干旱地区伤寒副伤寒与气象因素关系的BP神经网络模型  

The Model of Back-Propagation Neural Network about Meteorological Factors and Typhoid Fever,Paratyphoid Fever in drought area

作　　者：曲波[1] 黄德生[1] 郭海强[1] 周宝森[1] 董存华 卢景华 

机构地区：[1]中国医科大学公共卫生学院 [2]沈阳市大东区疾病预防控制中心 [3]辽阳市白塔区疾病预防控制中心

出　　处：《中国卫生统计》2004年第3期165-167,共3页Chinese Journal of Health Statistics

基　　金：国家自然基金资助 (课题编号 :30 1 70 833)

摘　　要：目的　应用人工神经网络的原理和方法 ,探讨在干旱灾害条件下影响伤寒副伤寒流行的关键气象因子 ,建立旱灾地区传染病疫情的BP神经网络模型 ,并评价模型的拟合效果。方法　利用Matlab 6 5软件对人工神经网络BP模型进行构建、训练及模拟。结果　伤寒副伤寒发病率回代平均误差率和R2 分别为 0 84%和 0 9999。自变量对输出的贡献量分析结果显示 ,平均蒸发量和平均气压对于伤寒副伤寒发病率影响最大。结论　伤寒副伤寒与气象因素关系的BP神经网络模型拟合效果较好 。Objective To investigate the relations between meteorological factors and typhoid fever and paratyphoid fever,Back Propagation artificial neural network model was built and evaluated.Methods Back Propagation artificial neural network model was built by Matlab,version 6.5.Results The Mean Error Rate and R 2 was 0 84% and 0 999 respectively. The mean evaporation and mean air pressure were correlation to the incidence of typhoid fever and paratyphoid fever.Conclusion The BP Neural Network model has practical value to popularize in simulation of situation between meteorological factors and infectious disease in drought area.

关 键 词：干旱地区 副伤寒 气象因素 BP神经网络模型 神经网络 神经冲动 

分 类 号：R188[医药卫生—流行病学]