论文部分内容阅读
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 application of BP neural network in the prediction model of cholera epidemic and provide a scientific basis for the prevention and control of cholera. Methods The neural network toolbox in Matlab7.2 package was used to establish the BP neural network model of epidemic of cholera in Fuzhou from 1978 to 2004, and the prediction accuracy was verified by data from 2002 to 2004. Results After neural network learning and training, the training error decreased and stabilized. The correlation coefficient was 0.816 and the prediction accuracy of the model was 80.56%. Conclusion BP neural network modeling between meteorological elements and cholera is feasible and can be used as a method to predict the epidemic of cholera.