Establishment of Risk Prediction Model for Echinococcosis Disease Outbreak based on Long Short-term Memory
The aim of this study is to develop a hybrid model based on a time series decomposition method and a long short-term memory(LSTM)network to predict the risk of future outbreaks of infectious diseases such as baumatosis.Firstly,the incidence data of echinococcosis in China's provinces between 2004 and 2019 were obtained from the Scientific Data Centre of the National Ministry of Health of China.Secondly,a hybrid prediction model was then established by time series decomposition and LSTM network analysis.Finally,the accuracy of the prediction model was evaluated.The results showed that the hybrid model with trend components derived from time series decomposition combined with LSTM had a lower test error compared with the single LSTM model,indicating that the model has higher accuracy in incidence trends prediction.In conclusion,the hybrid model provides a reference and technical support for the incidence risk of encapsulated disease prediction with high accuracy,and provides a research basis for in-depth exploration of the interdisciplinary field combining machine learning and infectious diseases.
国家科技期刊平台
NSTL
万方数据
