We have designed and evaluated a new Artificial Neural Network (ANN) structure, builded as an autoassociator, to classify some rhythm abnormalities of a single patient. We used a standard database (BIH-MIT) for the testing phase. The network is fed to reproduce the input pattern morphology over a part of the output layer and to give the pattern class over the remaining part. We have defined two uncertainty criteria to reject unknown or uncertain patterns. The recognition percentages were very good for normal vs. PVB beats (99.84% normal vs. 92.96% PVB) and a little worse for normals vs. APB's (97.71% normal vs. 93.44% APB). The error we found was as small as 0.15% for PVB beats, and 0.91% for APB's.

R., S., Gori, M., C., M. (1993). Autoassociator structured neural network for rhythm classification of long term electrocardiogramProceedings of Computers in Cardiology Conference. In Proceedings of Computers in Cardiology Conference (pp.349-352). Los Alamitos : IEEE [10.1109/CIC.1993.378432].

Autoassociator structured neural network for rhythm classification of long term electrocardiogramProceedings of Computers in Cardiology Conference

GORI, MARCO;
1993-01-01

Abstract

We have designed and evaluated a new Artificial Neural Network (ANN) structure, builded as an autoassociator, to classify some rhythm abnormalities of a single patient. We used a standard database (BIH-MIT) for the testing phase. The network is fed to reproduce the input pattern morphology over a part of the output layer and to give the pattern class over the remaining part. We have defined two uncertainty criteria to reject unknown or uncertain patterns. The recognition percentages were very good for normal vs. PVB beats (99.84% normal vs. 92.96% PVB) and a little worse for normals vs. APB's (97.71% normal vs. 93.44% APB). The error we found was as small as 0.15% for PVB beats, and 0.91% for APB's.
1993
0818654708
R., S., Gori, M., C., M. (1993). Autoassociator structured neural network for rhythm classification of long term electrocardiogramProceedings of Computers in Cardiology Conference. In Proceedings of Computers in Cardiology Conference (pp.349-352). Los Alamitos : IEEE [10.1109/CIC.1993.378432].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11365/36653
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo