Classification of Premature Ventricular Contraction (PVC) based on ECG Signal using Convolutional Neural Network

Jondri Jondri, Achmad Rizal


ECG signal can provide the information about the heart health of a person. Analysis on ECG signal can be visually conducted by a doctor by examining the form, rhythm and orientation of ECG signal. A number of digital signal processing methods have been developed to automatically detect any abnormalities in ECG signal. This research used the Premature Ventricular Contraction (PVC) on ECG signal. The input data were in the form of both one cycle of normal ECG signal or PVC. The classification used the convolutional neural network without any use of feature extraction. The highest accuracy obtained was 99.59% with the 5-fold cross-validation. This result was obtained from the test using 11361.


Electrocardiogram; PVC; CNN; Deep learning; Signal processing

Full Text: PDF


  • There are currently no refbacks.


Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
ISSN 2089-3272

Creative Commons Licence

This work is licensed under a Creative Commons Attribution 4.0 International License.

web analytics
View IJEEI Stats