Vector Quantized Variational Autoencoder-Based Compressive Sampling Method for Time Series in Structural Health Monitoring

The theory of compressive sampling (CS) has revolutionized data compression technology by capitalizing on the inherent sparsity of a signal to enable signal recovery from significantly far fewer samples than what is required by the Nyquist–Shannon sampling theorem. Recent advancement in deep generat...

Full description

Saved in:

Bibliographic Details
Published in:	Sustainability Vol. 15; no. 20; p. 14868
Main Authors:	Liang, Ge, Ji, Zhenglin, Zhong, Qunhong, Huang, Yong, Han, Kun
Format:	Journal Article
Language:	English
Published:	Basel MDPI AG 01.10.2023
Subjects:	Accuracy Big data Data compression Deep learning Inverse problems Methods Neural networks Parameter identification Signal processing Sparsity Sustainability Time series Wavelet transforms
ISSN:	2071-1050, 2071-1050
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The theory of compressive sampling (CS) has revolutionized data compression technology by capitalizing on the inherent sparsity of a signal to enable signal recovery from significantly far fewer samples than what is required by the Nyquist–Shannon sampling theorem. Recent advancement in deep generative models, which can represent high-dimension data in a low-dimension latent space efficiently when trained with big data, has been used to further reduce the sample size for image data compressive sampling. However, compressive sampling for 1D time series data has not significantly benefited from this technological progress. In this study, we investigate the application of different architectures of deep neural networks suitable for time series data compression and propose an efficient method to solve the compressive sampling problem on one-dimensional (1D) structural health monitoring (SHM) data, based on block CS and the vector quantized–variational autoencoder model with a naïve multitask paradigm (VQ-VAE-M). The proposed method utilizes VQ-VAE-M to learn the data characteristics of the signal, replaces the “hard constraint” of sparsity to realize the compressive sampling signal reconstruction and thereby does not need to select the appropriate sparse basis for the signal. A comparative analysis against various CS methods and other deep neural network models was performed in both synthetic data and real-world data from two real bridges in China. The results have demonstrated the superiority of the proposed method, with achieving the smallest reconstruction error of 0.038, 0.034 and 0.021, and the highest reconstruction accuracy of 0.882, 0.892 and 0.936 for compression ratios of 4.0, 2.66, and 2.0, respectively.
AbstractList	The theory of compressive sampling (CS) has revolutionized data compression technology by capitalizing on the inherent sparsity of a signal to enable signal recovery from significantly far fewer samples than what is required by the Nyquist–Shannon sampling theorem. Recent advancement in deep generative models, which can represent high-dimension data in a low-dimension latent space efficiently when trained with big data, has been used to further reduce the sample size for image data compressive sampling. However, compressive sampling for 1D time series data has not significantly benefited from this technological progress. In this study, we investigate the application of different architectures of deep neural networks suitable for time series data compression and propose an efficient method to solve the compressive sampling problem on one-dimensional (1D) structural health monitoring (SHM) data, based on block CS and the vector quantized–variational autoencoder model with a naïve multitask paradigm (VQ-VAE-M). The proposed method utilizes VQ-VAE-M to learn the data characteristics of the signal, replaces the “hard constraint” of sparsity to realize the compressive sampling signal reconstruction and thereby does not need to select the appropriate sparse basis for the signal. A comparative analysis against various CS methods and other deep neural network models was performed in both synthetic data and real-world data from two real bridges in China. The results have demonstrated the superiority of the proposed method, with achieving the smallest reconstruction error of 0.038, 0.034 and 0.021, and the highest reconstruction accuracy of 0.882, 0.892 and 0.936 for compression ratios of 4.0, 2.66, and 2.0, respectively.
