Continuous Latent Adversarial Autoencoder: A Time-Sensitive Method for Incomplete Time-Series Modeling

Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, mo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE internet of things journal Ročník 12; číslo 7; s. 8552 - 8569
Hlavní autoři:	Chang, Zhuoqing, Liu, Shubo, Cai, Zhaohui, Tu, Guoqing
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.04.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Accuracy Adversarial autoencoder (AAE) adversarial training Analytical models Automation Coders Data models Decoding Differential equations Imputation incomplete time series Internet of Things Long short term memory Mathematical models Missing data Modelling Neural networks ordinary differential equation (ODE) Ordinary differential equations probabilistic forecasting Time series Time series analysis Training
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	Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, most existing methods that directly model incomplete time series often fail to infer values at any desired time or support multistep prediction. To address these issues, this article introduces a novel generative model called the continuous latent adversarial autoencoder (CLAAE) for directly modeling incomplete time series. CLAAE can effectively impute missing data of any time point and support multistep prediction. Specifically, CLAAE devises a time-aware long short-term memory (LSTM) encoder to extract temporal and sequential characteristics. The decoder is built upon the augmented neural ordinary differential equation (ANODE), allowing it to infer the probability of missing data across an arbitrary continuous-time horizon. To guarantee the meaningfulness of samples generated from any region within the prior space, a fully connected neural network is utilized as a discriminator, encouraging the aggregated posterior learned by the encoder to be indistinguishable from a selected prior distribution. Extensive experimental results across simulations and real-world datasets demonstrate that CLAAE outperforms baseline methods, especially when the amount of missing data is overwhelming. By combining the autoencoder and adversarial training, CLAAE can significantly enhance the quality of the synthetic samples, respecting the original feature distributions and the temporal dynamics.
AbstractList	Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical data. However, integrating data preprocessing and subsequent analysis within a model can amplify the errors from processed values. Moreover, most existing methods that directly model incomplete time series often fail to infer values at any desired time or support multistep prediction. To address these issues, this article introduces a novel generative model called the continuous latent adversarial autoencoder (CLAAE) for directly modeling incomplete time series. CLAAE can effectively impute missing data of any time point and support multistep prediction. Specifically, CLAAE devises a time-aware long short-term memory (LSTM) encoder to extract temporal and sequential characteristics. The decoder is built upon the augmented neural ordinary differential equation (ANODE), allowing it to infer the probability of missing data across an arbitrary continuous-time horizon. To guarantee the meaningfulness of samples generated from any region within the prior space, a fully connected neural network is utilized as a discriminator, encouraging the aggregated posterior learned by the encoder to be indistinguishable from a selected prior distribution. Extensive experimental results across simulations and real-world datasets demonstrate that CLAAE outperforms baseline methods, especially when the amount of missing data is overwhelming. By combining the autoencoder and adversarial training, CLAAE can significantly enhance the quality of the synthetic samples, respecting the original feature distributions and the temporal dynamics.
Author	Cai, Zhaohui Liu, Shubo Tu, Guoqing Chang, Zhuoqing
Author_xml	– sequence: 1 givenname: Zhuoqing orcidid: 0000-0003-2391-7957 surname: Chang fullname: Chang, Zhuoqing email: changzhuoqing@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 2 givenname: Shubo orcidid: 0000-0003-0694-0856 surname: Liu fullname: Liu, Shubo email: liu.shubo@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 3 givenname: Zhaohui orcidid: 0000-0002-3263-1822 surname: Cai fullname: Cai, Zhaohui email: zhcai@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan, China – sequence: 4 givenname: Guoqing orcidid: 0000-0003-4748-4367 surname: Tu fullname: Tu, Guoqing email: tugq2000@163.com organization: School of Cyber Science and Engineering, Wuhan University, Wuhan, China
BookMark	eNpNkE1LAzEQhoMoWGt_gOAh4HlrPnazu96W4kelpQfreUmTiaa0SU2yBf-9W1qhpxmG550Xnht06bwDhO4oGVNK6sf36WI5ZoTlY14QyktxgQaMszLLhWCXZ_s1GsW4JoT0sYLWYoDMxLtkXee7iGcygUu40XsIUQYrN7jpkgenvIbwhBu8tFvIPsBFm-we8BzSt9fY-ICnPbTdbSDBPxQsRDzvkxvrvm7RlZGbCKPTHKLPl-fl5C2bLV6nk2aWKU6rlJW5llrXXDKjuZGMqXzFVFUJzaUxRbUiqhba1IRwXSnCoZYKZC1FsVIG-usQPRz_7oL_6SCmdu274PrKti-geZlXtegpeqRU8DEGMO0u2K0Mvy0l7cFoezDaHoy2J6N95v6YsQBwxpeFKHLB_wAd13Vz
CODEN	IITJAU
Cites_doi	10.1109/TCYB.2019.2923434 10.2307/2335739 10.1007/978-3-031-44192-9_2 10.1609/aaai.v35i10.17086 10.1016/j.patcog.2017.08.016 10.1109/ICCVW.2019.00075 10.1109/CVPRW56347.2022.00218 10.24963/ijcai.2019/607 10.24963/ijcai.2019/429 10.1016/j.patcog.2019.106973 10.1016/j.rse.2007.10.009 10.1109/MSP.2017.2765202 10.1016/j.trc.2016.09.015 10.1109/LSP.2022.3224880 10.1109/TNNLS.2015.2480959 10.1109/TKDE.2022.3167536 10.1016/j.neucom.2016.04.015 10.1016/j.asoc.2016.05.044 10.1145/3097983.3097997 10.1109/JIOT.2024.3358871 10.1016/j.neucom.2019.07.066 10.1146/annurev.psych.58.110405.085530 10.1109/BIBM47256.2019.8982996 10.48550/arXiv.1312.6114 10.1016/j.neucom.2019.06.007 10.1609/aaai.v37i9.26317 10.1016/j.ins.2008.07.024 10.1145/3447548.3467385 10.1007/s10618-022-00903-7 10.1609/aaai.v34i04.6056 10.1016/j.patcog.2020.107501 10.1109/TNNLS.2021.3114203 10.20470/jsi.v5i1.178 10.1126/science.1127647 10.1109/TPAMI.2020.3027975 10.1109/TCYB.2016.2561974 10.1038/s41598-018-24271-9
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1109/JIOT.2024.3501376
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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2327-4662
EndPage	8569
ExternalDocumentID	10_1109_JIOT_2024_3501376 10756546
Genre	orig-research
GrantInformation_xml	– fundername: Major Projects of Technical Innovation of Hubei Province grantid: 2018AAA046
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-c318t-74dadd93a2fd3fa22c4b2c886d3aff58b0c96df9003d8c03e9acea9a65bcfe003
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001453255300007&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 07:48:28 EDT 2025 Sat Nov 29 08:06:35 EST 2025 Wed Aug 27 01:37:52 EDT 2025
IsPeerReviewed	false
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-c318t-74dadd93a2fd3fa22c4b2c886d3aff58b0c96df9003d8c03e9acea9a65bcfe003
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3263-1822 0000-0003-4748-4367 0000-0003-0694-0856 0000-0003-2391-7957
