Combined Forecast Model of LSTM-CNN Hypertension Based on EEMD

According to studies at home and abroad, hypertension is an important disease that endangers human life and health. How to early warn the increase in blood pressure in time has become a hot research issue. To solve this problem, a long-short-term memory network (LSTM)-convolutional neural network (CNN) combined prediction model based on ensemble empirical mode decomposition is proposed. Firstly, the blood pressure data is decomposed into several intrinsic mode functions (IMF), and then LSTM and CNN are used to extract the time features and image features respectively, and predict the blood pressure change trend in the next time period. Finally, the prediction results of all IMF components are superimposed and combined to obtain the prediction results. The experiment uses root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and R2 to evaluate it, and this prediction method is combined with a single LSTM model, CNN model and LSTM-CNN combination model. Model comparison shows that our method has the smallest error and the highest prediction accuracy, which verifies the effectiveness and scalability of our model.