No Cover Image

Conference Paper/Proceeding/Abstract 1240 views 1716 downloads

A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders

Aniekan Essien, Cinzia Giannetti Orcid Logo

2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA), Pages: 1 - 6

Swansea University Author: Cinzia Giannetti Orcid Logo

DOI (Published version): 10.1109/INISTA.2019.8778417

Abstract

This paper proposes a deep learning framework where wavelet transforms (WT), 2-dimensional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) stacked autoencoders (SAE) are combined towards single-step time series prediction. Within the framework, the input dataset is denoised us...

Full description

Published in: 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)
ISBN: 978-1-7281-1863-5 978-1-7281-1862-8
Published: Sofia, Bulgaria IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) 2019
URI: https://cronfa.swan.ac.uk/Record/cronfa51622
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-08-29T14:53:23Z
last_indexed 2019-08-29T14:53:23Z
id cronfa51622
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-08-29T10:29:52.6831398</datestamp><bib-version>v2</bib-version><id>51622</id><entry>2019-08-29</entry><title>A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders</title><swanseaauthors><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-08-29</date><deptcode>MECH</deptcode><abstract>This paper proposes a deep learning framework where wavelet transforms (WT), 2-dimensional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) stacked autoencoders (SAE) are combined towards single-step time series prediction. Within the framework, the input dataset is denoised using wavelet decomposition, before learning in an unsupervised manner using SAEs comprising bidirectional Convolutional LSTM (ConvLSTM) layers to predict a single-step ahead value. To evaluate our proposed framework, we compared its performance to two (2) state-of-the-art deep learning predictive models using three open-source univariate time series datasets. The experimental results support the value of the approach when applied to univariate time series prediction.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)</journal><paginationStart>1</paginationStart><paginationEnd>6</paginationEnd><publisher>IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA)</publisher><placeOfPublication>Sofia, Bulgaria</placeOfPublication><isbnPrint>978-1-7281-1863-5</isbnPrint><isbnElectronic>978-1-7281-1862-8</isbnElectronic><keywords/><publishedDay>29</publishedDay><publishedMonth>7</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-07-29</publishedDate><doi>10.1109/INISTA.2019.8778417</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2019-08-29T10:29:52.6831398</lastEdited><Created>2019-08-29T10:23:57.1407106</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Aniekan</firstname><surname>Essien</surname><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author></authors><documents><document><filename>0051622-29082019102938.pdf</filename><originalFilename>essien2019.pdf</originalFilename><uploaded>2019-08-29T10:29:38.6800000</uploaded><type>Output</type><contentLength>827281</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-08-29T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2019-08-29T10:29:52.6831398 v2 51622 2019-08-29 A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2019-08-29 MECH This paper proposes a deep learning framework where wavelet transforms (WT), 2-dimensional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) stacked autoencoders (SAE) are combined towards single-step time series prediction. Within the framework, the input dataset is denoised using wavelet decomposition, before learning in an unsupervised manner using SAEs comprising bidirectional Convolutional LSTM (ConvLSTM) layers to predict a single-step ahead value. To evaluate our proposed framework, we compared its performance to two (2) state-of-the-art deep learning predictive models using three open-source univariate time series datasets. The experimental results support the value of the approach when applied to univariate time series prediction. Conference Paper/Proceeding/Abstract 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA) 1 6 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Sofia, Bulgaria 978-1-7281-1863-5 978-1-7281-1862-8 29 7 2019 2019-07-29 10.1109/INISTA.2019.8778417 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University 2019-08-29T10:29:52.6831398 2019-08-29T10:23:57.1407106 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Aniekan Essien 1 Cinzia Giannetti 0000-0003-0339-5872 2 0051622-29082019102938.pdf essien2019.pdf 2019-08-29T10:29:38.6800000 Output 827281 application/pdf Accepted Manuscript true 2019-08-29T00:00:00.0000000 true eng
title A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
spellingShingle A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
Cinzia Giannetti
title_short A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
title_full A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
title_fullStr A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
title_full_unstemmed A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
title_sort A Deep Learning Framework for Univariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders
author_id_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author Cinzia Giannetti
author2 Aniekan Essien
Cinzia Giannetti
format Conference Paper/Proceeding/Abstract
container_title 2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA)
container_start_page 1
publishDate 2019
institution Swansea University
isbn 978-1-7281-1863-5
978-1-7281-1862-8
doi_str_mv 10.1109/INISTA.2019.8778417
publisher IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description This paper proposes a deep learning framework where wavelet transforms (WT), 2-dimensional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) stacked autoencoders (SAE) are combined towards single-step time series prediction. Within the framework, the input dataset is denoised using wavelet decomposition, before learning in an unsupervised manner using SAEs comprising bidirectional Convolutional LSTM (ConvLSTM) layers to predict a single-step ahead value. To evaluate our proposed framework, we compared its performance to two (2) state-of-the-art deep learning predictive models using three open-source univariate time series datasets. The experimental results support the value of the approach when applied to univariate time series prediction.
published_date 2019-07-29T04:03:35Z
_version_ 1763753292804915200
score 11.017731

Similar Items