No Cover Image

Journal article 22367 views 297 downloads

Concurrent time-series selections using deep learning and dimension reduction

Mohammed Ali, Rita Borgo, Mark Jones Orcid Logo

Knowledge-Based Systems, Volume: 233, Start page: 107507

Swansea University Author: Mark Jones Orcid Logo

  • 57939.pdf

    PDF | Version of Record

    © 2021 The Author(s). This is an open access article under the CC BY license

    Download (3.08MB)

Check full text

DOI (Published version): 10.1016/j.knosys.2021.107507

Abstract

The objective of this work was to investigate from a user perspective linkage between a 1D time-series view of data and a 2D representation provided by dimension reduction techniques. Our hypothesis is that when such interaction happens seamlessly, the use of these linked views, compared to only int...

Full description

Published in: Knowledge-Based Systems
ISSN: 0950-7051
Published: Elsevier BV 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57939
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-09-17T13:38:30Z
last_indexed 2023-01-11T14:38:10Z
id cronfa57939
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-10-31T13:40:38.1172796</datestamp><bib-version>v2</bib-version><id>57939</id><entry>2021-09-17</entry><title>Concurrent time-series selections using deep learning and dimension reduction</title><swanseaauthors><author><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><ORCID>0000-0001-8991-1190</ORCID><firstname>Mark</firstname><surname>Jones</surname><name>Mark Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-09-17</date><deptcode>SCS</deptcode><abstract>The objective of this work was to investigate from a user perspective linkage between a 1D time-series view of data and a 2D representation provided by dimension reduction techniques. Our hypothesis is that when such interaction happens seamlessly, the use of these linked views, compared to only interacting with the 1D time-series view, for the ubiquitous task of selection and labelling, is more efficient and effective both in terms of performance and user experience. To this end we examine different dimension reduction techniques (UMAP, t-SNE, PCA and Autoencoder) and evaluate each technique within our experimental setting. Results demonstrate that there is a positive impact on speed and accuracy through augmenting 1D views with a dimension reduction 2D view when these views are linked and linkage is supported through coordinated interaction.</abstract><type>Journal Article</type><journal>Knowledge-Based Systems</journal><volume>233</volume><journalNumber/><paginationStart>107507</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0950-7051</issnPrint><issnElectronic/><keywords>User interaction; User study; Dimension reduction; Time-series data; Deep Learning</keywords><publishedDay>5</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-12-05</publishedDate><doi>10.1016/j.knosys.2021.107507</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>EPSRC</funders><projectreference>EP/N028139/1</projectreference><lastEdited>2022-10-31T13:40:38.1172796</lastEdited><Created>2021-09-17T14:31:46.7188502</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Mohammed</firstname><surname>Ali</surname><order>1</order></author><author><firstname>Rita</firstname><surname>Borgo</surname><order>2</order></author><author><firstname>Mark</firstname><surname>Jones</surname><orcid>0000-0001-8991-1190</orcid><order>3</order></author></authors><documents><document><filename>57939__21195__e4cf89c898924509b1a8fdf3f2e85d1f.pdf</filename><originalFilename>57939.pdf</originalFilename><uploaded>2021-10-18T09:33:41.7157894</uploaded><type>Output</type><contentLength>3227047</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 The Author(s). This is an open access article under the CC BY license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-10-31T13:40:38.1172796 v2 57939 2021-09-17 Concurrent time-series selections using deep learning and dimension reduction 2e1030b6e14fc9debd5d5ae7cc335562 0000-0001-8991-1190 Mark Jones Mark Jones true false 2021-09-17 SCS The objective of this work was to investigate from a user perspective linkage between a 1D time-series view of data and a 2D representation provided by dimension reduction techniques. Our hypothesis is that when such interaction happens seamlessly, the use of these linked views, compared to only interacting with the 1D time-series view, for the ubiquitous task of selection and labelling, is more efficient and effective both in terms of performance and user experience. To this end we examine different dimension reduction techniques (UMAP, t-SNE, PCA and Autoencoder) and evaluate each technique within our experimental setting. Results demonstrate that there is a positive impact on speed and accuracy through augmenting 1D views with a dimension reduction 2D view when these views are linked and linkage is supported through coordinated interaction. Journal Article Knowledge-Based Systems 233 107507 Elsevier BV 0950-7051 User interaction; User study; Dimension reduction; Time-series data; Deep Learning 5 12 2021 2021-12-05 10.1016/j.knosys.2021.107507 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University EPSRC EP/N028139/1 2022-10-31T13:40:38.1172796 2021-09-17T14:31:46.7188502 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Mohammed Ali 1 Rita Borgo 2 Mark Jones 0000-0001-8991-1190 3 57939__21195__e4cf89c898924509b1a8fdf3f2e85d1f.pdf 57939.pdf 2021-10-18T09:33:41.7157894 Output 3227047 application/pdf Version of Record true © 2021 The Author(s). This is an open access article under the CC BY license true eng http://creativecommons.org/licenses/by/4.0/
title Concurrent time-series selections using deep learning and dimension reduction
spellingShingle Concurrent time-series selections using deep learning and dimension reduction
Mark Jones
title_short Concurrent time-series selections using deep learning and dimension reduction
title_full Concurrent time-series selections using deep learning and dimension reduction
title_fullStr Concurrent time-series selections using deep learning and dimension reduction
title_full_unstemmed Concurrent time-series selections using deep learning and dimension reduction
title_sort Concurrent time-series selections using deep learning and dimension reduction
author_id_str_mv 2e1030b6e14fc9debd5d5ae7cc335562
author_id_fullname_str_mv 2e1030b6e14fc9debd5d5ae7cc335562_***_Mark Jones
author Mark Jones
author2 Mohammed Ali
Rita Borgo
Mark Jones
format Journal article
container_title Knowledge-Based Systems
container_volume 233
container_start_page 107507
publishDate 2021
institution Swansea University
issn 0950-7051
doi_str_mv 10.1016/j.knosys.2021.107507
publisher Elsevier BV
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 Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description The objective of this work was to investigate from a user perspective linkage between a 1D time-series view of data and a 2D representation provided by dimension reduction techniques. Our hypothesis is that when such interaction happens seamlessly, the use of these linked views, compared to only interacting with the 1D time-series view, for the ubiquitous task of selection and labelling, is more efficient and effective both in terms of performance and user experience. To this end we examine different dimension reduction techniques (UMAP, t-SNE, PCA and Autoencoder) and evaluate each technique within our experimental setting. Results demonstrate that there is a positive impact on speed and accuracy through augmenting 1D views with a dimension reduction 2D view when these views are linked and linkage is supported through coordinated interaction.
published_date 2021-12-05T04:14:03Z
_version_ 1763753950995021824
score 11.037319

Similar Items