| ARIMA时间序列和BP神经网络在传染病预测中的比较 |
| |
| 引用本文： | 董选军,贾伟娜.ARIMA时间序列和BP神经网络在传染病预测中的比较[J].现代实用医学,2010,22(2):142-143,147,F0004. |
| |
| 作者姓名： | 董选军 贾伟娜 |
| |
| 作者单位： | 1. 宁波市镇海区疾病预防控制中心,浙江宁波,315200
2. 宁波大学,浙江宁波,315020 |
| |
| 摘 要： | 目的比较自回归滑动平均时间序列模型和神经网络对传染病的预测效率。方法根据1985—2004年伤寒、副伤寒按季度发病率数据资料，利用dps7．55软件中的ARIMA时间序列、神经网络建立预测模型，用2005--2007年的伤寒、副伤寒季度发病率对二种预测模型进行检验，从而比较二种模型的优劣。结果用ARIMA时间序列分析得到拟合度为50．15％，验证模型的残差平方和为5154．381用神经网络分析得到拟合度为73．12％，验证模型的残差平方和为3559．24。结论神经网络模型更为适用于预测宁波市镇海区伤寒、副伤寒发病趋势。
|
| 关 键 词： | 伤寒 副伤寒 自回归滑动平均时间序列模型 神经网络 预测 |
Predictive efficiency comparison of ARIMA-time-series and BP neural net model on infectious diseases |
| |
| DONG Xuanjun,JIA Weina.Predictive efficiency comparison of ARIMA-time-series and BP neural net model on infectious diseases[J].Modern Practical Medicine,2010,22(2):142-143,147,F0004. |
| |
| Authors: | DONG Xuanjun JIA Weina |
| |
| Institution: | 1.Zhenhai district center for disease control and prevention/a>;Ningbo315200/a>;2. Ningbo university/a>;Ningbo 315200. |
| |
| Abstract: | Objective To compare the predictive efficiency of ARIMA-time-series model and neural net model. Methods According to typhoid and paratyphoid seasonal incidence from 1985 to 2004 in Zhenhai district,pre-diction models were established by ARIMA-time-series model and neural net model.The two prediction models were assessed by typhoid and paratyphoid seasonal incidence from 2005 to 2007.Results The fitness index of ARIMA-time-series model was 51.2%,and the index of neural net model was 80.6%.The sum of residual... |
| |
| Keywords: | Typhoid fever Paratyphoid ARIMA-time-series Neural net Prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
