A State-by-State online transfer learning framework with incremental clustering for blood glucose prediction

Abstract

This study proposes a State-by-State online transfer learning framework for blood glucose (BG) prediction. We assume that the BG data can be divided into states, representing different states of the patient. A thoroughly reliable blood glucose prediction model should not only be able to mimic the patient's physiology, such as fasting, food intake, and exercise, but also cope with external disturbances, such as noise, exercise, unannounced meals, and stress, among other factors. The state of the fixed-length BG data is separated using a clustering method. For each state, an appropriate prediction model is trained. This framework transforms the online prediction of BG into the process of matching the prediction model online, using incremental clustering methods and online transfer learning methods to cope when there is no matching model for the new state data input. The method uses incremental clustering to accurately divide the state of patients' blood glucose time series, builds a prediction model by state, and uses online transfer learning to train a new model when data is insufficient. In conclusion, we obtained the highest prediction accuracy on the dataset using this strategy.