A model of intelligent controller for hypothyroidism treatment
Tipo
Artigo de evento
Data de publicação
2010
Periódico
Proceedings - 10th IEEE International Conference on Computer and Information Technology, CIT-2010, 7th IEEE International Conference on Embedded Software and Systems, ICESS-2010, ScalCom-2010
Citações (Scopus)
1
Autores
Martins L.G.A.
Monteiro L.H.A.
Monteiro L.H.A.
Orientador
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
Hypothyroidism results from an insufficiency either in the production or/and in the action of the thyroid hormones. Most of the patients in hypothyroidism state must adopt hormonal replacement therapy for all their lives. An intelligent controller model for supplying therapeutic drugs to primary hypothyroidism patients, without the thyroid gland, is investigated in this work. Two multilayer perceptron neural networks are used to predict the concentrations of the hormones TSH and T4 in the blood. The controller, based on a set of production rules, uses these forecasts and the current concentrations of such hormones for calculating the necessary drug dosage to be released. Beyond the controller maintaining such concentrations inside regularity bands, it is also able of preventing abrupt changes on the time evolution of these concentrations. © 2010 IEEE.
Descrição
Palavras-chave
Assuntos Scopus
Abrupt change , Current concentration , Hormonal replacement therapies , Intelligent controllers , Multi-layer perceptron neural networks , Production rules , Therapeutic drugs , Thyroid glands , Thyroid hormones , Time evolutions