Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/90394
Título: | Electrocardiogram beat-classification based on a ResNet network |
Autor(es): | Brito, Cláudia Vanessa Martins Machado, Ana Sousa, António |
Palavras-chave: | Electrocardiogram Deep Learning Arrhythmia |
Data: | 2019 |
Editora: | IOS Press |
Revista: | Studies in Health Technology and Informatics |
Resumo(s): | When dealing with electrocardiography (ECG) the main focus relies on the classification of the heart's electric activity and deep learning has been proving its value over the years classifying the heartbeats, exhibiting great performance when doing so. Following these assumptions, we propose a deep learning model based on a ResNet architecture with convolutional ID layers to classes the beats into one of the 4 classes: normal, atrial premature contraction, premature ventricular contraction and others. Experimental results with MIT-BIH Arrhythmia Database confirmed that the model is able to perform well, obtaining an accuracy of 96% when using stochastic gradient descent (SGD) and 83% when using adaptive moment estimation (Adam), SGD also obtained F1-scores over 90% for the four classes proposed. A larger dataset was created and tested as unforeseen data for the trained model, proving that new tests should be done to improve the accuracy of it. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/90394 |
ISBN: | 978-1-64368-002-6 |
DOI: | 10.3233/SHTI190182 |
ISSN: | 0926-9630 |
e-ISSN: | 1879-8365 |
Arbitragem científica: | yes |
Acesso: | Acesso restrito UMinho |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
SHTI-264-SHTI190182 (2).pdf Acesso restrito! | 352,41 kB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons