智能神经网络模型用于气象因素对疟疾发病影响的初步研究

高春玉; 熊鸿燕; 易东; 柴光军; 杨小为; 刘莉

Abstract

高春玉,熊鸿燕,易东,柴光军,杨小为,刘莉.智能神经网络模型用于气象因素对疟疾发病影响的初步研究[J].Chinese journal of Epidemiology,2003,24(9):831-834

智能神经网络模型用于气象因素对疟疾发病影响的初步研究

Study on meteorological factors-based neural network model of malaria

Received:January 03, 2003

DOI：

KeyWord: 疟疾气象因素神经网络模型流行病学

English Key Word: Malaria Meteorological factors Neural network model Epidemiology

FundProject:

Author Name	Affiliation
GAO Chun-yu	Airforce Center for Diseases Control, Sanitation and Anti-epidemic Team, Logistics Department, Airforce, Beijing 100076, China
XIONG Hong-yan	第三军医大学流行病学教研室
YI Dong	第三军医大学统计学教研室
CHAI Guang-jun	空军后勤部卫生防疫队疾病监控室, 北京 100076
YANG Xiao-wei	空军后勤部卫生防疫队疾病监控室, 北京 100076
LIU Li	空军后勤部卫生防疫队疾病监控室, 北京 100076

Hits: 3741

Download times: 1158

Abstract:

目的　建立气象因素与疟疾的智能神经网络预测模型。方法　利用Matlab 6.1软件中的神经网络工具箱,根据预实验结果,利用云南省红河地区 1994～ 1999年月平均气压、月平均气温、月最高气温、月最低气温、月降水量、月降水日数、月平均相对湿度、月蒸发量、月日照时数等气象数据与疟疾发病率等级数据建立反向传播网络 (BP网络 )预测模型,并对模型进行验证。结果　神经网络经10 0次学习和训练,训练误差从 3.2 36 0 8下降至 0.0 35 86 2,通过建立的智能神经网络模型对未来疟疾发病率进行预测,其预测符合率为 84.85 %。结论　智能神经网络在气象因素与疟疾之间建模是可行的,其预测符合率达 80 %以上。智能神经网络具有综合能力强,对数据的要求不高,适时学习等突出优点,且操作简便,节省时间,易于掌握和应用。研究中数据的应用、纳入、排出等问题有待于进一步研究。智能神经网络模型可以作为疟疾预测的一种新方法。

English Abstract:

Objective In order to provide reliable data for strategies development on prevention, a meteorological factors-based predicating model for malaria forecast was studied. Methods Data on malaria occurrence and climate changes from 1994 to 1999 in counties in Yunnan province was collected and analyzed with software packages of FoxPro 6.0 and Excel 5.0. The forecasting model for malaria occurrence was established, using the Neural Network Toolbox of Matlab 6.1 software package.In the studies of forecasting model, data of malaria and meteorological factors from 1994 to 1999 in Honghe state in Yunnan province was chosen.The meteorological factors included average monthly pressure,air temperature,relative humidity,monthly maximum air temperature,minimum air temperature,rainfall,rainday,evaporation and sunshine hours in the study.The established forecasting model was also tested and verified. Results The BP network model was established according to data of diseases and meteorological factors from Honghe state in Yunnan province.After training the neural network for 100 times, the error of performance decreased from 3.236 08 to 0.035 862. Verified by fact data of malaria, the efficiency of malaria forecasting was 84.85 %. Conclusion Neural network model was effective for forecasting malaria. It showed advantages as: strong ability for analysis, lower claim for data, convenient and easy to apply etc.Neural network model might be used as a new method for malaria forecasting.

View Fulltext Html FullText View/Add Comment Download reader