LSTM和Prophet模型在肺结核发病数预测中的应用

Application of LSTM and Prophet Models in Predicting the Number of Tuberculosis Cases

为预测肺结核发病数,建立了两种能够较为精确描述以及预测肺结核发病数的模型.根据中国疾控中心提供的2007年7月至2019年6月肺结核发病数的数据,运用LSTM模型和Prophet模型对中国肺结核发病数进行预测,并将该两种模型的预测性能与ARIMA、GM(1,1)模型进行对比.结果表明,Prophet模型预测性能最佳,其MAE值与RMSE值分别为5 124.33、5 905.32,LSTM模型预测性能次之,ARIMA模型预测性能最差.

In order to predict the number of tuberculosis cases,two models that can accurately predict the number of tuberculosis cases were established in this paper. According to the data of the number of tuberculosis incidence from July 2007 to June 2019 provided by the Chinese Center for Disease Control and Prevention. We used the LSTM model and Prophet model to predict the incidence of tuberculosis in China. Moreover,the prediction performances of the two models were compared with the ARIMA and GM(1,1)models. The results show that the Prophet model has the best prediction performance,with MAE and RMSE values of 5 124.33 and 5 905.32,respectively,followed by the LSTM model,and the ARIMA model has the worst prediction performance.