中国媒介生物学及控制杂志

• 论著 • 上一篇    下一篇

应用BP人工神经网络模型预测肾综合征出血热发病率

吴泽明1,2;吴伟1;王萍2;周宝森1   

  1. 1中国医科大学流行病学教研室 沈阳110001;2沈阳市疾病预防控制中心
  • 出版日期:2006-06-20 发布日期:2006-06-20

Prediction for Incidence of Hemorrhagic Fever with Renal Syndrome with Back Propagation Artificial Neural Network Model

WU Ze-ming; WU Wei; WANG Ping; ZHOU Bao-sen   

  1. Shenyang Municipal Center for Disease Control and Prevention, Shenyang 110001, China
  • Online:2006-06-20 Published:2006-06-20

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。

关键词: BP人工神经网络, 肾综合征出血热, 发病率, 预测

Abstract: 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