Audience	Academic
Author	Liang, Ge Ji, Zhenglin Han, Kun Huang, Yong Zhong, Qunhong
Author_xml	– sequence: 1 givenname: Ge orcidid: 0009-0007-5555-3082 surname: Liang fullname: Liang, Ge – sequence: 2 givenname: Zhenglin surname: Ji fullname: Ji, Zhenglin – sequence: 3 givenname: Qunhong surname: Zhong fullname: Zhong, Qunhong – sequence: 4 givenname: Yong surname: Huang fullname: Huang, Yong – sequence: 5 givenname: Kun surname: Han fullname: Han, Kun
BookMark	eNptkV9vFCEUxYmpibX2yS9A4pMxU_mzwzCP66baJm2adjd9nVC4bGlmYAXGaD-9V9eH1hQeINzfOXA5b8lBTBEIec_ZiZQ9-1xm3grGF1rpV-RQsI43nLXs4Mn-DTku5YHhkJL3XB2Sx1uwNWV6PZtYwyM4emtyMDWkaEa6nGuCaJOD3HwxBaurNO0ylBJ-AF2baTeGuKWXUO-Tox59NmHCAuQAhYZI1zXPts4Zvc7AjPWeXqYY8EKUvSOvvRkLHP9bj8jm6-lmddZcXH07Xy0vGis7Xpvee-W0vpNWY3NSWe14Z7z2liu1EM71zijVG8YWd9xAb1thhNZeOgtCLOQR-bC33eX0fYZSh4c0Z-yuDIgJzRVCSJ3sqa0ZYQjRp5qNxelgChY_2gc8X3adaCVrW4GCj88EyFT4WbdmLmU4X988Zz_tWZtTKRn8sMthMvnXwNnwJ7vhSXZI8_9oG-rfRPBJYXxR8xvn455T
CitedBy_id	crossref_primary_10_1109_ACCESS_2024_3429195 crossref_primary_10_1155_2024_3374107
Cites_doi	10.1007/s11071-022-07328-3 10.1016/j.engstruct.2020.111347 10.1109/TSP.2007.914345 10.1177/1475921720959226 10.1155/2021/3739551 10.1177/14759217231170316 10.1109/RTEICT42901.2018.9012507 10.1111/mice.12528 10.1002/stc.3070 10.1109/TIT.2005.862083 10.1109/CVPR.2016.55 10.1088/1361-665X/aa7600 10.1109/LGRS.2017.2758397 10.1016/j.culher.2021.07.004 10.1016/j.neucom.2019.05.006 10.1109/ICASSP.2017.7952561 10.3390/s20041059 10.1109/JSEN.2023.3294912 10.1177/14759217231183663 10.1109/JSTSP.2007.910281 10.1007/s00034-022-02181-6 10.1016/j.engstruct.2021.113554 10.1177/14759217221079529 10.1109/POWERCON53406.2022.9930028 10.1016/j.acha.2008.07.002 10.1109/TMI.2017.2785879 10.1016/j.probengmech.2016.08.001 10.1177/14759217231184584 10.1016/j.ymssp.2020.107061 10.1371/journal.pone.0224365 10.1109/TIT.2006.871582 10.1109/DICTA.2016.7797053 10.1109/TSP.2016.2557301 10.1109/FSKD.2012.6234041 10.1002/stc.2433 10.1111/mice.12051 10.1109/TIP.2022.3195319 10.1186/1687-6180-2014-29 10.1016/j.dsp.2017.09.010 10.1016/j.jobe.2020.101921
ContentType	Journal Article
Copyright	COPYRIGHT 2023 MDPI AG 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2023 MDPI AG – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION ISR 4U- ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI
DOI	10.3390/su152014868
DatabaseName	CrossRef Gale In Context: Science University Readers ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition
DatabaseTitle	CrossRef Publicly Available Content Database University Readers ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: PIMPY name: ProQuest Publicly Available Content url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Economics Environmental Sciences
EISSN	2071-1050
ExternalDocumentID	A772530552 10_3390_su152014868
GroupedDBID	29Q 2WC 2XV 4P2 5VS 7XC 8FE 8FH A8Z AAHBH AAYXX ACHQT ADBBV ADMLS AENEX AFFHD AFKRA AFMMW ALMA_UNASSIGNED_HOLDINGS BCNDV BENPR CCPQU CITATION E3Z ECGQY ESTFP FRS GX1 IAO IEP ISR ITC KQ8 ML. MODMG M~E OK1 P2P PHGZM PHGZT PIMPY PROAC TR2 4U- ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI
ID	FETCH-LOGICAL-c371t-9ff6d88b3c801436c8d17af8fc16642dd9da669a004b1ae9c52a288f3dce2243
IEDL.DBID	BENPR
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001090037800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2071-1050
