The Influence Of Meteorological Factors On Various Infectious Diseases In Singapore

Infectious diseases are a type of disease that can make many people sick in a short period of time,posing a serious and even life-threatening risk to human health and life.Some infectious diseases spread very quickly and can threaten the whole community,leading to sudden outbreaks of disease,such as the new coronavirus pneumonia in the last two years,It is therefore essential that infectious diseases are controlled in a timely manner to prevent panic among the population.Therefore,in this paper,by collecting meteorological factors(daily rainfall,maximum30-minute rainfall,maximum 60-minute rainfall,maximum 120-minute rainfall,average temperature,maximum temperature,minimum temperature,average wind speed,maximum wind speed)and the number of incidences of different types of infectious diseases in Singapore from 2012 to 2020,descriptive statistical analysis,correlation analysis and principal A generalised linear model was constructed and analysed to reveal the degree of influence of meteorological factors on different infectious diseases,and a suitable ARIMA model and BP neural network model were constructed for prediction by smoothing the data on the monthly incidence of each infectious disease.The study concluded that meteorological factors had a significant impact on the number of incidences of most infectious diseases,and the degree and direction of the same meteorological factor on different infectious diseases were different,with temperature and wind speed having the greatest impact on dengue fever,both of which were positive;temperature had the greatest impact on salmonella infection(non-typhoid),showing a positive impact;temperature and wind speed had the greatest impact on campylobacter enteritis,showing a positive impact;and meteorological factors had a significant impact on the number of incidences of basal diseases.However,after Poisson fitting the number of infectious disease cases,the effect of meteorological factors on typhoid fever was found to be insignificant,pending rigorous multidimensional analysis;and it was concluded that dengue fever,campylobacter enteritis,measles,and salmonella infections(non-typhoid)had a positive effect.,and Salmonella infection(non-typhoid)were ARIMA prediction models as ARIMA(1,1,1),ARIMA(6,1,1),ARIMA(1,1,2),and ARIMA(1,1,1),and Back-Propagation neural network model for dengue fever was a learning rate taking a value of 0.65,a weight of 5 for the output layer neurons,and a training count of 500.