Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China

摘要: Background Cases of hemorrhagic fever with renal syndrome (HFRS) are widely distributed in eastern Asia, especially China, Russia, and Korea. It is proved to be a difficult task eliminate HFRS completely because the diverse animal reservoirs effects global warming. Reliable forecasting useful for prevention control HFRS. Methods Two hybrid models, one composed nonlinear autoregressive neural network (NARNN) integrated moving average (ARIMA) other generalized regression (GRNN) ARIMA were constructed predict incidence future year. Performances two models compared model. Results The ARIMA, ARIMA-NARNN ARIMA-GRNN model fitted predicted seasonal fluctuation well. Among three mean square error (MSE), absolute (MAE) percentage (MAPE) was lowest both modeling stage stage. As model, MSE, MAE MAPE performance MSE less than but did not improve. Conclusion Developing applying an effective method make us better understand epidemic characteristics could helpful HFRS.