Static Seeding and Clustering of LSTM Embeddings to Learn From Loosely Time-Decoupled Events

Humans learn from the occurrence of events at different places and times to predict similar trajectories of events. We define loosely decoupled time (LDT) phenomena as two or more events that could occur in different places and across different timelines but share similarities in the nature of the e...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE access Vol. 11; pp. 64219 - 64227
Main Authors:	Manasseh, Christian G., Veliche, Razvan, Bennett, Jared, Clouse, Hamilton Scott
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithm design and analysis artificial intelligence Clustering COVID-19 Data models Diseases Hidden Markov models Multivariate analysis numerical algorithms and problems Predictive models Recurrent neural networks statistical methods Time series Time series analysis Training
ISSN:	2169-3536, 2169-3536
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Humans learn from the occurrence of events at different places and times to predict similar trajectories of events. We define loosely decoupled time (LDT) phenomena as two or more events that could occur in different places and across different timelines but share similarities in the nature of the event and the properties of the location. In this work, we improve the use of recurrent neural networks (RNN), particularly long short-term memory (LSTM) networks, to enable AI solutions that generate better time series predictions for LDT. We used similarity measures between the time series based on the time series properties detected by the LSTM and introduced embeddings representing these properties. The embeddings represent the properties of the event, which, coupled with the LSTM structure, can be clustered to identify similar temporally unaligned events. In this study, we explore methods of seeding a multivariate LSTM from time-invariant data related to the geophysical and demographic phenomena modeled by the LSTM. We applied these methods to time-series data derived from COVID-19 detected infection and death cases. We use publicly available socioeconomic data to seed the LSTM models, creating embeddings, to determine whether such seeding improves case predictions. The embeddings produced by these LSTMs are clustered to identify the best-matching candidates for forecasting evolving time series. Applying this method, we showed an improvement in the 10-day moving average predictions of disease propagation at the US County level.
AbstractList	Humans learn from the occurrence of events at different places and times to predict similar trajectories of events. We define loosely decoupled time (LDT) phenomena as two or more events that could occur in different places and across different timelines but share similarities in the nature of the event and the properties of the location. In this work, we improve the use of recurrent neural networks (RNN), particularly long short-term memory (LSTM) networks, to enable AI solutions that generate better time series predictions for LDT. We used similarity measures between the time series based on the time series properties detected by the LSTM and introduced embeddings representing these properties. The embeddings represent the properties of the event, which, coupled with the LSTM structure, can be clustered to identify similar temporally unaligned events. In this study, we explore methods of seeding a multivariate LSTM from time-invariant data related to the geophysical and demographic phenomena modeled by the LSTM. We applied these methods to time-series data derived from COVID-19 detected infection and death cases. We use publicly available socioeconomic data to seed the LSTM models, creating embeddings, to determine whether such seeding improves case predictions. The embeddings produced by these LSTMs are clustered to identify the best-matching candidates for forecasting evolving time series. Applying this method, we showed an improvement in the 10-day moving average predictions of disease propagation at the US County level.