IngestDate	Mon Jun 30 14:55:51 EDT 2025 Tue Nov 04 18:38:27 EST 2025 Thu Nov 13 16:47:49 EST 2025 Tue Nov 18 22:10:44 EST 2025 Sat Nov 29 07:21:39 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	20
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c371t-9ff6d88b3c801436c8d17af8fc16642dd9da669a004b1ae9c52a288f3dce2243
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0007-5555-3082
OpenAccessLink	https://www.proquest.com/docview/2882816243?pq-origsite=%requestingapplication%
PQID	2882816243
PQPubID	2032327
ParticipantIDs	proquest_journals_2882816243 gale_infotracacademiconefile_A772530552 gale_incontextgauss_ISR_A772530552 crossref_primary_10_3390_su152014868 crossref_citationtrail_10_3390_su152014868
PublicationCentury	2000
PublicationDate	2023-10-01
PublicationDateYYYYMMDD	2023-10-01
PublicationDate_xml	– month: 10 year: 2023 text: 2023-10-01 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Sustainability
PublicationYear	2023
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	ref_50 Neddell (ref_45) 2009; 26 Figueiredo (ref_46) 2007; 1 ref_17 ref_16 Wang (ref_13) 2021; 251 Yao (ref_34) 2019; 359 Ji (ref_47) 2008; 56 Huang (ref_15) 2014; 29 ref_24 ref_23 ref_22 ref_20 Sony (ref_8) 2021; 226 Wang (ref_4) 2022; 29 Song (ref_2) 2021; 2021 Zhou (ref_42) 2014; 2014 Candes (ref_9) 2006; 52 Wang (ref_5) 2022; 21 ref_36 ref_35 ref_33 Chen (ref_26) 2022; 31 Iliadis (ref_25) 2018; 72 Schachner (ref_19) 2021; 51 Yang (ref_28) 2018; 37 Orr (ref_48) 2002; Volume 1524 ref_39 Ni (ref_29) 2019; 35 ref_38 ref_37 Palangi (ref_40) 2016; 64 Zhang (ref_12) 2022; 205 Huang (ref_14) 2016; 46 Wang (ref_27) 2023; 42 Wei (ref_7) 2017; 26 Zhang (ref_11) 2023; 23 ref_43 Chai (ref_32) 2022; 108 Hatir (ref_18) 2021; 34 ref_41 ref_1 Donoho (ref_10) 2006; 52 ref_3 Fan (ref_30) 2019; 26 ref_49 Lei (ref_31) 2020; 20 Huang (ref_21) 2021; 146 Liu (ref_44) 2017; 14 ref_6
References_xml	– volume: 108 start-page: 2671 year: 2022 ident: ref_32 article-title: An image encryption scheme based on multi-objective optimization and block compressed sensing publication-title: Nonlinear Dyn. doi: 10.1007/s11071-022-07328-3 – volume: 226 start-page: 111347 year: 2021 ident: ref_8 article-title: A systematic review of convolutional neural network-based structural condition assessment techniques publication-title: Eng. Struct. doi: 10.1016/j.engstruct.2020.111347 – ident: ref_39 – volume: 56 start-page: 2346 year: 2008 ident: ref_47 article-title: Bayesian compressive sensing publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2007.914345 – ident: ref_23 – volume: 20 start-page: 2069 year: 2020 ident: ref_31 article-title: Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks publication-title: Struct. Health Monit. doi: 10.1177/1475921720959226 – volume: 2021 start-page: 3739551 year: 2021 ident: ref_2 article-title: Outlier Detection Based on Multivariable Panel Data and K-Means Clustering for Dam Deformation Monitoring Data publication-title: Adv. Civ. Eng. doi: 10.1155/2021/3739551 – ident: ref_6 doi: 10.1177/14759217231170316 – ident: ref_16 doi: 10.1109/RTEICT42901.2018.9012507 – volume: 35 start-page: 685 year: 2019 ident: ref_29 article-title: Deep learning for data anomaly detection and data compression of a long-span suspension bridge publication-title: Comput.