Experimental Studies for the Application of deep learning Models in Forecasting Infection of COVID-19
Naoki Dohi, Yukinobu Hoshino · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · 2023
This study predicts and forecasts daily positive COVID-19 counts. In the epidemic fields, statistical methods are typically used. However, recently, machine learning is being applied. The appropriate model is different in each country because of differences in measurement methods and nationality. Thus, an adequate model needs to be evaluated and selected for use in Japan. Hence, in this paper, RNNs were trained with two loss functions, MSE and AIC, and then evaluated and compared based on ARIMA. The comparison results show a 49.5% reduction of RNN from the ARIMA’s RMSE. Seq2Seq has an R2=0.92. Moreover, this paper presents the comparison results of an RNN with the others models.