CAJ | 학술논문

目的：比较Elman神经网络模型与自回归移动平均（ ARIMA）模型对流感发病率预测的效果。方法：选取河南省2006年1月至2010年12月的流感疫情资料作为训练集，2011年1月至12月的流感疫情资料作为检验集，前者用于Elman神经网络模型和最优ARIMA模型的建立，后者用于两种模型的预测效能的检验与评价。结果：在最优ARIMA（1，0，0）模型和最优Elman神经网络预测模型下，检验集预测值的平均误差绝对值、平均误差绝对率和非线性相关系数分别为0．133、0．238、0．708和0．152、0．271、0．725。结论：Elman神经网络模型具有与ARIMA模型相近的预测效能，在流感发病率预测中有较好的应用价值。
목적：비교Elman신경망락모형여자회귀이동평균（ ARIMA）모형대류감발병솔예측적효과。방법：선취하남성2006년1월지2010년12월적류감역정자료작위훈련집，2011년1월지12월적류감역정자료작위검험집，전자용우Elman신경망락모형화최우ARIMA모형적건립，후자용우량충모형적예측효능적검험여평개。결과：재최우ARIMA（1，0，0）모형화최우Elman신경망락예측모형하，검험집예측치적평균오차절대치、평균오차절대솔화비선성상관계수분별위0．133、0．238、0．708화0．152、0．271、0．725。결론：Elman신경망락모형구유여ARIMA모형상근적예측효능，재류감발병솔예측중유교호적응용개치。
Aim:To compare the efficiency of Elman neural network model and autoregressive integrated moving aver -age( ARIMA) model to predict the incidence of influenza .Methods:Elman neural network model and ARIMA model were established using the epidemic data of influenza in Henan Province from January 1, 2006 to December 31, 2010, and the predictive performance was measured and accessed using the data from January 1 to December 31, 2011.Results:The op-timal ARIMA model was ARIMA(1,0,0)model, the optimal Elman neural network model was 4-12-1-1.The mean abso-lute error ( MAE) , mean error rate ( MER) and nonlinear correlation coefficient ( RNL) of prediction results of the test set using the optimal ARIMA model and Elman neural network model were 0.133, 0.238, 0.708 and 0.152, 0.271, 0.725, respectively.Conclusion:The predictive efficiency of models based on time series and Elman neural network model is e -quivalent ,and they perform well in predicting the incidence of influenza .