Prediction of measles incidence rate based on the support vector machine model

Objective To establish a support vector machine model for prediction of measles incidence rate, in order to provide the reference for measles prevention and control decision. Methods The data of measles incidence rate in china from 1996 to 2015 were collected. The incidence rates of measles from 1996 to 2014 were training samples, and the incidence rate of 2015 was testing sample. The prediction model was established based on the support vector machine regression algorithm, and the incidence rates of measles from 2016 to 2018 were predicted by using this model. Results The actual incidence rates and predicted incidence rates of measles were highly consistent; the average relative error was 0.620 07%. The predicted incidence rates of measles in china from 2016 to 2018 were 3.23/100 000 and 3.13/100 000, 3.79/100 000, respectively. Conclusions It is feasible and effective to predict the incidence rate of measles by using the support vector machine regression model.