Author	Veliche, Razvan Manasseh, Christian G. Clouse, Hamilton Scott Bennett, Jared
Author_xml	– sequence: 1 givenname: Christian G. orcidid: 0000-0002-2283-946X surname: Manasseh fullname: Manasseh, Christian G. email: cman@alum.mit.edu organization: Mobius Logic Inc., Tysons, VA, USA – sequence: 2 givenname: Razvan surname: Veliche fullname: Veliche, Razvan organization: Mobius Logic Inc., Tysons, VA, USA – sequence: 3 givenname: Jared orcidid: 0000-0003-4718-257X surname: Bennett fullname: Bennett, Jared organization: Mobius Logic Inc., Tysons, VA, USA – sequence: 4 givenname: Hamilton Scott surname: Clouse fullname: Clouse, Hamilton Scott organization: Air Force Research Laboratory, Wright-Patterson Air Force Base, OH, USA
BookMark	eNp9Uc1u3CAYRFUqNU3zBO0BqWdv-VkwHCN300Zy1YO3t0oIzEfklddswVspbx9cp1KUQ7jAN8yMBuY9upjiBAh9pGRDKdFfbppm13UbRhjfcKbUVtVv0CWjUldccHnx7PwOXed8IGWpAon6Ev3uZjsPPe4A_DDdYzt53IznPENaxhhw2-1_4N3RgV8IGc8Rt2DThG9TPOI2xgzjA94PR6i-Qh_PpxE83v2Fac4f0NtgxwzXT_sV-nW72zffq_bnt7vmpq36LdFzZV2QAFshhNTAZS2FcOVGWKdLUk8ClcQFWzviFdF9qGVPRGCM9NRyyym_Qnerr4_2YE5pONr0YKIdzD8gpntjU3nlCMZZR4MHJZQIW8qC1kHQAKKuqfMFLF6fV69Tin_OkGdziOc0lfiGKU4F00qrwtIrq08x5wTB9MPykXGakx1GQ4lZujFrN2bpxjx1U7T8hfZ_4tdVn1bVAADPFFRoLiR_BNGqm5g
CODEN	IAECCG
CitedBy_id	crossref_primary_10_1109_JSEN_2024_3521422
Cites_doi	10.1609/aaai.v33i01.33019607 10.1016/S1473-3099(20)30120-1 10.1609/aaai.v35i6.16616 10.1109/5.18626 10.24171/j.phrp.2021.0100 10.1109/TKDE.2015.2416723 10.1098/rspa.1927.0118 10.1609/aaai.v35i3.16284 10.1016/S0166-4115(97)80111-2 10.1145/3318464.3389760 10.1609/aaai.v35i6.16622 10.1007/s10618-016-0483-9 10.1109/RBME.2021.3069213 10.1109/ICME.2000.869621 10.1007/3-540-45014-9_1 10.1109/FG.2019.8756618 10.1016/s1473-3099(20)30120-1 10.1109/DSAA.2016.10 10.1109/ICASSP.1982.1171695 10.1162/neco.1997.9.8.1735 10.1109/TPAMI.2006.211
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2023.3288487
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts 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 METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	64227
ExternalDocumentID	oai_doaj_org_article_bab1fde8585f412f99f51fe5771bd585 10_1109_ACCESS_2023_3288487 10159356
Genre	orig-research
GrantInformation_xml	– fundername: Air Force Research Laboratory (AFRL) Autonomy Capability Team 3 (ACT3) grantid: FA8649-20-C-0130 funderid: 10.13039/100006602
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c409t-abf6ee455569e367655bc405ab9000d0f160bfa7b0d809cf76c05f220c1a3a313
IEDL.DBID	DOA
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001021931800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:52:48 EDT 2025 Sun Jun 29 16:29:13 EDT 2025 Sat Nov 29 04:02:46 EST 2025 Tue Nov 18 21:03:49 EST 2025 Wed Aug 27 02:25:49 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c409t-abf6ee455569e367655bc405ab9000d0f160bfa7b0d809cf76c05f220c1a3a313
