Time series forecasting based on a novel ensemble‐based network and variational mode decomposition

Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non‐stationarity and noise. This research develops a novel decomposition ensemble‐based network named VMD‐DENetwork for time series forecasting over different horizons. A robust decomposition technique ca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expert systems 2023-08, Vol.40 (7), p.n/a
Hauptverfasser: Nazarieh, Fatemeh, Naderi Dehkordi, Mohammad
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page n/a
container_issue 7
container_start_page
container_title Expert systems
container_volume 40
creator Nazarieh, Fatemeh
Naderi Dehkordi, Mohammad
description Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non‐stationarity and noise. This research develops a novel decomposition ensemble‐based network named VMD‐DENetwork for time series forecasting over different horizons. A robust decomposition technique called variational mode decomposition (VMD) is applied to decompose the input sequence into several intrinsic modes in a non‐recursive manner. The optimal number of intrinsic modes is selected based on a comprehensive analysis to ensure the stability of the framework. The proposed DENetwork is developed based on stacking architecture and constitutes heterogeneous learners to model the nonlinear and complex relationships. It combines a convolutional neural network, long short‐term memory and an extreme learning machine. A firefly optimization algorithm is adopted for utilizing hyperparameters of the proposed model to enhance the efficiency of VMD‐DENetwork. The forecasting performance is verified by using six real‐world data sets from the New York Mercantile and International Petroleum Exchange. The final obtained results are compared with several peer‐advanced algorithms using the root mean squared error (RMSE), mean absolute error (MAE), Theil inequality coefficient (TIC) and correlation coefficient (R) metrics. The experimental results confirm that the proposed model demonstrates outstanding prediction performance. The employed optimization algorithm is compared with three frequently used bio‐inspired optimization algorithms, and their performance is tested using standard CEC benchmarks.
doi_str_mv 10.1111/exsy.13291
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2833746969</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2833746969</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3011-57ed587afd317edcfe9a724d5f971c5f60da363a9cca568dca7908295ce1e1b43</originalsourceid><addsrcrecordid>eNp9kM1OwzAMgCMEEmNw4QkicUPqSJo2aY5oGj_SJA4MCU5Rlrgoo21G0m30xiPwjDwJHeWML7bsz5b1IXROyYT2cQUfsZtQlkp6gEY040VCmMwO0YiknCeZSMkxOolxRQihQvARsgtXA44QHERc-gBGx9Y1r3ipI1jsG6xx47dQYWgi1MsKvj-_hlkD7c6HN6wbi7c6ON063-gK194CtmB8vfbR7Zun6KjUVYSzvzxGTzezxfQumT_c3k-v54lhhNIkF2DzQujSMtqXpgSpRZrZvJSCmrzkxGrGmZbG6JwX1mghSZHK3AAFuszYGF0Md9fBv28gtmrlN6H_Kaq0YExkXHLZU5cDZYKPMUCp1sHVOnSKErW3qPYW1a_FHqYDvHMVdP-Qavb8-DLs_AD4PXgI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2833746969</pqid></control><display><type>article</type><title>Time series forecasting based on a novel ensemble‐based network and variational mode decomposition</title><source>Wiley-Blackwell Journals</source><source>Business Source Complete</source><creator>Nazarieh, Fatemeh ; Naderi Dehkordi, Mohammad</creator><creatorcontrib>Nazarieh, Fatemeh ; Naderi Dehkordi, Mohammad</creatorcontrib><description>Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non‐stationarity and noise. This research develops a novel decomposition ensemble‐based network named VMD‐DENetwork for time series forecasting over different horizons. A robust decomposition technique called variational mode decomposition (VMD) is applied to decompose the input sequence into several intrinsic modes in a non‐recursive manner. The optimal number of intrinsic modes is selected based on a comprehensive analysis to ensure the stability of the framework. The proposed DENetwork is developed based on stacking architecture and constitutes heterogeneous learners to model the nonlinear and complex relationships. It combines a convolutional neural network, long short‐term memory and an extreme learning machine. A firefly optimization algorithm is adopted for utilizing hyperparameters of the proposed model to enhance the efficiency of VMD‐DENetwork. The forecasting performance is verified by using six real‐world data sets from the New York Mercantile and International Petroleum Exchange. The final obtained results are compared with several peer‐advanced algorithms using the root mean squared error (RMSE), mean absolute error (MAE), Theil inequality coefficient (TIC) and correlation coefficient (R) metrics. The experimental results confirm that the proposed model demonstrates outstanding prediction performance. The employed optimization algorithm is compared with three frequently used bio‐inspired optimization algorithms, and their performance is tested using standard CEC benchmarks.