Blood Glucose Prediction Based on Empirical Mode Decomposition and GA-BP Neural Network

As a common endocrine disease characterized by hyperglycemia, diabetes has already threatened the health of many people. In order to avoid the occurrence of hyperglycemic, it is necessary to predict the blood glucose level of patients in advance by using appropriate prediction algorithms. In order to improve the prediction accuracy of blood glucose, this paper proposes a new method combined Empirical Mode Decomposition (EMD) and GA-BP neural network. Firstly, the EMD is used to decompose the blood glucose data of patients with Type 1 Diabetes (T1D). Secondly, the GA-BP neural network model is established for each component obtained after decomposition. Finally, the prediction results of each model are fused to obtain the final predicted value. The Root Mean Square Error (RMSE) of this method is 8.2095 mg/dl and the Mean Absolute Error (MAE) is 5.9750 mg/dl for Prediction Horizon (PH) = 30min. The results show that the method has high prediction accuracy for blood glucose and has a good application prospect.