COVID-19 Pandemic Prediction Using Hyper-Parameter-Tuned ANN, Bi-LSTM, and Stacked-LSTM in Türkiye

COVID-19 first appeared in China in December 2019. In Türkiye, the first case was seen on March 11, 2020. Since the emergence of COVID-19, it has rapidly affected the world and caused the death of many people. The rapid spread of the virus around the world and the fact that it poses a global threat have made it mandatory for the authorities to take quick measures and decisions. For this reason, the diagnosis, treatment, and prediction of the number of cases of COVID-19 disease is a vital issue. In this paper, daily deaths, daily cases, cumulative deaths, and cumulative case numbers were predicted using Türkiye's COVID-19 data. The prediction analysis for COVID-19 was conducted employing artificial intelligence (AI) techniques, specifically Stacked Long-Short Term Memory (Stacked-LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Artificial Neural Network (ANN) methods. Hyperparameter optimization using the Gray Wolf Optimizer Algorithm (GWO) was applied to optimize these models. To assess the accuracy and efficacy of prediction models, various performance metrics were employed, including Mean Absolute Percentage Error (MAPE), Coefficient of Determination (R^2 Score), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Explained Variance Score (EVS). The assessment of the accuracy and efficacy of the pandemic prediction models involved comparing the predicted data values with the actual values. Based on this analysis, the prediction model that exhibited the highest degree of similarity to the actual values was determined to be the most reliable and effective.