</description><identifier>ISSN: 0266-4720</identifier><identifier>EISSN: 1468-0394</identifier><identifier>DOI: 10.1111/exsy.13291</identifier><language>eng</language><publisher>Oxford: Blackwell Publishing Ltd</publisher><subject>Algorithms ; Artificial neural networks ; Correlation coefficients ; Decomposition ; deep learning ; ensemble learning ; Expert systems ; Forecasting ; Forecasting techniques ; Machine learning ; Mathematical models ; Nonlinearity ; Optimization ; Optimization algorithms ; Root-mean-square errors ; Stability analysis ; Time series ; time series forecasting ; variational mode decomposition</subject><ispartof>Expert systems, 2023-08, Vol.40 (7), p.n/a</ispartof><rights>2023 John Wiley &amp; Sons Ltd.</rights><rights>2023 John Wiley &amp; Sons, Ltd.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3011-57ed587afd317edcfe9a724d5f971c5f60da363a9cca568dca7908295ce1e1b43</citedby><cites>FETCH-LOGICAL-c3011-57ed587afd317edcfe9a724d5f971c5f60da363a9cca568dca7908295ce1e1b43</cites><orcidid>0000-0003-3678-7186</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1111%2Fexsy.13291$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1111%2Fexsy.13291$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids></links><search><creatorcontrib>Nazarieh, Fatemeh</creatorcontrib><creatorcontrib>Naderi Dehkordi, Mohammad</creatorcontrib><title>Time series forecasting based on a novel ensemble‐based network and variational mode decomposition</title><title>Expert systems</title><description>Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non‐stationarity and noise. This research develops a novel decomposition ensemble‐based network named VMD‐DENetwork for time series forecasting over different horizons. A robust decomposition technique called variational mode decomposition (VMD) is applied to decompose the input sequence into several intrinsic modes in a non‐recursive manner. The optimal number of intrinsic modes is selected based on a comprehensive analysis to ensure the stability of the framework. The proposed DENetwork is developed based on stacking architecture and constitutes heterogeneous learners to model the nonlinear and complex relationships. It combines a convolutional neural network, long short‐term memory and an extreme learning machine. A firefly optimization algorithm is adopted for utilizing hyperparameters of the proposed model to enhance the efficiency of VMD‐DENetwork. The forecasting performance is verified by using six real‐world data sets from the New York Mercantile and International Petroleum Exchange. The final obtained results are compared with several peer‐advanced algorithms using the root mean squared error (RMSE), mean absolute error (MAE), Theil inequality coefficient (TIC) and correlation coefficient (R) metrics. The experimental results confirm that the proposed model demonstrates outstanding prediction performance. The employed optimization algorithm is compared with three frequently used bio‐inspired optimization algorithms, and their performance is tested using standard CEC benchmarks.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Correlation coefficients</subject><subject>Decomposition</subject><subject>deep learning</subject><subject>ensemble learning</subject><subject>Expert systems</subject><subject>Forecasting</subject><subject>Forecasting techniques</subject><subject>Machine learning</subject><subject>Mathematical models</subject><subject>Nonlinearity</subject><subject>Optimization</subject><subject>Optimization algorithms</subject><subject>Root-mean-square errors</subject><subject>Stability analysis</subject><subject>Time series</subject><subject>time series forecasting</subject><subject>variational mode decomposition</subject><issn>0266-4720</issn><issn>1468-0394</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kM1OwzAMgCMEEmNw4QkicUPqSJo2aY5oGj_SJA4MCU5Rlrgoo21G0m30xiPwjDwJHeWML7bsz5b1IXROyYT2cQUfsZtQlkp6gEY040VCmMwO0YiknCeZSMkxOolxRQihQvARsgtXA44QHERc-gBGx9Y1r3ipI1jsG6xx47dQYWgi1MsKvj-_hlkD7c6HN6wbi7c6ON063-gK194CtmB8vfbR7Zun6KjUVYSzvzxGTzezxfQumT_c3k-v54lhhNIkF2DzQujSMtqXpgSpRZrZvJSCmrzkxGrGmZbG6JwX1mghSZHK3AAFuszYGF0Md9fBv28gtmrlN6H_Kaq0YExkXHLZU5cDZYKPMUCp1sHVOnSKErW3qPYW1a_FHqYDvHMVdP-Qavb8-DLs_AD4PXgI</recordid><startdate>202308</startdate><enddate>202308</enddate><creator>Nazarieh, Fatemeh</creator><creator>Naderi