Publication:

Improved Deep Learning Based ECG Classification through Automated Feature Selection and Weighted Loss Function

Date

2024
Proceedings Paper
https://doi.org/10.1109/IJCNN60899.2024.10651531
Simple item page Full metadata Statistics
 
dc.contributor.authorDe Waele, Timo
dc.contributor.authorPeralta, Daniel
dc.contributor.authorDe Poorter, Eli
dc.contributor.authorShahid, Adnan
dc.contributor.imecauthorDe Waele, Timo
dc.contributor.imecauthorPeralta, Daniel
dc.contributor.imecauthorDe Poorter, Eli
dc.contributor.imecauthorShahid, Adnan
dc.contributor.orcidimecDe Waele, Timo::0000-0001-6518-9834
dc.contributor.orcidimecPeralta, Daniel::0000-0002-7544-8411
dc.contributor.orcidimecDe Poorter, Eli::0000-0002-0214-5751
dc.contributor.orcidimecShahid, Adnan::0000-0003-1943-6261
dc.date.accessioned2025-08-18T11:04:24Z
dc.date.available2025-03-06T20:45:30Z
dc.date.available2025-03-07T08:51:03Z
dc.date.available2025-08-18T11:04:24Z
dc.date.embargo2024-09-09
dc.date.issued2024
dc.description.wosFundingTextThis work was supported by the Fund for Scientific Research Flanders, Belgium, FWO-Vlaanderen, FWO-SB, under Grant 1S33924N.This project was supported by the Erasmus+ program of the European Commission through the 'Capacity Building for Digital Health Monitoring and Care Systems in Asia (DigiHealth-Asia)' under grant agreement number 619193-EPP-1-2020-BE-EPPKA2-CBHE-JP.
dc.identifier.doi10.1109/IJCNN60899.2024.10651531
dc.identifier.eisbn979-8-3503-5931-2
dc.identifier.isbn979-8-3503-5932-9
dc.identifier.issn2161-4393
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/45321
dc.publisherIEEE
dc.source.conferenceInternational Joint Conference on Neural Networks (IJCNN)
dc.source.conferencedateJUN 30-JUL 05, 2024
dc.source.conferencelocationYokohama
dc.source.journalN/A
dc.source.numberofpages8
dc.subject.keywordsHEARTBEAT CLASSIFICATION
dc.title

Improved Deep Learning Based ECG Classification through Automated Feature Selection and Weighted Loss Function

dc.typeProceedings paper
dspace.entity.typePublication
Files

Original bundle

Name:
8644.pdf
Size:
1.16 MB
Format:
Unknown data format
Description:
Published version
Download
Name:
8644_acc.pdf
Size:
495.02 KB
Format:
Unknown data format
Description:
Accepted version
Download
Publication available in collections:
Conference contributions