Abstract:

COVID-19 is a critical and fatal disease, which was declated as the global pandemic. In this process in which the global pandemic state is alive, it is too important to make specific policies and plans to face the pandemic. Using COVID-19 verified data and making predictions with artificial intelligence techniques is an important issue as it allows deriving of future plans. In this study, Turkey's Health Ministry COVID-19 in the informational pages published using data, adaptive neuro-fuzzy inference system (ANFIS), and the artificial neural network (ANN) prediction models have been developed. These models were compared using different statistical evaluation criteria. As a result of the evaluation, the ANFIS model obtained the best model results with 0.0247 mean absolute error (MAE) value, 0.0012 mean square error (MSE) value, 0.0351 root mean square error (RMSE) value and 0.9847 regression coefficient R2. In addition, it was seen that the model created with ANFIS showed a better performance and predicted the number of deaths in the next five days with an accuracy rate of 96%.