Dehkordi, Mohammad</creator><general>Blackwell Publishing Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-3678-7186</orcidid></search><sort><creationdate>202308</creationdate><title>Time series forecasting based on a novel ensemble‐based network and variational mode decomposition</title><author>Nazarieh, Fatemeh ; Naderi Dehkordi, Mohammad</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3011-57ed587afd317edcfe9a724d5f971c5f60da363a9cca568dca7908295ce1e1b43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Correlation coefficients</topic><topic>Decomposition</topic><topic>deep learning</topic><topic>ensemble learning</topic><topic>Expert systems</topic><topic>Forecasting</topic><topic>Forecasting techniques</topic><topic>Machine learning</topic><topic>Mathematical models</topic><topic>Nonlinearity</topic><topic>Optimization</topic><topic>Optimization algorithms</topic><topic>Root-mean-square errors</topic><topic>Stability analysis</topic><topic>Time series</topic><topic>time series forecasting</topic><topic>variational mode decomposition</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nazarieh, Fatemeh</creatorcontrib><creatorcontrib>Naderi Dehkordi, Mohammad</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Expert systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nazarieh, Fatemeh</au><au>Naderi Dehkordi, Mohammad</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Time series forecasting based on a novel ensemble‐based network and variational mode decomposition</atitle><jtitle>Expert systems</jtitle><date>2023-08</date><risdate>2023</risdate><volume>40</volume><issue>7</issue><epage>n/a</epage><issn>0266-4720</issn><eissn>1468-0394</eissn><abstract>Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non‐stationarity and noise. This research develops a novel decomposition ensemble‐based network named VMD‐DENetwork for time series forecasting over different horizons. A robust decomposition technique called variational mode decomposition (VMD) is applied to decompose the input sequence into several intrinsic modes in a non‐recursive manner. The optimal number of intrinsic modes is selected based on a comprehensive analysis to ensure the stability of the framework. The proposed DENetwork is developed based on stacking architecture and constitutes heterogeneous learners to model the nonlinear and complex relationships. It combines a convolutional neural network, long short‐term memory and an extreme learning machine. A firefly optimization algorithm is adopted for utilizing hyperparameters of the proposed model to enhance the efficiency of VMD‐DENetwork. The forecasting performance is verified by using six real‐world data sets from the New York Mercantile and International Petroleum Exchange. The final obtained results are compared with several peer‐advanced algorithms using the root mean squared error (RMSE), mean absolute error (MAE), Theil inequality coefficient (TIC) and correlation coefficient (R) metrics. The experimental results confirm that the proposed model demonstrates outstanding prediction performance. The employed optimization algorithm is compared with three frequently used bio‐inspired optimization algorithms, and their performance is tested using standard CEC benchmarks.</abstract><cop>Oxford</cop><pub>Blackwell Publishing Ltd</pub><doi>10.1111/exsy.13291</doi><tpages>31</tpages><orcidid>https://orcid.org/0000-0003-3678-7186</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0266-4720
ispartof Expert systems, 2023-08, Vol.40 (7), p.n/a
issn 0266-4720
1468-0394
language eng
recordid cdi_proquest_journals_2833746969
source Wiley-Blackwell Journals; Business Source Complete
subjects Algorithms
Artificial neural networks
Correlation coefficients
Decomposition
deep learning
ensemble learning
Expert systems
Forecasting
Forecasting techniques
Machine learning
Mathematical models
Nonlinearity
Optimization
Optimization algorithms
Root-mean-square errors
Stability analysis
Time series
time series forecasting
variational mode decomposition
title Time series forecasting based on a novel ensemble‐based network and variational mode decomposition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A18%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Time%20series%20forecasting%20based%20on%20a%20novel%20ensemble%E2%80%90based%20network%20and%20variational%20mode%20decomposition&rft.jtitle=Expert%20systems&rft.au=Nazarieh,%20Fatemeh&rft.date=2023-08&rft.volume=40&rft.issue=7&rft.epage=n/a&rft.issn=0266-4720&rft.eissn=1468-0394&rft_id=info:doi/10.1111/exsy.13291&rft_dat=%3Cproquest_cross%3E2833746969%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2833746969&rft_id=info:pmid/&rfr_iscdi=true