A comparative study on the prediction of the BP artificial neural network model and the ARIMA model in the incidence of AIDS.

Such data diversity method could be adopted to better learn and train network models, and avoid overlearning and overfitting [ 24 ]. Results Features of time series analysis in the report rate of AIDS According to the surveillance data from January 2004 to December 2016, the figure of monthly incidence rates showed a trend of sharp increase from 2010 to 2016 the peak incidence existed in 2012 (Fig. 2 ).

also in 53,322 other papers