Project 2: Blood Glucose Forecasting Using Free-living and Patient Generated Data

Master’s thesis on time-series forecasting of glucose levels for diabetes management, using modern machine learning techniques to close the loop in Artificial Pancreas System (APS) technology, reducing root mean square error to 14.7 units.

Published paper (full text):

Comparing Machine Learning Techniques for Blood Glucose Forecasting Using Free-living and Patient Generated Data by Hadia Hameed and Samantha Kleinberg

Share this: