Title: Forecast of Dengue Cases in 20 Chinese Cities Based on Deep Learning Method
Abstract: Dengue Fever (DF) is one of the most rapidly spreading diseases in the world and accurate forecasts of dengue in timely might help the local government to take effective control measures. To obtain the accurate forecasting of DF cases, it is crucial to model long-term dependency in time series data which is difficult for the typical machine learning method. This study aims to develop a timely accurate forecast model of dengue based on the Long Short-Term Memory (LSTM) recurrent neural networks while just considering monthly dengue cases and climate factors. The performance of LSTM models was compared with the other previously published models when predicting DF cases one month into the future. Our results showed that the LSTM model trained by transfer learning (TL) improved average performance by 24.91% to 12.99%, and improved performance in the outbreak period by 26.82% to 15.09%. The LSTM model achieved superior performance in predicting dengue cases as compared with other previously published forecasting models. Moreover, TL can improve the generalization ability of the model in areas with fewer dengue incidences. The findings provide a more precise forecast dengue model and might be used for other dengue-like infectious diseases.