论文部分内容阅读
[目的]探索BP神经网络在细菌性痢疾预测模型的应用,为细菌性痢疾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1988～2007年的资料建立福州市山区菌痢流行的BP神经网络模型,并以2008年的资料验证其预测成功率。[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0.815,模型的预测成功率为10/12。[结论]BP神经网络在气象要素与菌痢发病之间建模是可行的,可以作为预测菌痢流行的一种新方法。
[Objective] The research aimed to explore the application of BP neural network in the prediction model of bacillary dysentery and provide a scientific basis for the prevention and control measures of bacillary dysentery. [Methods] The BP neural network model of bacillary dysentery in mountainous area of Fuzhou was established by neural network toolbox in Matlab7.2 software package from 1988 to 2007, and its prediction success rate was verified by the data from 2008. [Result] After learning and training neural network, the training error decreased and stabilized. The correlation coefficient was 0.815 and the prediction success rate was 10/12. [Conclusion] BP neural network was feasible to model the relationship between meteorological elements and dysentery and could be used as a new method to predict the prevalence of bacillary dysentery.