This paper deals with the ECG classification of arrhythmias by using a 1-D convolutional neural network. The input is given by the combination of several databases from Physionet and is composed of two leads, LEAD1 and LEAD2. Data are not preprocessed, and no feature extraction has been per-formed, except for the medical evaluation in order to label it. The test accuracy of our neural approach is very high. However, the goal of this work is also the interpretation not only of the results, but also of the behavior of the neural network, by means of correlation analysis and symbolic regression.

1-D Convolutional Neural Network for ECG Arrhythmia Classification / Ferretti, Jacopo; Randazzo, Vincenzo; Cirrincione, Giansalvo; Pasero, Eros (SMART INNOVATION, SYSTEMS AND TECHNOLOGIES). - In: Progresses in Artificial Intelligence and Neural Systems / Esposito A., Faundez-Zanuy M., Morabito F., Pasero E.. - ELETTRONICO. - [s.l] : Springer Singapore, 2020. - ISBN 978-981-15-5093-5. - pp. 269-279 [10.1007/978-981-15-5093-5_25]

1-D Convolutional Neural Network for ECG Arrhythmia Classification

Jacopo Ferretti;Vincenzo Randazzo;Giansalvo Cirrincione;Eros Pasero
2020

Abstract

This paper deals with the ECG classification of arrhythmias by using a 1-D convolutional neural network. The input is given by the combination of several databases from Physionet and is composed of two leads, LEAD1 and LEAD2. Data are not preprocessed, and no feature extraction has been per-formed, except for the medical evaluation in order to label it. The test accuracy of our neural approach is very high. However, the goal of this work is also the interpretation not only of the results, but also of the behavior of the neural network, by means of correlation analysis and symbolic regression.
2020
978-981-15-5093-5
978-981-15-5092-8
Progresses in Artificial Intelligence and Neural Systems
File in questo prodotto:
File Dimensione Formato  
Wirn2019_ECG_DeepLearning_abstract.pdf

accesso aperto

Tipologia: Abstract
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 36.12 kB
Formato Adobe PDF
36.12 kB Adobe PDF Visualizza/Apri
Wirn2019_ECG_DeepLearning_v5_final.pdf

Open Access dal 11/07/2022

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 533.4 kB
Formato Adobe PDF
533.4 kB Adobe PDF Visualizza/Apri
bookExtracted_1-D Convolutional Neural Network for ECG Arrhythmia Classification.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 752.78 kB
Formato Adobe PDF
752.78 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2759793