Neuro-fuzzy inverse optimal control incorporating a multistep predictor as applied to T1DM patients

摘要: Abstract Emerging technologies seek to provide effective solutions the most severe health problems such as type 1 diabetes mellitus (T1DM). In fact, number of diabetics around world has increased well mortality rate associated with this condition. T1DM is caused by an autoimmune failure which disables pancreas produce insulin; therefore, glucose not correctly metabolized be used efficient energy. Consequently, important fact keep patient's blood level within normal ranges in order avoid long-term complications. Recently, engineering innovative approaches based on intelligent systems artificial neural networks have been proposed for control biomedical systems. work, a novel neuro-fuzzy scheme regulation virtual patients proposed. The glucose-insulin dynamics modeled recurrent high-order network and then multistep predictor incorporated know behavior 15-min horizon; thereby, allowing knowledge future values determine convenient basal infusion insulin defined fuzzy membership functions. Test using well-known Uva/Padova simulator illustrated that controller maintains normoglycemia populations adults, adolescents, children digressing from two other neuro approaches. Thus, offer enormous potential improvement patients. present contribution illustrates very encouraging results closed-loop regarding autonomous pancreas.