关键词: 气象因素, 虫媒传染病, 反馈神经网络

Abstract: Objective To investigate the relationship between meteorological factors and incidence of arbo infectious disease,including endemic encephalitis B and endemic typhus,to built the Back-Propagation artificial neural network model and evaluate it. Methods The data of incidence of cerebrospinal meningitis and meteorological factors from 1981 to 1994 were collected and analyzed by SPSS for windows version 10.0; The model of Back-Propagation artificial neural network was built by Matlab,version 6.5. Results The incidences of endemic encephalitis B was negative correlated to annual mean atmospheric pressure ( P< 0.01),and was positive correlated to annual mean evaporation and the maximum temperature ( P< 0.05). The incidences of endemic typhus was negative correlated to annual mean temperature,the groud temperature( P< 0.05) and the minimum temperature ( P= 0.062). The MER and R² of endemic encephalitis B and endemic typhus model were 27.44%,98.09%and 29.00%,65.35%respectively. The relative error of endemic encephalitis B and endemic typhus was 80.00%and 120.86%respectively. Conclusion The incidence of arbo infectious disease is correlated to atmospheric pressure,evaporation,and temperature. The BP neural network model fits commonly for the study of arbo infectious diseases and needs further study.