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-2283-946X 0000-0003-4718-257X
OpenAccessLink	https://doaj.org/article/bab1fde8585f412f99f51fe5771bd585
PQID	2831529898
PQPubID	4845423
PageCount	9
ParticipantIDs	doaj_primary_oai_doaj_org_article_bab1fde8585f412f99f51fe5771bd585 ieee_primary_10159356 crossref_citationtrail_10_1109_ACCESS_2023_3288487 crossref_primary_10_1109_ACCESS_2023_3288487 proquest_journals_2831529898
PublicationCentury	2000
PublicationDate	20230000 2023-00-00 20230101 2023-01-01
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– year: 2023 text: 20230000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2023
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 ref15 ref14 ref11 ref10 ref2 ref1 ref17 ref16 ref18 (ref12) 2021 (ref27) 2023 (ref23) 2010 Jordan (ref19); 9 ref25 ref20 ref22 (ref24) 2021 ref21 ref8 ref7 ref9 ref4 ref3 ref6 (ref26) 2023 ref5
References_xml	– ident: ref17 doi: 10.1609/aaai.v33i01.33019607 – ident: ref25 doi: 10.1016/S1473-3099(20)30120-1 – ident: ref15 doi: 10.1609/aaai.v35i6.16616 – ident: ref3 doi: 10.1109/5.18626 – ident: ref20 doi: 10.24171/j.phrp.2021.0100 – ident: ref9 doi: 10.1109/TKDE.2015.2416723 – ident: ref22 doi: 10.1098/rspa.1927.0118 – ident: ref14 doi: 10.1609/aaai.v35i3.16284 – ident: ref1 doi: 10.1016/S0166-4115(97)80111-2 – ident: ref10 doi: 10.1145/3318464.3389760 – volume-title: Ray Tune: Scalable Hyperparameter Tuning year: 2023 ident: ref27 – ident: ref16 doi: 10.1609/aaai.v35i6.16622 – ident: ref6 doi: 10.1007/s10618-016-0483-9 – ident: ref21 doi: 10.1109/RBME.2021.3069213 – ident: ref18 doi: 10.1109/ICME.2000.869621 – ident: ref5 doi: 10.1007/3-540-45014-9_1 – volume: 9 start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref19 article-title: Hidden Markov decision trees – ident: ref11 doi: 10.1109/FG.2019.8756618 – volume-title: Machine Learning Crash Course year: 2021 ident: ref12 – ident: ref13 doi: 10.1016/s1473-3099(20)30120-1 – volume-title: PyTorch Machine Learning Framework year: 2023 ident: ref26 – ident: ref4 doi: 10.1109/DSAA.2016.10 – ident: ref7 doi: 10.1109/ICASSP.1982.1171695 – volume-title: USDA Economic Research Service year: 2021 ident: ref24 – ident: ref2 doi: 10.1162/neco.1997.9.8.1735 – volume-title: US Census Datasets year: 2010 ident: ref23 – ident: ref8 doi: 10.1109/TPAMI.2006.211
SSID	ssj0000816957
Score	2.2714655
Snippet	Humans learn from the occurrence of events at different places and times to predict similar trajectories of events. We define loosely decoupled time (LDT)...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	64219
SubjectTerms	Algorithm design and analysis artificial intelligence Clustering COVID-19 Data models Diseases Hidden Markov models Multivariate analysis numerical algorithms and problems Predictive models Recurrent neural networks statistical methods Time series Time series analysis Training
