Eduardo P. L. Jaqueira, Renato Candido, Magno T. M. Silva. Classificação de sinais de ECG sintéticos. Simpósio Brasileiro de Telecomunicações – SBrT’2024, 2024, Belém, Anais do SBrT 2024, 2024, pp. 1–2. (in portuguese)

Abstract

In this paper, synthetic electrocardiogram signals were generated using two generative models: one based on the generative adversarial network and other on the variational autoencoder. The synthetic signals were classified by a multilayer perceptron network trained with real signals. The correct classification rate of synthetic signals was superior to 80%, which indicates that these signals can be used to improve cardiac arrhythmia classification metrics.

Keywords

Machine learning, generative adversarial network, variational autoencoder, electrocardiogram, data augmentation

Downloads

• PDF