摘要
目的探讨反馈（BP）人工神经网络模型预测肾综合征出血热（HFRS）发病率的应用前景.方法利用沈阳市的气象资料（包括平均气温、相对湿度、降水量和日照）和动物疫情资料（包括鼠密度和鼠带病毒率）共6个指标作为神经网络的输入,将1984～2003年沈阳市HFRS发病率作为神经网络的输出.选择1984～2001年的数据,利用STATISTICA Neural Network（ST NN）建立BP网络预测模型,然后训练网络、预测2002和2003年HFRS的发病率.同时用上述指标建立线性预测模型,其结果与神经网络模型进行比较.结果对于BP神经网络,其平均误差率为7.89%,非线性相关系数为0.896.对于线性回归模型,其平均误差率为24.78%,非线性相关系数为0.711.结论BP人工神经网络可以用于HFRS发病率的预测,效果好于传统的线性回归方法.
Objective To study the application of back propagation （BP） artificial neural network model in prediction for incidence of hemorrhagic fever with renal syndrome （HFRS）. Methods Meteorological data, including average temperature, relative humidity, precipitation and sunshine time, obtained from Shenyang Municipal Meteorological Bureau, and epidemiologic information of animal diseases, including rat density and viral carriage of rats obtained from Shenyang Municipal Center for Disease Control and Prevention, were collected as input of artificial neural networks. And, incidence data of HFRS in Shenyang during 1984 to 2003 were collected as output of artificial neural networks. A predictive model of BP artificial neural networks was established using the data during 1984 to 2001 with STATISTICA Neural Network （ST NN） software. The artificial neural network with data set was trained and verified to predict incidence of HFRS in 2002 and 2003. Meanwhile, a linear predictive model was established with the data mentioned above, and results obtained from artificial neural network model and linear regression model was compared. Results Average error rate for BP artificial neural network model was 7.89 %, with a non-linear coefficient of correlation of 0,896, and those for linear regression model was 24,78% and 0.711, respectively. Conclusion BP artificial neural network model can be used in predicting incidence of HFRS, with a better result than that of traditional linear regression model.
出处
《中国媒介生物学及控制杂志》
CAS
CSCD
北大核心
2006年第3期223-226,共4页
Chinese Journal of Vector Biology and Control
基金
国家自然科学基金资助项目(30170833)
关键词
BP人工神经网络
肾综合征出血热
发病率
预测
Back propagation artificial neural network
Hemorrhagic fever with renal syndrome
Incidence rate
Prediction
