Chin J Schisto Control ›› 2016, Vol. 28 ›› Issue (6): 630-634.

Previous Articles     Next Articles

Prediction of schistosomiasis infection rates of population based on ARIMA-NARNN model

WANG Ke-wei| WU Yu| LI Jin-ping| JIANG Yu-yu*   

  1. Wuxi Medical College| Jiangnan University| Wuxi 214122| China
  • Online:2016-12-11 Published:2016-12-11
  • Contact: JIANG Yu?yu

基于ARIMA-NARNN组合模型的血吸虫感染率预测研究

王克伟|吴郁|李金平|蒋玉宇*   

  1. 江南大学无锡医学院(无锡 214122)
  • 通讯作者: 蒋玉宇
  • 作者简介:王克伟|男|博士|讲师。研究方向:流行病与卫生统计学
  • 基金资助:

    国家自然科学基金(81200645)

Abstract:

Objective To explore the effect of the autoregressive integrated moving average model?nonlinear auto?regressive neural network (ARIMA?NARNN) model on predicting schistosomiasis infection rates of population. Methods The ARIMA model, NARNN model and ARIMA?NARNN model were established based on monthly schistosomiasis infection rates from January 2005 to February 2015 in Jiangsu Province, China. The fitting and prediction performances of the three models were compared. Results Compared to the ARIMA model and NARNN model, the mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the ARIMA?NARNN model were the least with the values of 0.011 1, 0.090 0 and 0.282 4, respectively. Conclusion The ARIMA?NARNN model could effectively fit and predict schistosomiasis infection rates of population, which might have a great application value for the prevention and control of schistosomiasis.

Key words: Autoregressive integrated moving average model (ARIMA); Nonlinear auto?regressive neural network (NARNN); Time series; Schistosomiasis; Prediction

摘要:

目的 探讨ARIMA?NARNN组合模型预测血吸虫感染率的有效性。 方法 利用2005年1月至2015年2月江苏省血吸虫感染率资料分别建立ARIMA模型、NARNN模型和ARIMA?NARNN组合模型,比较各模型的拟合和预测效果。 结果 相比较ARIMA模型和NARNN模型,ARIMA?NARNN组合模型预测样本的MSE、MAE和MAPE均最小,分别为0.011 1、0.090 0和0.282 4。 结论 ARIMA?NARNN组合模型能有效模拟和预测血吸虫感染率,具有较好的推广应用价值。

关键词: 自回归滑动平均模型;非线性自回归神经网络;时间序列;血吸虫病;预测

CLC Number: