神经网络技术在霍乱流行预测模型中的应用

Prediction of transmission of cholera by BP neural network model

目的探索BP神经网络在霍乱流行预测模型的应用,为制定霍乱的预防控制措施提供科学依据。方法用Matlab7.2软件包中的神经网络工具箱,以1978—2004年的资料建立福州市霍乱流行的BP神经网络模型,并以2002~2004年的资料验证其预测精度。结果神经网络经学习和训练,训练误差下降并趋于稳定,回代相关系数为0.816,模型的预测精度为80.56%。结论 BP神经网络在气象要素与霍乱之间建模是可行的,可以作为预测霍乱流行的一种方法 。

Objective to explore the prediction of transmission of cholera by BP neural network model so as to provide the evidence for formulating the preventive strategy of cholera.Methods The forecasting model for cholera occurrence was established by using the neural network toolbox of Matlab 7.2 software package.In the studies of forecasting model,the data from 1978 to 2004 in Fuzhou City were chosen.The established forecasting model was tested by the data of cholera from 2002 to 2004.Results After training the neural network,the error of performance decreased and the coefficient of regression was 0.816.The efficiency of the model＇s forecasting for cholera was 80.56%.Conclusions the BP neural network model is feasible to analyze the relationship between the meteorological factors and cholera.Therefore,the BP neural network model could be used as an effective method for forecasting cholera.