摘要：It is aimed to minimize the great losses caused by public health emergencies to people's health, daily life, and national economy. The tuberculosis data from June 2017 to June 2019 in a city are collected. By determining the relevant indicators and parameter estimation, the structural equation model (SEM) is constructed to determine the relationship between hidden and explicit variables. On this basis, the prediction model based on artificial neural network (ANN) and convolutional neural network (CNN) is constructed. The effectiveness of the method is verified by comparing the loss value and accuracy of the prediction model in training and testing. At the same time, 50 pieces of information data of actual cases are tested, and the warning level is determined according to the T value. The results show that comparing and analyzing ANN, CNN, and the hybrid network of ANN and CNN, the accuracy of the hybrid network (95.1%) is higher than that of the other two algorithms, 89.1% and 90.1 %. Also, it can show good prediction effect and accuracy when predicting actual cases. Therefore, the early warning method based on ANN under deep learning shows better performance in early warning of public health emergencies, which is greatly significant for improving early warning capabilities.
关键词：Public health emergencies; artificial neural network; Convolutional Neural Network; structural equation model; early warning
