首页 | 本学科首页   官方微博 | 高级检索  
检索        

Elman神经网络在手足口病发病率预测中的应用初探
引用本文:张兴裕,冯海欢,肖雄,刘元元,李晓松.Elman神经网络在手足口病发病率预测中的应用初探[J].现代预防医学,2012,39(9):2136-2138,2141.
作者姓名:张兴裕  冯海欢  肖雄  刘元元  李晓松
作者单位:四川大学华西公共卫生学院卫生统计学教研室,成都,610041
基金项目:卫生公益性科研专项经费项目(200802133)
摘    要:目的探索Elman神经网络在传染病预测中的应用价值。方法利用2005年1月~2010年6月我国内地法定报告的手足口病月发病率资料分别构建Elman神经网络、BP神经网络以及季节性自回归移动平均模型(SARIMA),并对3种模型进行预测效果评价。结果 Elman神经网络的预测结果的平均绝对误差(MAE)及均方误差平方根(RMSE)均小于BP神经网络、SARIMA模型。结论 Elman神经网络的预测效果较好,对于手足口病发病率预测具有较好的应用价值。

关 键 词:Elman神经网络  BP神经网络  SARIMA  手足口病

Application of Elman Recurrent Neural Network in the incidence prediction of hand-foot-month disease
ZHANG Xing-yu , FENG Hai-huan , XIAO Xiong , LIU Yuan-yuan , LI Xiao-song.Application of Elman Recurrent Neural Network in the incidence prediction of hand-foot-month disease[J].Modern Preventive Medicine,2012,39(9):2136-2138,2141.
Authors:ZHANG Xing-yu  FENG Hai-huan  XIAO Xiong  LIU Yuan-yuan  LI Xiao-song
Institution:.Department of Medical Statistics,West China School of Public Health,Sichuan University,Chengdu,Sichuan 610041,China
Abstract:OBJECTIVE To explore the application value of Elman Recurrent Neural Networks(ERNN)in forecasting the incidence rate of HFMD per month in mainland China.METHODS ERNN,Back Propagation Neural Networks(BPNN)and SARIMA model were developed based on the monthly incidence of HFMD in mainland China from Jan.2005 to Jun.2010,and the prediction effect was estimated.RESULTS The MAE and RMSE of predicted values by ERNN were all lower than those obtained from BPNN and SARIMA model.CONCLUSION The forecasting efficiency of ERNN method is better than the BPNN and SARIMA model.The ERNN model can be applied to forecast the incidence of HFMD.
Keywords:Elman recurrent neural networks  BP neural networks  SARIMA  HFMD
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号