Deep Learning-Based Auto-Encoder for Time-Offset Sub-Faster-Than-Nyquist Downlink NOMA With Timing Errors and Imperfect CSI
This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink time-offset sub-faster-than-Nyquist non-orthogonal multiple access signaling (TO-sFTN-NOMA). A conventional singular value decomposition (SVD)-based s...
Uloženo v:
| Vydáno v: | IEEE journal of selected topics in signal processing Ročník 18; číslo 7; s. 1178 - 1193 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
New York
IEEE
01.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1932-4553, 1941-0484 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink time-offset sub-faster-than-Nyquist non-orthogonal multiple access signaling (TO-sFTN-NOMA). A conventional singular value decomposition (SVD)-based scheme for TO-sFTN-NOMA is employed as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER) performance. Moreover, the SVD scheme is sensitive to timing offset errors, and its complexity increases quadratically with the sequence length. To overcome these limitations and improve the TO-sFTN-NOMA's performance, we propose a convolutional neural network (CNN) auto-encoder (AE) technique for encoding and decoding with linear time complexity. We explain the design of the encoder and decoder architectures and the training criteria. By considering several variants of the proposed CNN AE, we show that the proposed CNN AE can achieve an excellent trade-off between performance and complexity. The proposed CNN AE surpasses the SVD method by approximately 10 dB in a TO-sFTN-NOMA system with no timing offset errors and no channel state information (CSI) estimation errors. In the presence of CSI error with variance of 1<inline-formula><tex-math notation="LaTeX">\%</tex-math></inline-formula> and uniform timing error at <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula>4% of the symbol interval, the proposed CNN AE provides up to 16 dB SNR gain over the SVD method. We also propose a novel modified training objective function consisting of a weighted summation of the cross-entropy (CE) loss and a Q-function metric related to the BER. Simulations show that the modified objective loss function achieves SNR gains of up to 1 dB over the CE loss function alone. |
|---|---|
| AbstractList | This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink time-offset sub-faster-than-Nyquist non-orthogonal multiple access signaling (TO-sFTN-NOMA). A conventional singular value decomposition (SVD)-based scheme for TO-sFTN-NOMA is employed as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER) performance. Moreover, the SVD scheme is sensitive to timing offset errors, and its complexity increases quadratically with the sequence length. To overcome these limitations and improve the TO-sFTN-NOMA's performance, we propose a convolutional neural network (CNN) auto-encoder (AE) technique for encoding and decoding with linear time complexity. We explain the design of the encoder and decoder architectures and the training criteria. By considering several variants of the proposed CNN AE, we show that the proposed CNN AE can achieve an excellent trade-off between performance and complexity. The proposed CNN AE surpasses the SVD method by approximately 10 dB in a TO-sFTN-NOMA system with no timing offset errors and no channel state information (CSI) estimation errors. In the presence of CSI error with variance of 1<inline-formula><tex-math notation="LaTeX">\%</tex-math></inline-formula> and uniform timing error at <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula>4% of the symbol interval, the proposed CNN AE provides up to 16 dB SNR gain over the SVD method. We also propose a novel modified training objective function consisting of a weighted summation of the cross-entropy (CE) loss and a Q-function metric related to the BER. Simulations show that the modified objective loss function achieves SNR gains of up to 1 dB over the CE loss function alone. This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink time-offset sub-faster-than-Nyquist non-orthogonal multiple access signaling (TO-sFTN-NOMA). A conventional singular value decomposition (SVD)-based scheme for TO-sFTN-NOMA is employed as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER) performance. Moreover, the SVD scheme is sensitive to timing offset errors, and its complexity increases quadratically with the sequence length. To overcome these limitations and improve the TO-sFTN-NOMA's performance, we propose a convolutional neural network (CNN) auto-encoder (AE) technique for encoding and decoding with linear time complexity. We explain the design of the encoder and decoder architectures and the training criteria. By considering several variants of the proposed CNN AE, we show that the proposed CNN AE can achieve an excellent trade-off between performance and complexity. The proposed CNN AE surpasses the SVD method by approximately 10 dB in a TO-sFTN-NOMA system with no timing offset errors and no channel state information (CSI) estimation errors. In the presence of CSI error with variance of 1[Formula Omitted] and uniform timing error at [Formula Omitted]4% of the symbol interval, the proposed CNN AE provides up to 16 dB SNR gain over the SVD method. We also propose a novel modified training objective function consisting of a weighted summation of the cross-entropy (CE) loss and a Q-function metric related to the BER. Simulations show that the modified objective loss function achieves SNR gains of up to 1 dB over the CE loss function alone. |
| Author | Sivakumar, Krishnamoorthy Torabi, Mohammad Belzer, Benjamin Aboutaleb, Ahmed |
| Author_xml | – sequence: 1 givenname: Ahmed orcidid: 0000-0003-0791-7762 surname: Aboutaleb fullname: Aboutaleb, Ahmed organization: Marvell Technology Inc., Santa Clara, CA, USA – sequence: 2 givenname: Mohammad surname: Torabi fullname: Torabi, Mohammad organization: School of EECS, Washington State University, Pullman, WA, USA – sequence: 3 givenname: Benjamin orcidid: 0000-0001-9419-9281 surname: Belzer fullname: Belzer, Benjamin email: belzer@wsu.edu organization: School of EECS, Washington State University, Pullman, WA, USA – sequence: 4 givenname: Krishnamoorthy orcidid: 0000-0002-4026-7768 surname: Sivakumar fullname: Sivakumar, Krishnamoorthy organization: School of EECS, Washington State University, Pullman, WA, USA |
| BookMark | eNpNkLFOwzAQhi0EEhR4AcRgidnFjp04HktpoahQpBYxRo5zhkBrt3YiVPHyNJSB6W74v_90Xw8dOu8AoQtG-4xRdf0wX8yf-wlNRJ-LVFImDtAJU4IRKnJx2O08ISJN-THqxfhBaSozJk7Q9y3AGk9BB1e7N3KjI1R40DaejJzxFQRsfcCLegVkZm2EBs_bkox1bCCQxbt25Gm7aevY4Fv_5Za1-8RPs8cBfq2b9w7bleJRCD5ErF2FJ6s1BAumwcP55AwdWb2McP43T9HLeLQY3pPp7G4yHEyJSYRsCLOlMKAoq1RSSZobqm1pSqFz4FIom1MmpRGKGilsKri0eQZJlRmelt2X_BRd7XvXwW9aiE3x4dvgdicLztKcqTzn2S6V7FMm-BgD2GId6pUO24LRopNc_EouOsnFn-QddLmHagD4B2RS0VTxH62XeeI |
| CODEN | IJSTGY |
| Cites_doi | 10.1109/LWC.2022.3164979 10.1109/TCCN.2021.3130308 10.1109/GLOCOMW.2018.8644090 10.1109/WCNC.2019.8886124 10.1109/JIOT.2021.3051603 10.1109/LCOMM.2015.2424423 10.1109/GLOBECOM48099.2022.10001617 10.1109/jstsp.2024.3457014 10.1007/978-3-319-92090-0_5 10.1109/TCCN.2017.2758370 10.1109/JRPROC.1959.287136 10.1109/JPROC.2012.2233451 10.1109/JSYST.2019.2937463 10.1109/ISPACS.2013.6704653 10.1109/LSP.2020.3005051 10.1109/MWC.2019.1800598 10.1109/VTCSpring.2013.6692652 10.1109/TWC.2019.2963185 10.1109/ICCV.2019.00140 10.1115/1.3138251 10.1109/LCOMM.2016.2619339 10.1002/047174882X 10.1109/LCOMM.2023.3338475 10.1109/JSAC.2017.2725519 10.1109/WCNC55385.2023.10118621 10.5555/3045118.3045167 10.1109/LWC.2020.3026700 10.1109/TWC.2021.3058405 10.1109/LWC.2022.3163810 10.1109/TVT.2017.2689000 10.1109/TVT.2022.3193201 10.1109/LCOMM.2023.3260881 10.1109/LCOMM.2020.3038951 10.1007/978-3-319-92090-0 10.1002/aic.690370209 10.1109/ICC45855.2022.9838265 10.1109/SARNOF.2006.4534773 10.1109/QBSC.2012.6221379 10.1109/TVT.2018.2848294 10.1109/JSTSP.2019.2899731 10.1109/MCOM.2017.1601065 10.1109/TCOMM.2016.2521821 |
