Multi-Regional Collaborative Influenza Prediction Method Based on Optimized LSTM Network
Influenza usually shows the characteristics of seasonal,acute onset and rapid transmission,so the accurate prediction of influenza is very important.Aiming at the problems of poor accuracy of influ-enza prediction and the difficulty of optimizing parameters of long short-term memory(LSTM),a multi-region collaborative influenza prediction method(MRC-DBO-LSTM)based on Pearson correlation coeffi-cient and dung beetle optimization algorithm(DBO)was proposed.The model learns not only the histori-cal data of the local area,but also the historical data of the region with which it is strongly related.Firstly,Pearson correlation coefficient was used to select the regions strongly correlated with the predic-tion place,so as to obtain the input features of higher dimensions.Secondly,the LSTM gate mechanism was used to measure the weight of these regional data for feature fusion.Finally,dung beetle optimization algorithm was introduced to optimize the super parameters(such as the number of hidden layers,the num-ber of hidden layer nodes and the number of iterations,etc.)of the LSTM,so as to generate prediction results.The experimental results of predicting influenza incidence in Shanxi Province show that the R-Squared of the MRC-DBO-LSTM model based on multi-regional historical data is 0.988,and the mean square error(MSE)is only 0.003 8.Compared with the differential integrated moving average autoregres-sion(ARIMA)model,MSE is decreased by 99.6%,MSE is decreased by 98.7%compared to the sea-sonal differential autoregressive moving average(SARIMA)model,MSE is decreased by 71.0%com-pared to the LSTM model,and MSE is decreased by 48.6%compared to the DBO-LSTM model using only local historical data.It is proved that the proposed model can effectively improve the prediction accu-racy of influenza.
influenza predictiondung beetle optimization algorithmlong short-term memory networkdeep learningtime series