论文部分内容阅读
目的:比较ARIMA模型、BPNN模型和ARIMA-ERNN组合模型在我国甲肝发病率预测中的应用效果,探讨预测甲肝发病率的优化模型。方法:收集2004年1月至2015年12月我国甲肝发病率资料,用SPSS 17.0和Eviews 8.0建立ARIMA模型,用Matlab 8.0建立BPNN模型和ARIMA-ERNN组合模型,并对模型的预测效果进行评价。结果:ARIMAERNN组合模型拟合及预测的MRE、MER、MSE、RMSE、MAE均小于ARIMA模型和BPNN模型,其MRE均小于5%。结论:ARIMA-ERNN组合模型对我国甲肝发病率的拟合及预测效果优于ARIMA模型和BPNN模型。
OBJECTIVE: To compare the application effects of ARIMA model, BPNN model and ARIMA-ERNN combined model in predicting the incidence of hepatitis A in China, and to explore the optimal model for predicting the incidence of hepatitis A. Methods: The data of incidence of hepatitis A in our country from January 2004 to December 2015 were collected. The ARIMA model was established with SPSS 17.0 and Eviews 8.0. The combined model of BPNN and ARIMA-ERNN was established by Matlab 8.0, and the predictive effect of the model was evaluated. Results: MRE, MER, MSE, RMSE and MAE fitted and predicted by ARIMAERNN combined model were all less than those of ARIMA model and BPNN model with MRE less than 5%. Conclusion: The ARIMA-ERNN combination model is superior to ARIMA model and BPNN model in predicting the incidence of hepatitis A in our country.