Using an Artificial Neural Network Model to Predict the Number of COVID-19 Cases in Iran

Background: Forecasting methods are used in various fields including the health problems. This study aims to use the Artificial Neural Network (ANN) method for predicting coronavirus disease 2019 (COVID-19) cases in Iran. Materials and Methods: This is a descriptive, analytical, and comparative stud...
Ausführliche Beschreibung

Background: Forecasting methods are used in various fields including the health problems. This study aims to use the Artificial Neural Network (ANN) method for predicting coronavirus disease 2019 (COVID-19) cases in Iran. Materials and Methods: This is a descriptive, analytical, and comparative study to predict the time series of COVID-19 cases in Iran from May 2020 to May 2021. An ANN model was used for forecast​ing, which had three Input, output, and intermediate layers. The network training was conducted by the Levenberg-Marquardt algorithm. The forecasting accuracy was measured by calculating the mean absolute percentage error. Results: The mean absolute error of the designed ANN model was 6 and its accuracy was 94%. Conclusion: The ANN has high accuracy in forecasting the number of COVID-19 cases in Iran. The outputs of this model can be used as a basis for decisions in controlling the COVID-19. Ausführliche Beschreibung