Fast Training Algorithms for Deep Convolutional Fuzzy Systems With Application to Stock Index Prediction
A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multilayer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS b...
Uloženo v:
| Vydáno v: | IEEE transactions on fuzzy systems Ročník 28; číslo 7; s. 1301 - 1314 |
|---|---|
| Hlavní autor: | |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
New York
IEEE
01.07.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1063-6706, 1941-0034 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multilayer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on an input-output data pairs, we propose a bottom-up layer-by-layer scheme. Specifically, by viewing each of the first-layer fuzzy systems as a weak estimator of the output based only on a very small portion of the input variables, we design these fuzzy systems using the Wang-Mendel method. After the first-layer fuzzy systems are designed, we pass the data through the first layer to form a new dataset and design the second-layer fuzzy systems based on this new dataset in the same way as designing the first-layer fuzzy systems. Repeating this process layer-by-layer, we design the whole DCFS. We also propose a DCFS with parameter sharing to save memory and computation. We apply the DCFS models to predict a synthetic chaotic plus random time-series and the real Hang Seng Index of the Hong Kong stock market. |
|---|---|
| AbstractList | A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multilayer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on an input–output data pairs, we propose a bottom–up layer-by-layer scheme. Specifically, by viewing each of the first-layer fuzzy systems as a weak estimator of the output based only on a very small portion of the input variables, we design these fuzzy systems using the Wang–Mendel method. After the first-layer fuzzy systems are designed, we pass the data through the first layer to form a new dataset and design the second-layer fuzzy systems based on this new dataset in the same way as designing the first-layer fuzzy systems. Repeating this process layer-by-layer, we design the whole DCFS. We also propose a DCFS with parameter sharing to save memory and computation. We apply the DCFS models to predict a synthetic chaotic plus random time-series and the real Hang Seng Index of the Hong Kong stock market. |
| Author | Wang, Li-Xin |
| Author_xml | – sequence: 1 givenname: Li-Xin orcidid: 0000-0002-0820-9592 surname: Wang fullname: Wang, Li-Xin email: lxwang@ucas.edu.cn organization: University of Chinese Academy of Sciences, Beijing, China |
| BookMark | eNp9kEFLwzAYhoMoqNM_oJeA5858TZemxzGdDgYKmwheSpZ-dZm1qUkmbr_e1g0PHjx9ge95kzfPKTmsbY2EXADrA7Dsej5-ennpxwyyfpxxlkh5QE4gSyBijCeH7ZkJHomUiWNy6v2KMUgGIE_Icqx8oHOnTG3qVzqsXq0zYfnuaWkdvUFs6MjWn7ZaB2NrVdHxervd0NnGB2yh55alw6apjFYdQIOls2D1G53UBX7RR4eF0d3mjByVqvJ4vp898jS-nY_uo-nD3WQ0nEaa8yxEWPCygCJJU1Q6FlIvMBNpIbvqmrFFKbQClDFAwlU2AB2jEFwOFAIMOCx4j1zt7m2c_VijD_nKrl3b3Odx0hrJJOdpS8U7SjvrvcMyb5x5V26TA8s7o_mP0bwzmu-NtiH5J6RN-Pl2aP1V_0cvd1GDiL9vyVRKwWP-Dc5nh2I |
| CODEN | IEFSEV |
| CitedBy_id | crossref_primary_10_1109_TFUZZ_2024_3354919 crossref_primary_10_1007_s10489_022_04134_7 crossref_primary_10_1016_j_energy_2020_118700 crossref_primary_10_1109_TFUZZ_2024_3397728 crossref_primary_10_1109_TETCI_2024_3432667 crossref_primary_10_1109_TFUZZ_2024_3398719 crossref_primary_10_1109_TFUZZ_2022_3149395 crossref_primary_10_1109_TFUZZ_2023_3293834 crossref_primary_10_1109_TFUZZ_2025_3588624 crossref_primary_10_1109_TFUZZ_2023_3330883 crossref_primary_10_1145_3502289 crossref_primary_10_1007_s00521_021_06807_9 crossref_primary_10_1007_s10614_024_10599_0 crossref_primary_10_1007_s10614_023_10464_6 crossref_primary_10_1109_TFUZZ_2025_3572922 crossref_primary_10_1109_TFUZZ_2020_3021713 crossref_primary_10_1007_s10462_022_10188_3 crossref_primary_10_1109_TFUZZ_2022_3163909 crossref_primary_10_1109_TFUZZ_2024_3519767 crossref_primary_10_1109_TFUZZ_2021_3098339 crossref_primary_10_1109_TITS_2022_3222492 crossref_primary_10_1109_TFUZZ_2023_3347793 crossref_primary_10_1109_TSMC_2025_3534988 crossref_primary_10_1007_s10489_021_02326_1 crossref_primary_10_1038_s41598_023_48575_7 crossref_primary_10_1109_ACCESS_2022_3171109 |
| Cites_doi | 10.1007/s12083-015-0365-8 10.4018/IJCINI.2016010104 10.1109/TFUZZ.2006.882472 10.1109/ICIES.2012.6530868 10.1109/FUZZY.1992.258711 10.1109/21.199466 10.1109/FUZZ-IEEE.2017.8015616 10.1109/ICEEE.2011.6106658 10.1080/00207179108934205 10.3233/IFS-141410 10.1109/IEDEC.2013.6526772 10.2307/2325486 10.3905/joi.2001.319457 10.1109/TFUZZ.2005.856559 10.1109/FUZZY.2010.5584232 10.1109/ICISIP.2004.1287681 10.1109/TETCI.2017.2761915 10.1109/TCYB.2013.2295114 10.1016/S0165-0114(01)00176-2 10.1016/S0165-0114(96)00197-2 10.1109/TFUZZ.2014.2374193 10.5391/IJFIS.2008.8.2.087 10.1109/TMECH.2015.2494607 10.1109/TFUZZ.2017.2729507 10.1109/TFUZZ.2004.832538 10.1006/jcss.1997.1504 10.1007/s00500-013-1179-3 10.1007/s00500-018-3111-3 10.1109/TFUZZ.2017.2698399 10.1109/TFUZZ.2014.2346244 10.1109/TFUZZ.2003.819839 10.1007/BF00058655 10.1109/TFUZZ.2008.924343 10.1016/j.apm.2007.03.007 10.1016/j.smhl.2018.07.001 10.1109/TFUZZ.2006.876365 10.3182/20110828-6-IT-1002.00986 10.1109/91.797984 10.1038/nature14539 10.1109/TFUZZ.2017.2701313 10.1109/FUZZY.2010.5584851 10.1109/ICCCYB.2009.5393940 10.1109/IJCNN.2016.7727238 10.1023/A:1010933404324 10.1162/neco.2006.18.7.1527 10.1109/91.868953 10.1109/FUZZY.2010.5584496 10.1093/rfs/1.1.41 10.1109/TFUZZ.2016.2574911 10.1038/nature16961 10.1016/j.jsv.2004.11.030 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TFUZZ.2019.2930488 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access (Activated by CARLI) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library Online 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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1941-0034 |
| EndPage | 1314 |
| ExternalDocumentID | 10_1109_TFUZZ_2019_2930488 8788632 |
| Genre | orig-research |
| GroupedDBID | -~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c339t-ed3fd1d477eac268cbe967d86706c00bf6ca1e821143a951c2e66385ae11531b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 73 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000545205300011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1063-6706 |
| IngestDate | Mon Jun 30 02:26:23 EDT 2025 Sat Nov 29 03:12:38 EST 2025 Tue Nov 18 22:32:15 EST 2025 Wed Aug 27 02:37:45 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0/legalcode |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c339t-ed3fd1d477eac268cbe967d86706c00bf6ca1e821143a951c2e66385ae11531b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-0820-9592 |
| OpenAccessLink | https://ieeexplore.ieee.org/document/8788632 |
| PQID | 2419498337 |
| PQPubID | 85428 |
| PageCount | 14 |
| ParticipantIDs | crossref_primary_10_1109_TFUZZ_2019_2930488 proquest_journals_2419498337 crossref_citationtrail_10_1109_TFUZZ_2019_2930488 ieee_primary_8788632 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-07-01 |
| PublicationDateYYYYMMDD | 2020-07-01 |
| PublicationDate_xml | – month: 07 year: 2020 text: 2020-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on fuzzy systems |
| PublicationTitleAbbrev | TFUZZ |
