Comparing the PaGMO Framework to a De-randomized Meta-Differential Evolution on Calculation and Prediction of Glucose Levels

Abstract

The PaGMO framework offers several optimization algorithms to determine optimal parameters of a black-box model. Such a model could be, for example, that for glucose homeostasis.

As we are concerned about calculating and predicting glucose levels for diabetic patients, we evaluate the PaGMO framework for this particular task. Using three scenarios, we test PaGMO's individual algorithms and compare them to our previous results, which we obtained with de-randomized Meta-Differential Evolutions.

All testing scenarios address real aspects of processing a signal of the continuous glucose monitoring system. Specifically, we address signal reconstruction and prediction.

Keywords

• Artifical Bee Colony
• Covariance Matrix Adaptation
• Differential Evolution
• Exponential Evolution
• Glucose Level
• Improved Harmony Search
• PaGMO
• Particle Swarm Optimization
• Prediction