-Aided Civ. Infrastruct. Eng. doi: 10.1111/mice.12528 – volume: 29 start-page: e3070 year: 2022 ident: ref_4 article-title: Towards probabilistic data-driven damage detection in SHM using sparse Bayesian learning scheme publication-title: Struct. Control Health Monit. doi: 10.1002/stc.3070 – volume: 52 start-page: 489 year: 2006 ident: ref_9 article-title: Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2005.862083 – ident: ref_35 doi: 10.1109/CVPR.2016.55 – volume: 26 start-page: 104007 year: 2017 ident: ref_7 article-title: Strain features and condition assessment of orthotropic steel deck cable-supported bridges subjected to vehicle loads by using dense FBG strain sensors publication-title: Smart Mater. Struct. doi: 10.1088/1361-665X/aa7600 – volume: 14 start-page: 2230 year: 2017 ident: ref_44 article-title: An Over-Complete Dictionary Design Based on GSR for SAR Image Despeckling publication-title: IEEE Geosci. Remote. Sens. Lett. doi: 10.1109/LGRS.2017.2758397 – volume: 205 start-page: 112418 year: 2022 ident: ref_12 article-title: State-monitoring for abnormal vibration of bridge cables focusing on non-stationary responses: From knowledge in phenomena to digital indicators publication-title: Measurement – volume: 51 start-page: 37 year: 2021 ident: ref_19 article-title: The deep learning method applied to the detection and mapping of stone deterioration in open-air sanctuaries of the Hittite period in Anatolia publication-title: J. Cult. Herit. doi: 10.1016/j.culher.2021.07.004 – volume: 359 start-page: 483 year: 2019 ident: ref_34 article-title: DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.05.006 – ident: ref_38 – ident: ref_20 – ident: ref_33 doi: 10.1109/ICASSP.2017.7952561 – ident: ref_3 doi: 10.3390/s20041059 – volume: 23 start-page: 19635 year: 2023 ident: ref_11 article-title: Bayesian Multiple Linear Regression and New Modeling Paradigm for Structural Deflection Robust to Data Time Lag and Abnormal Signal publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2023.3294912 – ident: ref_22 doi: 10.1177/14759217231183663 – volume: 1 start-page: 586 year: 2007 ident: ref_46 article-title: Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems publication-title: IEEE J. Sel. Top. Signal Process. doi: 10.1109/JSTSP.2007.910281 – volume: 42 start-page: 1593 year: 2023 ident: ref_27 article-title: High-Quality Image Compressed Sensing and Reconstruction with Multi-scale Dilated Convolutional Neural Network publication-title: Circuits Syst. Signal Process. doi: 10.1007/s00034-022-02181-6 – ident: ref_24 – volume: Volume 1524 start-page: 55 year: 2002 ident: ref_48 article-title: Early Stopping—But When? publication-title: Neural Networks: Tricks of the Trade – volume: 251 start-page: 113554 year: 2021 ident: ref_13 article-title: Modelling and forecasting of SHM strain measurement for a large-scale suspension bridge during typhoon events using variational heteroscedasic Gaussian process publication-title: Eng. Struct. doi: 10.1016/j.engstruct.2021.113554 – volume: 21 start-page: 2933 year: 2022 ident: ref_5 article-title: Bayesian dynamic linear model framework for structural health monitoring data forecasting and missing data imputation during typhoon events publication-title: Struct. Health Monit. doi: 10.1177/14759217221079529 – ident: ref_43 doi: 10.1109/POWERCON53406.2022.9930028 – volume: 26 start-page: 301 year: 2009 ident: ref_45 article-title: CoSaMP: Iterative signal recovery from incomplete and inaccurate samples publication-title: Appl. Comput. Harmon. Anal. doi: 10.1016/j.acha.2008.07.002 – volume: 37 start-page: 1310 year: 2018 ident: ref_28 article-title: DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2017.2785879 – ident: ref_37 – volume: 46 start-page: 62 year: 2016 ident: ref_14 article-title: Bayesian compressive sensing for approximately sparse signals and application to structural health monitoring signals for data loss recovery publication-title: Probabilistic Eng. Mech. doi: 10.1016/j.probengmech.2016.08.001 – ident: ref_1 doi: 10.1177/14759217231184584 – volume: 146 start-page: 107061 year: 2021 ident: ref_21 article-title: Recovering compressed images for automatic crack segmentation using generative models publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2020.107061 – ident: ref_49 doi: 10.1371/journal.pone.0224365 – ident: ref_50 – volume: 52 start-page: 1289 year: 2006 ident: ref_10 article-title: Compressed sensing publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2006.871582 – ident: ref_17 doi: 10.1109/DICTA.2016.7797053 – volume: 64 start-page: 4504 year: 2016 ident: ref_40 article-title: Distributed Compressive Sensing: A Deep Learning Approach publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2016.2557301 – ident: ref_41 doi: 10.1109/FSKD.2012.6234041 – volume: 26 start-page: e2433 year: 2019 ident: ref_30 article-title: Lost data recovery for structural health monitoring based on convolutional neural networks publication-title: Struct. Control Health Monit. doi: 10.1002/stc.2433 – volume: 29 start-page: 160 year: 2014 ident: ref_15 article-title: Robust Bayesian compressive sensing for signals in structural health monitoring publication-title: Comput. -Aided Civ. Infrastruct. Eng. doi: 10.1111/mice.12051 – volume: 31 start-page: 5412 year: 2022 ident: ref_26 article-title: Content-Aware Scalable Deep Compressed Sensing publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3195319 – ident: ref_36 – volume: 2014 start-page: 29 year: 2014 ident: ref_42 article-title: A novel method for sparse channel estimation using super-resolution dictionary publication-title: EURASIP J. Adv. Signal Process. doi: 10.1186/1687-6180-2014-29 – volume: 72 start-page: 9 year: 2018 ident: ref_25 article-title: Deep fully-connected networks for video compressive sensing publication-title: Digit. Signal Process. doi: 10.1016/j.dsp.2017.09.010 – volume: 34 start-page: 101921 year: 2021 ident: ref_18 article-title: Lithology mapping of stone heritage via state-of-the-art computer vision publication-title: J. Build. Eng. doi: 10.1016/j.jobe.2020.101921
SSID	ssj0000331916
Score	2.3318925
Snippet	The theory of compressive sampling (CS) has revolutionized data compression technology by capitalizing on the inherent sparsity of a signal to enable signal...
SourceID	proquest gale crossref
SourceType	Aggregation Database Enrichment Source Index Database
StartPage	14868
SubjectTerms	Accuracy Big data Data compression Deep learning Inverse problems Methods Neural networks Parameter identification Signal processing Sparsity Sustainability Time series Wavelet transforms
Title	Vector Quantized Variational Autoencoder-Based Compressive Sampling Method for Time Series in Structural Health Monitoring
URI	https://www.proquest.com/docview/2882816243
Volume	15