PQID	3181474896
PQPubID	2040421
PageCount	18
ParticipantIDs	proquest_journals_3181474896 crossref_primary_10_1109_JIOT_2024_3501376 ieee_primary_10756546
PublicationCentury	2000
PublicationDate	2025-04-01
PublicationDateYYYYMMDD	2025-04-01
PublicationDate_xml	– month: 04 year: 2025 text: 2025-04-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE internet of things journal
PublicationTitleAbbrev	JIoT
PublicationYear	2025
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 ref15 ref58 ref53 ref52 ref55 ref10 Cao (ref17); 31 Gupta (ref18) 2020 ref19 Alcaraz (ref59) 2023 Makhzani (ref23) 2015 Huang (ref42); 33 ref51 Silva (ref56) ref46 ref45 ref48 ref47 ref41 Chen (ref20); 31 ref44 ref43 Hastie (ref12) 2015; 16 Bengio (ref9); 8 ref8 ref7 Box (ref11) 2015 ref4 Dupont (ref40); 32 ref3 ref6 Li (ref13) 2019 ref5 Zhao (ref22) Pidhorskyi (ref50); 31 Rubanova (ref21); 32 ref35 ref34 Yoon (ref36) ref31 ref30 ref32 Gondara (ref33) 2017 ref2 ref1 ref38 Galbraith (ref28) 2001 Fortuin (ref39) ref24 Luo (ref37); 31 ref26 Schreyer (ref49) 2019 ref25 ref27 Choi (ref16) Lipton (ref14) ref29 ref60 ref61 Adler (ref54); 31
References_xml	– volume: 33 start-page: 16177 volume-title: Proc. 34th Conf. Neural Inf. Process. Syst. ident: ref42 article-title: Learning continuous system dynamics from irregularly-sampled partial observations – volume: 16 start-page: 3367 issue: 1 year: 2015 ident: ref12 article-title: Matrix completion and low-rank SVD via fast alternating least squares publication-title: J. Mach. Learn. Res. – ident: ref30 doi: 10.1109/TCYB.2019.2923434 – ident: ref7 doi: 10.2307/2335739 – ident: ref57 doi: 10.1007/978-3-031-44192-9_2 – ident: ref19 doi: 10.1609/aaai.v35i10.17086 – ident: ref51 doi: 10.1016/j.patcog.2017.08.016 – ident: ref45 doi: 10.1109/ICCVW.2019.00075 – ident: ref48 doi: 10.1109/CVPRW56347.2022.00218 – ident: ref55 doi: 10.24963/ijcai.2019/607 – ident: ref1 doi: 10.24963/ijcai.2019/429 – ident: ref52 doi: 10.1016/j.patcog.2019.106973 – volume-title: Time Series Analysis: Forecasting and Control year: 2015 ident: ref11 – ident: ref10 doi: 10.1016/j.rse.2007.10.009 – start-page: 1651 volume-title: Proc. Int. Conf. Artif. Intell. Statist. ident: ref39 article-title: GP-VAE: Deep probabilistic time series imputation – ident: ref46 doi: 10.1109/MSP.2017.2765202 – ident: ref35 doi: 10.1016/j.trc.2016.09.015 – year: 2019 ident: ref49 article-title: Detection of accounting anomalies in the latent space using adversarial autoencoder neural networks publication-title: arXiv:1908.00734 – ident: ref60 doi: 10.1109/LSP.2022.3224880 – year: 2015 ident: ref23 article-title: Adversarial autoencoders publication-title: arXiv:1511.05644 – volume: 31 start-page: 1 volume-title: Proc. 32nd Conf. Neural Inf. Process. Syst. ident: ref54 article-title: Banach Wasserstein GAN – ident: ref5 doi: 10.1109/TNNLS.2015.2480959 – ident: ref41 doi: 10.1109/TKDE.2022.3167536 – ident: ref27 doi: 10.1016/j.neucom.2016.04.015 – ident: ref26 doi: 10.1016/j.asoc.2016.05.044 – year: 2017 ident: ref33 article-title: Multiple imputation using deep denoising autoencoders publication-title: arXiv:1705.02737 – ident: ref31 doi: 10.1145/3097983.3097997 – volume: 32 start-page: 1 volume-title: Proc. 33rd Conf. Neural Inf. Process. Syst. ident: ref40 article-title: Augmented neural odes – volume: 31 start-page: 1 volume-title: Proc. 32nd Conf. Neural Inf. Process. Syst. ident: ref20 article-title: Neural ordinary differential equations – volume: 31 start-page: 1 volume-title: Proc. 32nd Conf. Neural Inf. Process. Syst. ident: ref50 article-title: Generative probabilistic novelty detection with adversarial autoencoders – ident: ref2 doi: 10.1109/JIOT.2024.3358871 – volume: 8 start-page: 1 volume-title: Proc. Neural Inf. Process. Syst. ident: ref9 article-title: Recurrent neural networks for missing or asynchronous data – volume: 31 start-page: 1603 volume-title: Proc. 32nd Int Conf. Neural Inf. Process. Syst. ident: ref37 article-title: Multivariate time series imputation with generative adversarial networks – year: 2020 ident: ref18 article-title: Time-series imputation and prediction with bi-directional generative adversarial networks publication-title: arXiv:2009.08900 – ident: ref32 doi: 10.1016/j.neucom.2019.07.066 – start-page: 301 volume-title: Proc. Mach. Learn. Healthcare Conf. ident: ref16 article-title: Doctor AI: Predicting clinical events via recurrent neural networks – year: 2019 ident: ref13 article-title: MisGAN: Learning from incomplete data with generative adversarial networks publication-title: arXiv:1902.09599 – start-page: 245 volume-title: Proc. Comput. Cardiol. ident: ref56 article-title: Predicting in-hospital mortality of ICU patients: The PhysioNet/computing in cardiology challenge 2012 – ident: ref24 doi: 10.1146/annurev.psych.58.110405.085530 – ident: ref34 doi: 10.1109/BIBM47256.2019.8982996 – volume: 31 start-page: 6776 volume-title: Proc. 32nd Int. Conf. Neural Inf. Process. Syst. ident: ref17 article-title: BRITS: Bidirectional recurrent imputation for time series – ident: ref61 doi: 10.48550/arXiv.1312.6114 – volume: 32 start-page: 1 volume-title: Proc. 33rd Conf. Neural Inf. Process. Syst. ident: ref21 article-title: Latent ODEs for irregularly-sampled time series – ident: ref53 doi: 10.1016/j.neucom.2019.06.007 – ident: ref58 doi: 10.1609/aaai.v37i9.26317 – ident: ref29 doi: 10.1016/j.ins.2008.07.024 – start-page: 5902 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref22 article-title: Adversarially regularized autoencoders – ident: ref43 doi: 10.1145/3447548.3467385 – ident: ref3 doi: 10.1007/s10618-022-00903-7 – year: 2023 ident: ref59 article-title: Diffusion-based time series imputation and forecasting with structured state space models publication-title: Trans. Mach. Learn. Res. – ident: ref4 doi: 10.1609/aaai.v34i04.6056 – ident: ref38 doi: 10.1016/j.patcog.2020.107501 – volume-title: Autoregression-Based Estimators for ARFIMA Models year: 2001 ident: ref28 – ident: ref47 doi: 10.1109/TNNLS.2021.3114203 – start-page: 5689 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref36 article-title: Gain: Missing data imputation using generative adversarial nets – ident: ref25 doi: 10.20470/jsi.v5i1.178 – start-page: 253 volume-title: Proc. Mach. Learn. Healthcare Conf. ident: ref14 article-title: Directly modeling missing data in sequences with RNNs: Improved classification of clinical time series – ident: ref44 doi: 10.1126/science.1127647 – ident: ref8 doi: 10.1109/TPAMI.2020.3027975 – ident: ref6 doi: 10.1109/TCYB.2016.2561974 – ident: ref15 doi: 10.1038/s41598-018-24271-9
SSID	ssj0001105196
Score	2.3364637
Snippet	Incomplete time-series modeling is an unavoidable topic in real-world time-series analysis because of the frequent occurrence of missing values in practical...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	8552
SubjectTerms	Accuracy Adversarial autoencoder (AAE) adversarial training Analytical models Automation Coders Data models Decoding Differential equations Imputation incomplete time series Internet of Things Long short term memory Mathematical models Missing data Modelling Neural networks ordinary differential equation (ODE) Ordinary differential equations probabilistic forecasting Time series Time series analysis Training
Title	Continuous Latent Adversarial Autoencoder: A Time-Sensitive Method for Incomplete Time-Series Modeling
URI	https://ieeexplore.ieee.org/document/10756546 https://www.proquest.com/docview/3181474896
Volume	12
WOSCitedRecordID	wos001453255300007&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: 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/eLvHCXMwlV3fS8MwED7c8MEX54-J0yl58EnobJs0bXwb4lCZU3DK3kqapLCXTrbWv99c2uJAfPCtlATaXO5yl7v7PoCrKJRxYILMo8qGqwh_4iXcKI8rmeTM2EPCAWl_TOPZLFksxGvTrO56YYwxrvjMjPDR5fL1SlV4VWY1PI6w-aYDnTjmdbPWz4VKgN4IbzKXgS9unh5f5jYCDNkIs2cUYUW2zh5HpvLLArtjZdL75wcdwH7jP5JxLfBD2DHFEfRabgbSqOox5Ag7tSwqG9iTqfUni5I47uWNxB1HxlW5QghLbda3ZEywEcR7w1p2tH7k2dFKE-vPEms_sOjcutbtIIytCVKoYSN7H94n9_O7B6_hVPCU1d7Si5m2Fk1QGeaa5jIMFctClSRcU5nnUZL5SnCd4_2mTpRPjZDKSCF5lKnc2Lcn0C1WhTkF4mdUyEAyG5NQZjgTmYy4sO6RpJpmOh7Adbva6WcNnZG6kMMXKYomRdGkjWgG0Mfl3RpYr-wAhq2A0ka7Nqn9k4AhbA4_-2PaOeyFSNTrSmyG0C3XlbmAXfVVLjfrS7dxvgGHs8PZ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED50Cvri_DFxOjUPPgmdbdOmjW9DHJt2U3DK3kqapLCXTrbWv99c1uFAfPCtlATaXO5yl7v7PoCb0BeRp73ModKEqwh_4sRMS4dJEeeBNoeEBdL-SKLxOJ5O-WvdrG57YbTWtvhMd_HR5vLVXFZ4VWY0PAqx-WYbdpA6q27X-rlS8dAfYXXu0nP53dPwZWJiQD_oYv6MIrDIxulj6VR-2WB7sPSb__ykQzioPUjSW4n8CLZ0cQzNNTsDqZX1BHIEnpoVlQntSWI8yqIkln15KXDPkV5VzhHEUunFPekRbAVx3rCaHe0fGVliaWI8WmIsCJadG-d6PQija4IkatjK3oL3_uPkYeDUrAqONPpbOlGgjE3jVPi5ornwfRlkvoxjpqjI8zDOXMmZyvGGU8XSpZoLqQUXLMxkrs3bU2gU80KfAXEzyoUnAhOV0ECzgGciZNw4SIIqmqmoDbfr1U4_V-AZqQ06XJ6iaFIUTVqLpg0tXN6NgauVbUNnLaC01q9lav7ECxA4h53_Me0a9gaTUZImw_HzBez7SNtrC2460CgXlb6EXflVzpaLK7uJvgHjtcci
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=Continuous+Latent+Adversarial+Autoencoder%3A+A+Time-Sensitive+Method+for+Incomplete+Time-Series+Modeling&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Chang%2C+Zhuoqing&rft.au=Liu%2C+Shubo&rft.au=Cai%2C+Zhaohui&rft.au=Tu%2C+Guoqing&rft.date=2025-04-01&rft.issn=2327-4662&rft.eissn=2327-4662&rft.volume=12&rft.issue=7&rft.spage=8552&rft.epage=8569&rft_id=info:doi/10.1109%2FJIOT.2024.3501376&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JIOT_2024_3501376
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