No Cover Image

Journal article 37 views 2 downloads

Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification

Jarod Hartley, Joe MacInnes Orcid Logo

Computers, Volume: 15, Issue: 5, Start page: 301

Swansea University Authors: Jarod Hartley, Joe MacInnes Orcid Logo

  • 71894.VoR.pdf

    PDF | Version of Record

    © 2026 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.

    Download (663.04KB)

Check full text

DOI (Published version): 10.3390/computers15050301

Abstract

Vision transformers (ViTs) have demonstrated considerable promise for classifying electrocardiogram (ECG) rhythms. However, much of the existing research is conducted in highly controlled, data-sterile settings that fail to reflect the substantial variability present in real-world ECG signals. This...

Full description

Published in: Computers
ISSN: 2073-431X
Published: MDPI AG 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71894
first_indexed 2026-05-14T16:02:11Z
last_indexed 2026-06-05T10:51:40Z
id cronfa71894
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-06-04T12:27:18.4939672</datestamp><bib-version>v2</bib-version><id>71894</id><entry>2026-05-14</entry><title>Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification</title><swanseaauthors><author><sid>e721973c025146a293722aad5406e254</sid><ORCID/><firstname>Jarod</firstname><surname>Hartley</surname><name>Jarod Hartley</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>06dcb003ec50192bafde2c77bef4fd5c</sid><ORCID>0000-0002-5134-1601</ORCID><firstname>Joe</firstname><surname>MacInnes</surname><name>Joe MacInnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-14</date><deptcode>MACS</deptcode><abstract>Vision transformers (ViTs) have demonstrated considerable promise for classifying electrocardiogram (ECG) rhythms. However, much of the existing research is conducted in highly controlled, data-sterile settings that fail to reflect the substantial variability present in real-world ECG signals. This paper seeks to address this gap by examining how signal simplification, data quantity, and task difficulty influence the performance of the SwinV2 ViT model in ECG rhythm classification. Through systematic analysis, we highlight that classifying highly abstracted signals yields only a limited impact on model performance, with all models achieving over 95% accuracy, while the amount of training data plays a crucial role with an almost 15% accuracy difference between the models trained on the most data and the least data. Finally, our analysis shows the model&#x2019;s ability to effectively adapt to an increased class count, which is essential due to the varying nature of ECG diagnosis. In summary, these results highlight the importance of carefully balancing data clarity, dataset size, and diagnostic variety when designing ECG classification systems. Achieving this balance is crucial for building reliable and scalable AI solutions for cardiac assessment.</abstract><type>Journal Article</type><journal>Computers</journal><volume>15</volume><journalNumber>5</journalNumber><paginationStart>301</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2073-431X</issnElectronic><keywords>vision transformer; ViT; signal simplification; data quantity; task difficulty; electrocardiogram; ECG; machine learning</keywords><publishedDay>9</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-05-09</publishedDate><doi>10.3390/computers15050301</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><funders/><projectreference/><lastEdited>2026-06-04T12:27:18.4939672</lastEdited><Created>2026-05-14T10:14:05.2370043</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>Jarod</firstname><surname>Hartley</surname><orcid/><order>1</order></author><author><firstname>Joe</firstname><surname>MacInnes</surname><orcid>0000-0002-5134-1601</orcid><order>2</order></author></authors><documents><document><filename>71894__36864__804d9570975b4dd897d920bcabfc7c23.pdf</filename><originalFilename>71894.VoR.pdf</originalFilename><uploaded>2026-06-04T12:24:50.0432758</uploaded><type>Output</type><contentLength>678948</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2026 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-06-04T12:27:18.4939672 v2 71894 2026-05-14 Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification e721973c025146a293722aad5406e254 Jarod Hartley Jarod Hartley true false 06dcb003ec50192bafde2c77bef4fd5c 0000-0002-5134-1601 Joe MacInnes Joe MacInnes true false 2026-05-14 MACS Vision transformers (ViTs) have demonstrated considerable promise for classifying electrocardiogram (ECG) rhythms. However, much of the existing research is conducted in highly controlled, data-sterile settings that fail to reflect the substantial variability present in real-world ECG signals. This paper seeks to address this gap by examining how signal simplification, data quantity, and task difficulty influence the performance of the SwinV2 ViT model in ECG rhythm classification. Through systematic analysis, we highlight that classifying highly abstracted signals yields only a limited impact on model performance, with all models achieving over 95% accuracy, while the amount of training data plays a crucial role with an almost 15% accuracy difference between the models trained on the most data and the least data. Finally, our analysis shows the model’s ability to effectively adapt to an increased class count, which is essential due to the varying nature of ECG diagnosis. In summary, these results highlight the importance of carefully balancing data clarity, dataset size, and diagnostic variety when designing ECG classification systems. Achieving this balance is crucial for building reliable and scalable AI solutions for cardiac assessment. Journal Article Computers 15 5 301 MDPI AG 2073-431X vision transformer; ViT; signal simplification; data quantity; task difficulty; electrocardiogram; ECG; machine learning 9 5 2026 2026-05-09 10.3390/computers15050301 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Other 2026-06-04T12:27:18.4939672 2026-05-14T10:14:05.2370043 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Jarod Hartley 1 Joe MacInnes 0000-0002-5134-1601 2 71894__36864__804d9570975b4dd897d920bcabfc7c23.pdf 71894.VoR.pdf 2026-06-04T12:24:50.0432758 Output 678948 application/pdf Version of Record true © 2026 by the authors. This is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. true eng https://creativecommons.org/licenses/by/4.0/
title Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
spellingShingle Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
Jarod Hartley
Joe MacInnes
title_short Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
title_full Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
title_fullStr Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
title_full_unstemmed Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
title_sort Quantifying the Impact of Signal Simplification, Data Quantity, and Task Difficulty on Vision Transformer Performance for ECG Rhythm Classification
author_id_str_mv e721973c025146a293722aad5406e254
06dcb003ec50192bafde2c77bef4fd5c
author_id_fullname_str_mv e721973c025146a293722aad5406e254_***_Jarod Hartley
06dcb003ec50192bafde2c77bef4fd5c_***_Joe MacInnes
author Jarod Hartley
Joe MacInnes
author2 Jarod Hartley
Joe MacInnes
format Journal article
container_title Computers
container_volume 15
container_issue 5
container_start_page 301
publishDate 2026
institution Swansea University
issn 2073-431X
doi_str_mv 10.3390/computers15050301
publisher MDPI AG
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 Vision transformers (ViTs) have demonstrated considerable promise for classifying electrocardiogram (ECG) rhythms. However, much of the existing research is conducted in highly controlled, data-sterile settings that fail to reflect the substantial variability present in real-world ECG signals. This paper seeks to address this gap by examining how signal simplification, data quantity, and task difficulty influence the performance of the SwinV2 ViT model in ECG rhythm classification. Through systematic analysis, we highlight that classifying highly abstracted signals yields only a limited impact on model performance, with all models achieving over 95% accuracy, while the amount of training data plays a crucial role with an almost 15% accuracy difference between the models trained on the most data and the least data. Finally, our analysis shows the model’s ability to effectively adapt to an increased class count, which is essential due to the varying nature of ECG diagnosis. In summary, these results highlight the importance of carefully balancing data clarity, dataset size, and diagnostic variety when designing ECG classification systems. Achieving this balance is crucial for building reliable and scalable AI solutions for cardiac assessment.
published_date 2026-05-09T11:51:40Z
_version_ 1867153880471568384
score 11.107897

Similar Items