Alamsyah, Budi Prasetiyo, M. Faris Al Hakim, Fadli Dony Pradana
This paper is the result of research which is the development of previous research. In the previous studies, it was explained about the prediction of COVID-19 based on symptoms experienced in humans. The method used is Recurrent Neural Network (RNN) model. The level of accuraacy in COVID-19 prediction produced in previous studies was 88%. By using the same dataset, the optimal parameters of Maximum Epoch, Learning Rate, Hidden Node, and Momentum are applied to Recurrent Neural Network model. The result of this study indicates that there is an increase in accuracy to 90% with Maximum Epoch value is 400, Learning Rate value is 0.3, 7 Hidden Nodes, and Momentum value is 0.3. © 2023 Author(s).
Department of Computer Science, Universitas Negeri Semarang, Semarang, Indonesia
