肾综合征出血热发病率的ANN预测模型

Predictive model of BP artificial neural network for HFRS incidence

目的 :探讨ANN时间序列预测模型在疾病发病率或死亡率预测上的应用前景。方法 :利用动态学习比率BP算法以双曲正切函数为功能函数的非线性时间序列预测方法。结果 :建立HFRS发病率的ANN预测模型 ,其预测精度高。结论

Objective: To explore the prospect of predicting disease incidence of the predictive model of nonlinear time series by BP neural network. Method: Based on dynamic error correction BP artificial neural network with Hyperbolic Tangent function as activation function and the number of hidden node six. Result: ANN forecast model of HFRS incidence was built with high prediction precision. Conclusion: BP artificial neural network can be used to forecast for disease incidence or mortality.