DOI: 10.36347/sjpms.2020.v07i05.002

Pages: 56-61

Aiming at the complexity and correlation characteristics of infectious disease prevalence evaluation factors, a comprehensive evaluation method of infectious disease prevalence combined with principal component analysis and BP neural network is proposed. After comprehensive analysis, the evaluation index system based on the population, the number of infections, the number of deaths and deaths, the duration of the epidemic, the economic status, medical conditions, population density, epidemic prevention policies, and the number of infected countries is selected. The relevant data of "epidemic" and "pandemic" constitutes a BP neural network evaluation model for evaluating the prevalence of infectious diseases. The research results show that the combined method of PCA and BP neural network reduces the input variables from 9 to 2, avoiding the influence caused by the correlation of variables, simplifying the evaluation process, and the results are more reasonable. The actual results and the calculation results of the comprehensive evaluation model of the prevalence of infectious diseases based on PCA and BP neural network support each other.