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB6VVQ9waCkFsbCtfOBIljix4-RIt7viQFElQOJQKYpfEtLuBu2jEv-eGcesVqpA6i1xbMXJ58eM7fk-gLMUTWT0MjL0TXKRCK1NUuqqwcEQXZaq8taKTmxC3dyUDw_V7xisHmJhnHPh8Jkb0mXYy7etWdNSGfZwnHxzWezAjlKqC9baLKiQgkQlVWQW4ml1cTka4UcMSSB8mGdlKejc3NbsE0j6o6rKP0NxmF8mn_-zZvvwKRqS7LJD_gt8cPMD2NuiF_wKf8iSfDTstpuhWDO3bDRdEzUC3baeXd_e_WLjmXY2bEGxVcsC4SqbLNoZu27bpZs-MwoTSX6in7p-mjrLxnREcnkI95Px3egqiWoKiUEfbpU02hfOCSllUTniaZNS4xPZaNINtannRap9o3RqESjjVWFS6bMsNbzJm5znR9Cbt3N3DCxvypw8K6LeEVJbbRwXXppMaFsWouhD9vqXaxOpxknxYloHlyOt6g6amqCpIzR9ON8UeuqYNt7P_oPg22QlmuyQgLjUsdehJaC5t472Pr3gmcfGJ7l3UimuLSb24ZCw3HpfB2MfBq-toY59elmjIYbGDultnrxR7BR2qYrdCs0AeqvF2n2Dj-bv6nG5-B6a6ws5nuXj priority: 102 providerName: IEEE
Title	Static Seeding and Clustering of LSTM Embeddings to Learn From Loosely Time-Decoupled Events
URI	https://ieeexplore.ieee.org/document/10159356 https://www.proquest.com/docview/2831529898 https://doaj.org/article/bab1fde8585f412f99f51fe5771bd585
Volume	11
WOSCitedRecordID	wos001021931800001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHvQgPnF9LDl4tNq0SR9HXXfx4C7CKngQQp4grFvZh-DF3-5MWqUg6MVLoWlCmpnpZL4m-YaQ0xhCZEAZCWCTlEdcaxMVulTgDAGylKW3ltfJJvLRqHh8LO9aqb5wT1hND1wL7kIrzbx1uHzlOUs8tBfMO5HnTFsoRO8LUU8LTAUfXLCsFHlDM8Ti8uKy14MRnWO28PM0KQqOm-haU1Fg7G9SrPzwy2GyGWyRzSZKpJf1222TFTfdIRst7sBd8oRh4rOh43r6oWpqaW-yRN4DvK08vR3fD2n_RTsb1pfooqKBTZUOZtULva2quZu8UzwDEl0DCF2-Tpylfdz_ON8jD4P-fe8malIlRAYA2iJS2mfOcSFEVjokYRNCwxOhNCYFtbFnWay9ynVsQQvG55mJhU-S2DCVqpSl-2R1Wk3dAaGpKlKETcirw4W22jjGvTAJ17bIeNYhyZfUpGl4xDGdxUQGPBGXsha1RFHLRtQdcvbd6LWm0fi9-hWq47sqcmCHArAM2ViG_MsyOmQPldnqD0K3VMAAjr-0K5sPdi4hyoJIBpNpHv5H30dkHcdT_6s5JquL2dKdkDXztniez7rBVuE6_Oh3w4nDT7sq6w0
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFD5oLWgf1GqLW6vmoY_OOplJ5vLYrrtU3C6FrtAHIUxuUNjulL0U-u97TiZdFkTBt7kkJDNfLuckOd8HcJKiiYxeRoa-SS4SobVJKl03OBiiy1LX3lrRiU2Uk0l1fV1fxmD1EAvjnAuHz1yfLsNevm3NmpbKsIfj5JvL4jm8wAIy3oVrbZZUSEOilmXkFuJp_e10MMDP6JNEeD_PqkrQybmt-SfQ9EddlT8G4zDDjN78Z93ewutoSrLTDvt9eObm72Bvi2DwPfwmW_LGsKtujmLN3LLBbE3kCHTbeja-ml6w4a12NmxCsVXLAuUqGy3aWzZu26WbPTAKFEm-o6e6vps5y4Z0SHJ5AL9Gw-ngPIl6ColBL26VNNoXzgkpZVE7YmqTUuMb2WhSDrWp50WqfVPq1CJUxpeFSaXPstTwJm9ynh_Czryduw_A8qbKybci8h0htdXGceGlyYS2VSGKHmRPf1mZSDZOmhczFZyOtFYdNIqgURGaHnzdZLrruDb-nfyM4NskJaLs8ABxUbHfoS2gubeOdj-94JnH5ie5d7Isubb4sAcHhOVWeR2MPTh-ag0q9uqlQlMMzR1S3Dz6S7Yv8PJ8ejFW4x-Tnx_hFVW3W685hp3VYu0-wa65X90sF59D030EU-npKg
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=Static+Seeding+and+Clustering+of+LSTM+Embeddings+to+Learn+From+Loosely+Time-Decoupled+Events&rft.jtitle=IEEE+access&rft.au=Manasseh%2C+Christian+G.&rft.au=Veliche%2C+Razvan&rft.au=Bennett%2C+Jared&rft.au=Clouse%2C+Hamilton+Scott&rft.date=2023&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=11&rft.spage=64219&rft.epage=64227&rft_id=info:doi/10.1109%2FACCESS.2023.3288487&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2023_3288487
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon