This paper puts forward a 1-D convolutional neural network (CNN) that exploits a novel analysis of the correlation between the two leads of the noisy electrocardiogram (ECG) to classify heartbeats. The proposed method is one-dimensional, enabling complex structures while maintaining a reasonable computational complexity. It is based on the combination of elementary handcrafted time domain features, frequency domain features through spectrograms and the use of autoregressive modeling. On the MIT-BIH database, a 95.52% overall accuracy is obtained by classifying 15 types, whereas a 95.70% overall accuracy is reached when classifying 7 types from the INCART database.

Tanoh, I., Napoletano, P. (2021). A novel 1-d ccanet for ecg classification. APPLIED SCIENCES, 11(6) [10.3390/app11062758].

A novel 1-d ccanet for ecg classification

Napoletano P.
2021

Abstract

This paper puts forward a 1-D convolutional neural network (CNN) that exploits a novel analysis of the correlation between the two leads of the noisy electrocardiogram (ECG) to classify heartbeats. The proposed method is one-dimensional, enabling complex structures while maintaining a reasonable computational complexity. It is based on the combination of elementary handcrafted time domain features, frequency domain features through spectrograms and the use of autoregressive modeling. On the MIT-BIH database, a 95.52% overall accuracy is obtained by classifying 15 types, whereas a 95.70% overall accuracy is reached when classifying 7 types from the INCART database.
Articolo in rivista - Articolo scientifico
Canonical correlation analysis (CCA); Convolutional neural network (CNN); Heartbeat classification;
English
19-mar-2021
2021
11
6
2758
open
Tanoh, I., Napoletano, P. (2021). A novel 1-d ccanet for ecg classification. APPLIED SCIENCES, 11(6) [10.3390/app11062758].
File in questo prodotto:
File Dimensione Formato  
10281-318876_VoR.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 401.35 kB
Formato Adobe PDF
401.35 kB Adobe PDF Visualizza/Apri

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/10281/318876
Citazioni
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 7
Social impact