Authors:
Nathanaël Cottin
;
Olivier Grunder
and
Abdellah ElMoudni
Affiliation:
Université de Technologie de Belfort Montbéliard, France
Keyword(s):
Diabetes, Glycaemia regulation, Insulin, NPC, Artificial neural network, Resilient propagation.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Data Engineering
;
Decision Support Systems
;
Development of Assistive Technology
;
Enterprise Information Systems
;
Health Information Systems
;
Information Systems Analysis and Specification
;
Knowledge Management
;
Ontologies and the Semantic Web
;
Pattern Recognition and Machine Learning
;
Society, e-Business and e-Government
;
Software Systems in Medicine
;
Therapeutic Systems and Technologies
;
Web Information Systems and Technologies
Abstract:
Type 1 blood glucose regulation remains a complex problem to simulate. Different blood glucose control schemes for insulin-dependent diabetes therapies and systems have been proposed in the literature. This article presents an adaptative predictive control system for glycaemia regulation based on feedforward Artificial Neural Networks trained with the resilient propagation (RPROP) method. Experiments performed on a mathematical (theoretical) compensation model and our system aim to objectively compare the behaviour of each approach when both exact and perturbated data are presented. These experiments, which make use of a virtual patient, not only cover the ANN’s best configuration and training parameters on exact training information, they also demonstrate the accuracy of the neural approach when up to 20% perturbated data are supplied. As a result of the experiments on perturbated data, the neural approach gives slightly better evaluations than the theoretical model. This demonstrat
es the neural system’s ability to adapt to perturbated environments.
(More)