| PublicationYear | 2020 |
| 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 | ref57 ref13 ref12 ref59 rapach (ref52) 0; 2a ref15 shiller (ref56) 2006 ref55 ref11 lecun (ref1) 1990 ref54 ref10 ref17 ref16 ref19 ref18 ref51 ref50 dong (ref14) 2004; 2 ref46 ref45 ref48 ref41 ref44 soros (ref53) 2003 ref8 ref7 malkiel (ref47) 2012 ref9 ref6 ref5 ref40 hastie (ref43) 2009 ref35 ref34 ref37 ref36 ref31 ref30 ref33 surowiecki (ref42) 2005 ref32 lo (ref49) 2001 ref2 ref39 ref38 lecun (ref3) 2015; 521 ref24 ref23 ref26 ref25 ref20 silver (ref4) 2016; 529 ref22 ref21 wang (ref58) 1997 ref27 ahin (ref28) 2011; 44 ref29 ref60 ref61 |
| References_xml | – ident: ref24 doi: 10.1007/s12083-015-0365-8 – volume: 2 start-page: 1530 year: 2004 ident: ref14 article-title: Approach for evolving hierarchical T-S fuzzy systems publication-title: Proc Int Conf Signal Process – ident: ref26 doi: 10.4018/IJCINI.2016010104 – ident: ref13 doi: 10.1109/TFUZZ.2006.882472 – year: 2012 ident: ref47 publication-title: A Random Walk Down Wall Street – ident: ref23 doi: 10.1109/ICIES.2012.6530868 – ident: ref60 doi: 10.1109/FUZZY.1992.258711 – ident: ref40 doi: 10.1109/21.199466 – ident: ref37 doi: 10.1109/FUZZ-IEEE.2017.8015616 – ident: ref32 doi: 10.1109/ICEEE.2011.6106658 – ident: ref6 doi: 10.1080/00207179108934205 – ident: ref20 doi: 10.3233/IFS-141410 – ident: ref18 doi: 10.1109/IEDEC.2013.6526772 – ident: ref48 doi: 10.2307/2325486 – ident: ref51 doi: 10.3905/joi.2001.319457 – ident: ref11 doi: 10.1109/TFUZZ.2005.856559 – ident: ref19 doi: 10.1109/FUZZY.2010.5584232 – ident: ref15 doi: 10.1109/ICISIP.2004.1287681 – ident: ref38 doi: 10.1109/TETCI.2017.2761915 – ident: ref35 doi: 10.1109/TCYB.2013.2295114 – ident: ref10 doi: 10.1016/S0165-0114(01)00176-2 – ident: ref7 doi: 10.1016/S0165-0114(96)00197-2 – ident: ref54 doi: 10.1109/TFUZZ.2014.2374193 – ident: ref30 doi: 10.5391/IJFIS.2008.8.2.087 – ident: ref31 doi: 10.1109/TMECH.2015.2494607 – ident: ref39 doi: 10.1109/TFUZZ.2017.2729507 – ident: ref21 doi: 10.1109/TFUZZ.2004.832538 – year: 2009 ident: ref43 publication-title: The Elements of Statistical Learning Data Mining Inference and Prediction – ident: ref46 doi: 10.1006/jcss.1997.1504 – start-page: 396 year: 1990 ident: ref1 article-title: Handwritten digit recognition with a back-propagation network publication-title: Proc Adv Neural Inf Process Syst – ident: ref25 doi: 10.1007/s00500-013-1179-3 – year: 1997 ident: ref58 publication-title: A Course in Fuzzy Systems and Control – ident: ref34 doi: 10.1007/s00500-018-3111-3 – ident: ref36 doi: 10.1109/TFUZZ.2017.2698399 – ident: ref57 doi: 10.1109/TFUZZ.2014.2346244 – ident: ref41 doi: 10.1109/TFUZZ.2003.819839 – ident: ref44 doi: 10.1007/BF00058655 – ident: ref12 doi: 10.1109/TFUZZ.2008.924343 – ident: ref16 doi: 10.1016/j.apm.2007.03.007 – ident: ref5 doi: 10.1016/j.smhl.2018.07.001 – year: 2001 ident: ref49 publication-title: A Non-Random Walk Down Wall Street – ident: ref9 doi: 10.1109/TFUZZ.2006.876365 – volume: 44 start-page: 8993 year: 2011 ident: ref28 article-title: A hierarchical fuzzy decision maker for the weapon target assignment publication-title: IFAC Proc Vol doi: 10.3182/20110828-6-IT-1002.00986 – ident: ref8 doi: 10.1109/91.797984 – volume: 521 start-page: 436 year: 2015 ident: ref3 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: ref61 doi: 10.1109/TFUZZ.2017.2701313 – ident: ref17 doi: 10.1109/FUZZY.2010.5584851 – year: 2003 ident: ref53 publication-title: The Alchemy of Finance – ident: ref29 doi: 10.1109/ICCCYB.2009.5393940 – volume: 2a start-page: 327 year: 0 ident: ref52 article-title: Forecasting stock returns publication-title: Handbook of Economic Forecasting – ident: ref33 doi: 10.1109/IJCNN.2016.7727238 – ident: ref45 doi: 10.1023/A:1010933404324 – ident: ref2 doi: 10.1162/neco.2006.18.7.1527 – ident: ref59 doi: 10.1109/91.868953 – ident: ref22 doi: 10.1109/FUZZY.2010.5584496 – year: 2006 ident: ref56 publication-title: Irrational Exuberance – ident: ref50 doi: 10.1093/rfs/1.1.41 – year: 2005 ident: ref42 publication-title: The wisdom of crowds Why the many are smarter than the few – ident: ref55 doi: 10.1109/TFUZZ.2016.2574911 – volume: 529 start-page: 484 year: 2016 ident: ref4 article-title: Mastering the game of Go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – ident: ref27 doi: 10.1016/j.jsv.2004.11.030 |
| SSID | ssj0014518 |
| Score | 2.5896149 |
| Snippet | A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multilayer connection of many low-dimensional fuzzy systems, where the input... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1301 |
| SubjectTerms | Algorithms Computational modeling Datasets Deep learning Fuzzy sets Fuzzy systems hierarchical fuzzy systems Input variables Multilayers Prediction algorithms stock index prediction Stock market indexes Training Wang–Mendel (WM) method Windows |
| Title | Fast Training Algorithms for Deep Convolutional Fuzzy Systems With Application to Stock Index Prediction |
| URI | https://ieeexplore.ieee.org/document/8788632 https://www.proquest.com/docview/2419498337 |
| Volume | 28 |
| WOSCitedRecordID | wos000545205300011&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: 1941-0034 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014518 issn: 1063-6706 databaseCode: RIE dateStart: 19930101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT9swFH8CxGEcKNBNlC_5sNsWSOIkto8VEDFpQkgrW8Uliu1nQIIGtSkS_euxXbcb2jSJWyQ_R5F_z-8j7wvgc2zQGGOZl2OdRlmKLJKJVlFmEmaktou-PPrnd3Z5yYdDcbUCX5e1MIjok8_w2D36WL5u1NT9Kjvh1l8rqBW4q4yxea3WMmKQ5cm87K2gUcHiYlEgE4uTQXl9c-OyuMSxVW6OZd8oIT9V5S9R7PVL2Xnfl23BZrAjSX8O_Das4GgHOosZDSRc2R3Y-KPhYBfuynrSkkEYC0H6D7fN-L69e5wQa7uSM8QnctqMngM72veX09nshYS25uSXpSX93yFv0jbkR2slKvnmmi6Sq7EL-7iVj3Bdng9OL6IwayFSlIo2Qk2NTnTGmJXEacGVRFEwzd1RqjiWplB1gty6ixmtrVWmUrS2Cs9rtCYlTST9BGujZoS7QKyPJHmucsmNzFgta5kpoWITixq1zmUPksXhVyo0InfzMB4q75DEovKAVQ6wKgDWgy_LPU_zNhz_pe46iJaUAZ0eHCwwrsJNnVTWghGZ4JSyvX_v2ocPqfOxfYruAay14ykewrp6bu8n4yPPhK9iEtzL |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NTxQxFH8hSKIeREDiKmoP3HRgZtqZtscNOoG4bkhYlHCZTNtXIcEdsjtLIn-9bbe7YiAm3Cbp62TS3-v7mPcFsJtatNY65hXY5AnLkScqMzphNuNWGbcYyqO_D_hwKM7O5PEKfFrWwiBiSD7DPf8YYvmm1TP_q2xfOH-tpE7gPikYy7N5tdYyZsCKbF74VtKk5Gm5KJFJ5f6oOj0_93lccs-pN8-0_6ihMFflnjAOGqZaf9y3vYQX0ZIk_Tn0G7CC401YX0xpIPHSbsLzOy0Ht-CiaqYdGcXBEKR_9bOdXHYXv6bEWa_kM-I1OWjHN5Eh3fur2e3tbxIbm5Mfjpb0_wa9SdeSk87JVHLk2y6S44kP_PiVV3BafRkdHCZx2kKiKZVdgoZakxnGuZPFeSm0QllyI_xR6jRVttRNhsI5jIw2zi7TOTprRRQNOqOSZopuw-q4HeNrIM5LUqLQhRJWMd6oRjEtdWpT2aAxhepBtjj8WsdW5H4ixlUdXJJU1gGw2gNWR8B68HG553reiOO_1FseoiVlRKcHOwuM63hXp7WzYSSTglL-5uFdH-Dp4ejboB4cDb--hWe597hDwu4OrHaTGb6DNX3TXU4n7wND_gEDY-AS |
| 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=Fast+Training+Algorithms+for+Deep+Convolutional+Fuzzy+Systems+With+Application+to+Stock+Index+Prediction&rft.jtitle=IEEE+transactions+on+fuzzy+systems&rft.au=Li-Xin%2C+Wang&rft.date=2020-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1063-6706&rft.eissn=1941-0034&rft.volume=28&rft.issue=7&rft.spage=1301&rft_id=info:doi/10.1109%2FTFUZZ.2019.2930488&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6706&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6706&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6706&client=summon |