DocumentCode :
1827386
Title :
Preliminary results of a novel approach for glucose regulation using an Actor-Critic learning based controller
Author :
Daskalaki, Elena ; Scarnato, Luca ; Diem, Peter ; Mougiakakou, Stavroula G.
Author_Institution :
ARTORG Center for Biomed. Eng. Res., Univ. of Bern, Bern, Switzerland
fYear :
2010
fDate :
7-10 Sept. 2010
Firstpage :
1
Lastpage :
5
Abstract :
In this paper, a novel approach for glucose regulation in individuals with type 1 diabetes mellitus is considered using the principles of adaptive reinforcement learning techniques. More specifically a controller based on Actor-Critic (AC) learning algorithm is used for the estimation of insulin infusion rate in adult patients using continuous glucose monitoring devices and insulin infusion pumps. Generally, AC algorithms are able to solve control problems of nonlinear, dynamic systems. Aim of the paper is to investigate the applicability of the AC learning method to the problem of glucose regulation and the feasibility to be used for an artificial pancreas. The implemented controller has been tested in an in silico environment. Preliminary results have shown that although the algorithm prevents hypoglycemic events, further research is needed in order to reduce the percentage of glucose concentration values over the acceptable normoglycaemia bound. Furthermore, open issues with the proposed algorithm have been identified, while the next research steps have been defined.
Keywords :
adaptive control; artificial organs; computerised monitoring; diseases; learning (artificial intelligence); medical control systems; nonlinear dynamical systems; sugar; AC learning algorithm; actor-critic learning-based controller; adaptive reinforcement learning techniques; adult patients; artificial pancreas; glucose concentration value percentage reduction; glucose monitoring devices; glucose regulation; hypoglycemic event prevention; in-silico environment; insulin infusion pumps; insulin infusion rate estimation; nonlinear dynamic systems; normoglycaemia bound; type-1 diabetes mellitus; Actor-Critic Learning; Artificial pancreas; Closed loop control; Diabetes; Neural network models;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Control 2010, UKACC International Conference on
Conference_Location :
Coventry
Electronic_ISBN :
978-1-84600-038-6
Type :
conf
DOI :
10.1049/ic.2010.0287
Filename :
6490745
Link To Document :
بازگشت