Type I diabetes: modeling, identification and non-linear model predictive control

GASTÓN SCHLOTTHAUER; GUIDO ALEJANDRO NICOLINI; LUCAS GUILLERMO GAMERO; MARÍA EUGENIA TORRES

Houston, EEUU

Conferencia; Second Joint EMBS/BMES Conference; 2002

IEEE - EMBS - BMES

Patients with diabetic type I nearly always need a therapy with insulin. The most desirable treatment would be to mimic the operation of a normal pancreas. In this work we model a patient affected with this pathology, identify it with a neural network, and evaluate a control strategy known as nonlinear model predictive control as an approach to command an insulin pump using the subcutaneous route.