Modelling and identification for Artificial Pancreas Applications

چکیده مقاله

Abstract

Designing Automated controllers in order to regulate blood glucose concentrations in patients with Type 1 diabetes mellitus (T1DM) must avoid hypoglycemia (blood glucose <;70 mg/dl) while minimizing hyperglycemia (>180 mg/dl) makes automatic blood glucose control very challenging. Due to the large patient variability in human physiology and the impacts of variables such as exercise or meals challenge current prediction modeling methods. Various patients have different insulin responses, and a control law based on a non-individualized model could be ineffective. Modelling and system identification and validation are based on silico information collected during simulations of clinical protocols designed so as to produce a sufficient signal excitation without compromising patient safety. Physiological models are very precise but complicated and specific physiological knowledge is required. However, data-based models allow the incorporation of additional inputs and accurately capture the relationship between inputs and the result, but at the cost of losing the physiological meaning of the model.

دریافت لینک دانلود مقاله