| 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 7SP 8FD H8D L7M |
| DOI | 10.1109/JSTSP.2024.3457014 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Aerospace Database Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Aerospace Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Architecture |
| EISSN | 1941-0484 |
| EndPage | 1193 |
| ExternalDocumentID | 10_1109_JSTSP_2024_3457014 10679059 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Science Foundation; US NSF grantid: CCF-1817083 funderid: 10.13039/100000001 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL RIA RIE RNS AAYXX CITATION 7SP 8FD H8D L7M |
| ID | FETCH-LOGICAL-c247t-1fb4ce901d92d708c0afbcb4a8e3749f80177c490c74f5437f86e2d6c35b57613 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001403223000016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1932-4553 |
| IngestDate | Tue Jul 22 18:40:47 EDT 2025 Sat Nov 29 04:10:35 EST 2025 Wed Aug 27 01:53:40 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| 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-c247t-1fb4ce901d92d708c0afbcb4a8e3749f80177c490c74f5437f86e2d6c35b57613 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-4026-7768 0000-0003-0791-7762 0000-0001-9419-9281 |
| PQID | 3158198836 |
| PQPubID | 75721 |
| PageCount | 16 |
| ParticipantIDs | crossref_primary_10_1109_JSTSP_2024_3457014 ieee_primary_10679059 proquest_journals_3158198836 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-01 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE journal of selected topics in signal processing |
| PublicationTitleAbbrev | JSTSP |
| 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 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref16 ref38 ref19 ref18 Proakis (ref46) 2007 ref24 ref23 ref45 ref26 Menon (ref39) 2019; 32 ref25 ref47 ref20 Klambauer (ref35) 2017 ref41 ref22 ref44 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 Kingma (ref42) 2015 ref5 ref40 Bergstra (ref43) 2013 |
| References_xml | – ident: ref30 doi: 10.1109/LWC.2022.3164979 – ident: ref31 doi: 10.1109/TCCN.2021.3130308 – ident: ref26 doi: 10.1109/GLOCOMW.2018.8644090 – ident: ref11 doi: 10.1109/WCNC.2019.8886124 – volume-title: Digital Communications year: 2007 ident: ref46 – volume: 32 start-page: 10600 year: 2019 ident: ref39 article-title: Multilabel reductions: What is my loss optimising? publication-title: Adv. Neural Inf. Process. Syst. – ident: ref16 doi: 10.1109/JIOT.2021.3051603 – ident: ref40 doi: 10.1109/LCOMM.2015.2424423 – ident: ref19 doi: 10.1109/GLOBECOM48099.2022.10001617 – ident: ref34 doi: 10.1109/jstsp.2024.3457014 – ident: ref3 doi: 10.1007/978-3-319-92090-0_5 – ident: ref21 doi: 10.1109/TCCN.2017.2758370 – ident: ref37 doi: 10.1109/JRPROC.1959.287136 – ident: ref9 doi: 10.1109/JPROC.2012.2233451 – ident: ref25 doi: 10.1109/JSYST.2019.2937463 – ident: ref12 doi: 10.1109/ISPACS.2013.6704653 – ident: ref44 doi: 10.1109/LSP.2020.3005051 – ident: ref14 doi: 10.1109/MWC.2019.1800598 – ident: ref1 doi: 10.1109/VTCSpring.2013.6692652 – ident: ref27 doi: 10.1109/TWC.2019.2963185 – ident: ref38 doi: 10.1109/ICCV.2019.00140 – ident: ref47 doi: 10.1115/1.3138251 – ident: ref18 doi: 10.1109/LCOMM.2016.2619339 – ident: ref10 doi: 10.1002/047174882X – ident: ref32 doi: 10.1109/LCOMM.2023.3338475 – ident: ref7 doi: 10.1109/JSAC.2017.2725519 – ident: ref33 doi: 10.1109/WCNC55385.2023.10118621 – ident: ref36 doi: 10.5555/3045118.3045167 – ident: ref15 doi: 10.1109/LWC.2020.3026700 – ident: ref17 doi: 10.1109/TWC.2021.3058405 – ident: ref28 doi: 10.1109/LWC.2022.3163810 – start-page: 115 volume-title: Proc. 30th Int. Conf. Mach. Learn. year: 2013 ident: ref43 article-title: Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures – start-page: 971 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2017 