WOSCitedRecordID	wos001090037800001&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: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2071-1050 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331916 issn: 2071-1050 databaseCode: M~E dateStart: 20090101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2071-1050 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331916 issn: 2071-1050 databaseCode: BENPR dateStart: 20090301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content customDbUrl: eissn: 2071-1050 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000331916 issn: 2071-1050 databaseCode: PIMPY dateStart: 20090301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fSxtBEB6qFtqXWrVibJSlCAXhMLd72dt7KlEi9SEhGhF9Ojb7QwJySXOJDz74t3fmbhMVpC99PG6OW3bmZna-m_kG4AgjUttnuhUlklpynOWRTpyKDM9ULL0QqfLVsIm031e3t9kgAG5lKKtc-sTKUduJIYz8hONREJ_mifg1_RPR1Cj6uxpGaKzBBjGVoZ1vnHb7g6sVytISaGKxrBvzBOb3qF-MWASjEbnqq1D0vkOuosz55v-u7yt8CedL1qkNYgs-uGIbPi3bj8tt2O2-tLahYPi2yx14uqkAfHa5wM0ePznLbjCPDlgh6yzmE-K8tG4WnWLks4w8SVVE--jYUFNhenHPetVAaoYnYUbNJYzAN1eyccGGFVEtkXywuvWJ1e6EcMVvcH3evT77HYXJDJERaTyPMu-lVWokDJHPCGmUjVPtlTexxITG2sxqKdEEWsko1i4zba5xg7ywxuGZQezCejEp3B4wqaTQAnOcxKVJ5rORNG1tNXdcjpThsgHHSx3lJrCW0_CMhxyzF1Jo_kqhDThaCU9rso73xX6QsnOivyiovuZeL8oyvxhe5R1MNtpEgsYb8DMI-Qm-0OjQroDLJsasN5LNpUXkwQGU-Ys57P_79nf4TBPs6_rAJqyjMtwBfDSP83E5Owz2fAhrvecuXg0ueoO7vyPnBFI
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3daxNBEB9qKtQXP6rFaNVFKoJwmNu97O09iERtaWgTogmlfVo2-1ECcqm5pGL_J_9HZ-6jrVB864PPN3e77P5uZnZ25jcAO2iRuiEznSiRVJLjHY9M4lVkeaZiGYRIVSibTaTDoTo-zkZr8LuphaG0ykYnlorazS3FyN9zdAXxbZ6Ij2c_IuoaRberTQuNChYH_tdPPLIVH_pfcH_fcL63O_m8H9VdBSIr0ngZZSFIp9RUWCJOEdIqF6cmqGBjic64c5kzUuL0O8k0Nj6zXW5w8CCc9WjvBH72DqwnhPUWrI_6g9HJZVCnIxDRsazqAIXIOggnNJAUtSMu12uW72b9Xxq1vQf_2XI8hPu198x6FdwfwZrPN2GjKa4uNmFr96pwDwVrzVU8houj8nqCfV0hlGYX3rEjs5jVkVDWWy3nxOjp_CL6hHbdMdKTZYrwuWdjQ2n3-SkblO22Gfr5jEpnGIUWfcFmORuXNLxEYcKqwi5WKUuKmj6ByW0syRa08nnunwKTSgoj8ASX-DTJQjaVtmuc4Z7LqbJctuFdAwlta052ag3yXePZjPCjr-GnDTuXwmcVFcnNYq8JW5rIPXLKHjo1q6LQ_fE33cOjVJco3ngb3tZCYY4DWlMXY-C0iQ_sL8ntBoC6Vm-FvkLfs38_fgUb-5PBoT7sDw-ewz2OHmKVCbkNLdwY_wLu2vPlrFi8rH8lBvqW0foHnXleSg
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VFEEvPAoVgQIWKkJCWjVrb7zeA0KBNiIqjQKpqvZkOX5UkdCmzSZF9J_x75jZR1ukilsPnHf2ZX-eGY9nvgHYQovUDZnpRImkkhzveGQSryLLMxXLIESqQtlsIh0O1dFRNlqB300tDKVVNjqxVNRuZilGvs3RFcS7eSK2Q50WMdrpfzw9i6iDFJ20Nu00Kojs-V8_cftWfBjs4Fy_5by_e_D5S1R3GIisSONFlIUgnVITYYlERUirXJyaoIKNJTrmzmXOSIm_0kkmsfGZ7XKDHxKEsx5tn8DH3oFV9MgT3oLV0WB_dHwZ4OkIRHcsq5pAIbIOQguNJUXwiNf1mhW82RaUBq7_8D8emkfwoPaqWa9aBo9hxefrcL8pui7WYWP3qqAPBWuNVjyBi8Py2IJ9WyLEphfesUMzn9YRUtZbLmbE9On8PPqE9t4x0p9l6vC5Z2ND6fj5Cdsv23Az9P8ZldQwCjn6gk1zNi7peYnahFUFX6xSohRNfQoHtzEkG9DKZ7l_BkwqKYzAnV3i0yQL2UTarnGGey4nynLZhvcNPLStudqpZcgPjXs2wpK-hqU2bF0Kn1YUJTeLvSGcaSL9yAkjJ2ZZFHow_q57uMXqEvUbb8O7WijM8IXW1EUa-NnEE_aX5GYDRl2rvUJfIfH5vy-_hnsIUf11MNx7AWscHccqQXITWjgv_iXcteeLaTF_Va8qBvqWwfoHiyxnCg
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=Vector+Quantized+Variational+Autoencoder-Based+Compressive+Sampling+Method+for+Time+Series+in+Structural+Health+Monitoring&rft.jtitle=Sustainability&rft.au=Liang%2C+Ge&rft.au=Ji%2C+Zhenglin&rft.au=Zhong%2C+Qunhong&rft.au=Huang%2C+Yong&rft.date=2023-10-01&rft.pub=MDPI+AG&rft.issn=2071-1050&rft.eissn=2071-1050&rft.volume=15&rft.issue=20&rft_id=info:doi/10.3390%2Fsu152014868&rft.externalDocID=A772530552
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2071-1050&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2071-1050&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2071-1050&client=summon