109 funderid: 10.13039/501100021171 – fundername: National Key Research and Development Program of China; National Key Research and Development Program grantid: 2021YFB2900301; 2020YFB1806604; 2021YFB3901302 funderid: 10.13039/501100012166 – fundername: Fundamental Research Funds for the Central Universities grantid: 2022JBQY004 funderid: 10.13039/501100012226 – fundername: Internal Project Fund from Shenzhen Research Institute of Big Data grantid: J00120230001 – fundername: Fundamental Research Funds for the Central Universities (Collaborative Innovation Center of Railway Traffic Safety) grantid: 2022JBXT001 – fundername: Basic Research Project of Hetao Shenzhen-HK S&T Cooperation Zone grantid: HZQB-KCZYZ-2021067 – fundername: Shenzhen Outstanding Talents Training Fund grantid: 202002 – fundername: Guangdong Research Projects grantid: 2017ZT07X152; 2019CX01X104 – fundername: Shenzhen Municipal Fundamental Research Program; Shenzhen Fundamental Research Program grantid: JCYJ20210324133405015 funderid: 10.13039/501100017607
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IES IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c292t-788432c91bceb9f9b784ba853f5916688cdafc20c035c736f996577ff8b5ebb63
IEDL.DBID	RIE
ISICitedReferencesCount	45
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001329887800019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1276
IngestDate	Fri Jul 25 12:30:22 EDT 2025 Sat Nov 29 06:23:59 EST 2025 Tue Nov 18 22:11:35 EST 2025 Wed Aug 27 02:32:38 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
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-c292t-788432c91bceb9f9b784ba853f5916688cdafc20c035c736f996577ff8b5ebb63
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0980-1395 0000-0002-4854-8839 0000-0001-9532-9201 0000-0003-2608-775X 0000-0001-6850-0595
PQID	3092924796
PQPubID	105736
PageCount	17
ParticipantIDs	proquest_journals_3092924796 ieee_primary_10388062 crossref_citationtrail_10_1109_TWC_2023_3349330 crossref_primary_10_1109_TWC_2023_3349330
PublicationCentury	2000
PublicationDate	2024-08-01
PublicationDateYYYYMMDD	2024-08-01
PublicationDate_xml	– month: 08 year: 2024 text: 2024-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on wireless communications
PublicationTitleAbbrev	TWC
PublicationYear	2024
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 ref35 ref12 ref15 ref14 ref31 ref30 ref11 ref33 ref10 ref2 ref1 Ma (ref6) 2023 ref17 ref16 ref38 ref19 ref18 Zhang (ref25) 2022 Krizhevsky (ref37) 2009 ref24 ref23 ref26 ref20 ref22 ref21 LeCun (ref36) ref28 ref29 ref8 ref7 Yu (ref27); 33 Goodfellow (ref34) 2016 ref9 ref4 Xue (ref32) ref3 ref5
References_xml	– ident: ref8 doi: 10.1109/JSTSP.2022.3226836 – ident: ref33 doi: 10.1109/CVPR.2019.00939 – ident: ref28 doi: 10.3390/e24040456 – ident: ref11 doi: 10.1109/TCCN.2019.2919300 – year: 2023 ident: ref6 article-title: A theory for semantic communications publication-title: arXiv:2303.05181 – volume-title: Deep Learning year: 2016 ident: ref34 – ident: ref38 doi: 10.1109/CVPR.2016.90 – ident: ref17 doi: 10.1109/JSAC.2023.3288231 – ident: ref16 doi: 10.1109/JSAC.2021.3087240 – ident: ref22 doi: 10.1109/LWC.2021.3136045 – ident: ref23 doi: 10.1109/ICRA46639.2022.9811825 – volume: 33 start-page: 9422 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref27 article-title: Learning diverse and discriminative representations via the principle of maximal coding rate reduction – ident: ref29 doi: 10.1109/TWC.2020.2970707 – ident: ref18 doi: 10.1109/TIP.2003.819861 – ident: ref30 doi: 10.1002/0471200611 – ident: ref35 doi: 10.1109/CVPRW.2018.00143 – year: 2009 ident: ref37 article-title: Learning multiple layers of features from tiny images – ident: ref1 doi: 10.1109/GCWkshps58843.2023.10464706 – ident: ref4 doi: 10.1007/s11432-022-3652-2 – ident: ref24 doi: 10.1109/GLOBECOM48099.2022.10000850 – ident: ref10 doi: 10.1109/JSAC.2022.3221991 – ident: ref9 doi: 10.1145/584091.584093 – ident: ref14 doi: 10.1109/JSAC.2022.3180802 – ident: ref26 doi: 10.1109/TPAMI.2007.1085 – ident: ref13 doi: 10.1109/JSAC.2022.3221999 – start-page: 24851 volume-title: Proc. Int. Conf. Mach. Learn. (ICML) ident: ref32 article-title: Investigating why contrastive learning benefits robustness against label noise – ident: ref2 doi: 10.1109/JIOT.2021.3103320 – ident: ref19 doi: 10.1109/JSAC.2020.3036955 – ident: ref15 doi: 10.1109/TSP.2021.3071210 – ident: ref20 doi: 10.1109/JSAC.2021.3126087 – ident: ref7 doi: 10.1109/JSAC.2022.3223408 – volume-title: The MNIST Database of Handwritten Digits ident: ref36 – ident: ref5 doi: 10.1016/j.comnet.2021.107930 – ident: ref3 doi: 10.1109/JSAC.2021.3126076 – ident: ref21 doi: 10.1109/TWC.2022.3191118 – ident: ref31 doi: 10.3390/technologies9010002 – year: 2022 ident: ref25 article-title: A unified multi-task semantic communication system for multimodal data publication-title: arXiv:2209.07689 – ident: ref12 doi: 10.1109/ICCC52777.2021.9580301
SSID	ssj0017655
Score	2.6342294
Snippet	With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	8388
SubjectTerms	Artificial intelligence Channel coding Classification Clustering Data mining Data recovery deep joint source and channel coding (JSCC) Deep learning Edge artificial intelligence (AI) Error reduction Feature extraction Image coding Image quality Labels Logic gates Machine learning Maximization Optimization semantic communications Semantics Task analysis task-oriented communications
Title	Semantic Communications for Image Recovery and Classification via Deep Joint Source and Channel Coding
URI	https://ieeexplore.ieee.org/document/10388062 https://www.proquest.com/docview/3092924796
Volume	23
WOSCitedRecordID	wos001329887800019&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: 1558-2248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017655 issn: 1536-1276 databaseCode: RIE dateStart: 20020101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46POjBnxOnU3Lw4qFb26RJc5SpqMgQNnG30qQvOHDd2LqB_71J2o0NUfDWw8uj5Evy3kveex9C15xEEsKUelyGyrMtuz2REfC0Vsb6B0xA6lrmv_BuNx4MxGtVrO5qYQDAJZ9By366t_xsrOb2qqwduNYl9sTd5pyVxVqrJwPOHMWp2cGWWIav3iR90e6_d1qWJrxFCLUB_IYNcqQqP05iZ14eDv75Y4dov_Ij8W0J_BHagvwY7a11FzxBugcjM29DhTeqQGbY-Kn4aWQOEmyDT7OWv3CaZ9jxY9rMISeGF8MU3wFM8PN4mBe45275S8GP1GbHGLXW8NXR28N9v_PoVbQKngpFWNj8QUpCJQKpQAotJI-pTI3Z1pHxFVkcqyzVKvSVTyLFCdMmJIo41zqWEUjJyCmq5eMczhDWmc4ESONSWJ0iEpRGmmkFQcYVENFA7eVEJ6rqOW6pLz4TF3v4IjHQJBaapIKmgW5WIyZlv40_ZOsWijW5EoUGai7BTKodOUuIbxzBkHLBzn8ZdoF2jXZaZvc1Ua2YzuES7ahFMZxNr9xi-wbEKdG4
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG8MmqgHPzGiqD148TAYa7euR4MSUCQmYOS2rN1rJJFB-Er87227QSBGE287vLZLf23fe-1774fQLSO-AC-mDhOedEzJbocnBBylpNb-tYBDbEvmt1mnE_b7_DVPVre5MABgg8-gYj7tW34yknNzVVat2dIl5sTd9in13Cxda_VowAJLcqr3sKGWYatXSZdXe-_1iiEKrxBCjQu_oYUsrcqPs9gqmMbhP3_tCB3kliS-z6A_RluQnqD9tfqCp0h1YahnbiDxRh7IFGtLFbeG-ijBxv3Uq_kLx2mCLUOmiR2yYngxiPEDwBg_jQbpDHftPX8m-BGb-BjdrVF9RfTWeOzVm05OrOBIj3szE0FIiSd5TUgQXHHBQipirbiVr63FIAxlEivpudIlvmQkUNop8hlTKhQ-CBGQM1RIRymcI6wSlXAQ2qgwfXKfU-qrQEmoJUwC4SVUXU50JPOq44b84jOy3ofLIw1NZKCJcmhK6G7VYpxV3PhDtmigWJPLUCih8hLMKN-T04i42hT0KOPBxS_NbtBus_fSjtqtzvMl2tMj0SzWr4wKs8kcrtCOXMwG08m1XXjf1W3U_w
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=Semantic+Communications+for+Image+Recovery+and+Classification+via+Deep+Joint+Source+and+Channel+Coding&rft.jtitle=IEEE+transactions+on+wireless+communications&rft.au=Lyu%2C+Zhonghao&rft.au=Zhu%2C+Guangxu&rft.au=Xu%2C+Jie&rft.au=Ai%2C+Bo&rft.date=2024-08-01&rft.pub=IEEE&rft.issn=1536-1276&rft.volume=23&rft.issue=8&rft.spage=8388&rft.epage=8404&rft_id=info:doi/10.1109%2FTWC.2023.3349330&rft.externalDocID=10388062
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1276&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1276&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1276&client=summon