ident: ref35 article-title: Self-normalizing neural networks – ident: ref45 doi: 10.1109/TVT.2017.2689000 – ident: ref23 doi: 10.1109/TVT.2022.3193201 – ident: ref29 doi: 10.1109/LCOMM.2023.3260881 – ident: ref41 doi: 10.1109/LCOMM.2020.3038951 – start-page: 1 volume-title: Proc. 3rd Int. Conf. Learn. Representations year: 2015 ident: ref42 article-title: Adam: A method for stochastic optimization – ident: ref4 doi: 10.1007/978-3-319-92090-0 – ident: ref20 doi: 10.1002/aic.690370209 – ident: ref22 doi: 10.1109/ICC45855.2022.9838265 – ident: ref5 doi: 10.1109/SARNOF.2006.4534773 – ident: ref8 doi: 10.1109/QBSC.2012.6221379 – ident: ref24 doi: 10.1109/TVT.2018.2848294 – ident: ref13 doi: 10.1109/JSTSP.2019.2899731 – ident: ref2 doi: 10.1109/MCOM.2017.1601065 – ident: ref6 doi: 10.1109/TCOMM.2016.2521821 |
| SSID | ssj0057614 |
| Score | 2.4181 |
| Snippet | This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 1178 |
| SubjectTerms | Architecture Artificial neural networks Asynchronous transmission auto-encoder Autoencoders Bit error rate Coders Coding Complexity Convolutional neural networks Decoding Deep learning Downlink Downlinking faster-than Nyquist signaling Interference cancellation Machine learning Neural networks NOMA non-orthogonal multiple access Nonorthogonal multiple access Performance evaluation Singular value decomposition Symbols Timing |
| Title | Deep Learning-Based Auto-Encoder for Time-Offset Sub-Faster-Than-Nyquist Downlink NOMA With Timing Errors and Imperfect CSI |
| URI | https://ieeexplore.ieee.org/document/10679059 https://www.proquest.com/docview/3158198836 |
| Volume | 18 |
| WOSCitedRecordID | wos001403223000016&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: 1941-0484 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0057614 issn: 1932-4553 databaseCode: RIE dateStart: 20070101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELYAMcDAG1Fe8sCGDElsx_ZYoBWVoCDx3CLHD9olLWmKhPjz2E4qFSEGlihDbEV3l7vvcvedATjhUhKpqEBE5zkizFrEBdPuomzCZIJpOL7t-Yb1-_z1Vdw3ZPXAhTHGhOYzc-ZvQy1fj9TU_yo79-POhMMDi2CRsbQma83crsPNcVNCThChFM8YMpE4dzb-cO9ywYScYUJZFJMfUSgcq_LLF4cA013_56ttgLUGScJ2rfpNsGCKLbA6N19wG3xdGTOGzQjVN3ThIpaG7Wk1Qp3Cc9lL6CAr9CwQdGftxFTQ-RHUlX54AnocyAL1P9-nzhDglZ-p79JW2L-7bcOXYTXwy9ymsFOWo3ICZaFhz0Hw0reHwMuH3g546nYeL69Rc9oCUglhFYptTpRx8ECLRLOIq0jaXOVEcoMZEdaFMsYUEZFixFKCmeWpSXSqMM298PEuWCpGhdkDUBsH5CTVyjBOsE5lJKPExFT5sh-1tAVOZ9LPxvVQjSwkI5HIgq4yr6us0VUL7Hh5zz1Zi7oFDmcay5oPb5LhmDqMwzlO9_9YdgBW_O51Q94hWKrKqTkCy-qjGk7K42BT34OLyVw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BQQIOPItYKOADN-TW8WNtH5d2V12xTSt1gd4ix4-2l2zJZpEQfx7byUpFiAOXKIc4iWYmM99k5hsDfFDGcGOFxtzVNeYyBKy0dPFgA5WGMpG3b_u6kGWpLi702UBWz1wY731uPvP76TTX8t3KbtKvsoM07kxHPHAX7gnOKenpWlvHG5FzMRSRKeZCsC1HhuiDaOXnZzEbpHyfcSFJwf-IQ3ljlb-8cQ4xsyf_-XJP4fGAJdGkV_4zuOOb5_Do1oTBF_DryPsbNAxRvcSfYsxyaLLpVnjaJDZ7iyJoRYkHgk9DWPsORU-CZyaNT8DLK9Pg8uf3TTQFdJSm6sfEFZWnJxP07bq7SsviTdG0bVftGpnGoXkE4W1qEEGH5_Nd-DKbLg-P8bDfAraUyw4XoebWR4DgNHWSKEtMqG3NjfJMch1iMJPSck2s5EFwJoMae-rGlok6CZ-9hJ1m1fhXgJyPUM4IZ71UnLmxIYZQXwibCn8iiBF83Eq_uunHalQ5HSG6yrqqkq6qQVcj2E3yvnVlL-oR7G01Vg2f3rpihYgoRyk2fv2PZe_hwfHyZFEt5uXnN_AwPalvz9uDna7d-Ldw3_7ortftu2xfvwEoZMyj |
| 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=Deep+Learning-Based+Auto-Encoder+for+Time-Offset+Sub-Faster-Than-Nyquist+Downlink+NOMA+With+Timing+Errors+and+Imperfect+CSI&rft.jtitle=IEEE+journal+of+selected+topics+in+signal+processing&rft.au=Aboutaleb%2C+Ahmed&rft.au=Torabi%2C+Mohammad&rft.au=Belzer%2C+Benjamin&rft.au=Sivakumar%2C+Krishnamoorthy&rft.date=2024-10-01&rft.issn=1932-4553&rft.eissn=1941-0484&rft.volume=18&rft.issue=7&rft.spage=1178&rft.epage=1193&rft_id=info:doi/10.1109%2FJSTSP.2024.3457014&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSTSP_2024_3457014 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4553&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4553&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4553&client=summon |