Title :
Markov modelling and adaptive control in management of type 1 diabetes mellitus
Author :
Santoso, Lucia ; Mareels, Iven M Y
Abstract :
We present management of diabetes mellitus as a constrained control problem, with very sparse sampling, where no information on dynamics are available. This, problem has been approached through modelling of the system as a Markov decision process, and through direct derivation of control rules. Considering the complexity of the system constraints imposed by lack of information, we argue that non-model based control is the best and simplest method for this problem.
Keywords :
Markov processes; adaptive control; biocontrol; decision theory; diseases; dynamic programming; physiological models; 60 to 90 day; Markov decision process; adaptive control; blood glucose concentration; constrained control problem; type 1 diabetes mellitus management; very sparse sampling; Adaptive control; Biochemistry; Control systems; Diabetes; Engineering management; Fluids and secretions; Insulin; Pancreas; Sampling methods; Sugar;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020641
