GlyCoach presents a novel approach to charaterize the decision boundary of a model and leverage it to generate counterfactual expalantions reflecting user preferences.
Accurately forecasts future blood glucose level and predicts dysglycemic events thereby.
GlySim accurately forecasts future blood glucose level, intervenes by identifying the factor contributing most towards blood glucose spike and suggests optimal behavioral change to avoid abnormality.
With a Tiramisu model, we have been able to denoise ECG signals buried under motion noise and estimate inter-beat-intervals (IBI) accurately.
Briefly evaluates the factors behind medication adherence of patients at risk for atherosclerotic cardiovascular disease.
Optimizes change in consumed nutrients while driving users to their desired diet goals.
DietNudge is a decision tree based approach that can detect impending hyperglycemic events and provides explanations why hyperglycemia occred.
