liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Parralel Recurrent Convolutional Neural Network for Abnormal Heart Sound Classification
School of Information Technology, Halmstad University, Halmstad, Sweden.ORCID-id: 0000-0002-3413-2859
Department of Electrical Engineering, Amirkabir University, Tehran, Iran.
Linköpings universitet, Institutionen för medicinsk teknik, Avdelningen för medicinsk teknik. Linköpings universitet, Tekniska fakulteten. Department Information Science and Media Studies, University of Bergen, Bergen, Norway.
2023 (Engelska)Ingår i: CARING IS SHARING-EXPLOITING THE VALUE IN DATA FOR HEALTH AND INNOVATION-PROCEEDINGS OF MIE 2023, IOS PRESS , 2023, Vol. 302, s. 526-530Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

This paper presents the results of a study performed on Parallel Convolutional Neural Network (PCNN) toward detecting heart abnormalities from the heart sound signals. The PCNN preserves dynamic contents of the signal in a parallel combination of the recurrent neural network and a Convolutional Neural Network (CNN). The performance of the PCNN is evaluated and compared to the one obtained from a Serial form of the Convolutional Neural Network (SCNN) as well as two other baseline studies: a Long- and Short-Term Memory (LSTM) neural network and a Conventional CNN (CCNN). We employed a well-known public dataset of heart sound signals: the Physionet heart sound. The accuracy of the PCNN, was estimated to be 87.2% which outperforms the rest of the three methods: the SCNN, the LSTM, and the CCNN by 12%, 7%, and 0.5%, respectively. The resulting method can be easily implemented in an Internet of Things platform to be employed as a decision support system for the screening heart abnormalities.

Ort, förlag, år, upplaga, sidor
IOS PRESS , 2023. Vol. 302, s. 526-530
Serie
Studies in Health Technology and Informatics, ISSN 0926-9630
Nyckelord [en]
Heart sound; convolutional neural networks; deep learning; intelligent phonocardiography; parallel convolutional neural network
Nationell ämneskategori
Datorsystem
Identifikatorer
URN: urn:nbn:se:liu:diva-197239DOI: 10.3233/shti230198ISI: 001071432900141PubMedID: 37203741ISBN: 9781643683898 (tryckt)OAI: oai:DiVA.org:liu-197239DiVA, id: diva2:1792366
Konferens
33rd Medical Informatics Europe Conference (MIE) - Caring is Sharing - Exploiting the Value in Data for Health and Innovation, European Federat Med Informat, Gothenburg, SWEDEN, may 22-25, 2023
Tillgänglig från: 2023-08-29 Skapad: 2023-08-29 Senast uppdaterad: 2024-01-22

Open Access i DiVA

fulltext(274 kB)23 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 274 kBChecksumma SHA-512
8c6f12e10c22e565b187d6474e83a1daf89ea41e1ece92d89c8a26c569219a83c7d752c521f08baa4bd99f209b9d861a998cbbfcc9318bc96be58ddb6fa5f8b4
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextPubMed

Person

Gharehbaghi, ArashBabic, Ankica

Sök vidare i DiVA

Av författaren/redaktören
Gharehbaghi, ArashBabic, Ankica
Av organisationen
Avdelningen för medicinsk teknikTekniska fakulteten
Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 23 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
pubmed
isbn
urn-nbn

Altmetricpoäng

doi
pubmed
isbn
urn-nbn
Totalt: 76 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf