Glucose-Insulin regulator for type 1 diabetes using high order neural networks

Orozco López, Onofré; Castañeda Hernández, Carlos Eduardo; Rodríguez Herrero, Agustín; García Saéz, Gema y Hernando Pérez, María Elena (2014). Glucose-Insulin regulator for type 1 diabetes using high order neural networks. "International Journal of Artificial Intelligence and Neural Networks (IJAINN)", v. 4 (n. 3); pp. 40-47. ISSN 2250-3749.

Descripción

Título: Glucose-Insulin regulator for type 1 diabetes using high order neural networks
Autor/es:
  • Orozco López, Onofré
  • Castañeda Hernández, Carlos Eduardo
  • Rodríguez Herrero, Agustín
  • García Saéz, Gema
  • Hernando Pérez, María Elena
Tipo de Documento: Artículo
Título del Evento: Proc. of the International Conference on Advances In Computing, Communication and Information Technology
Fechas del Evento: 01/06/2014 - 02/06/2014
Lugar del Evento: LONDRES, UK
Título de Revista/Publicación: International Journal of Artificial Intelligence and Neural Networks (IJAINN)
Fecha: Septiembre 2014
Volumen: 4
Materias:
Palabras Clave Informales: Identification, Recurrent Neural Networks, Extended Kalman, Diabetes, Artificial Pancreas, insulin, glucose
Escuela: E.T.S.I. y Sistemas de Telecomunicación (UPM)
Departamento: Ingeniería Telemática y Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (798kB) | Vista Previa

Resumen

In this paper a Glucose-Insulin regulator for Type 1 Diabetes using artificial neural networks (ANN) is proposed. This is done using a discrete recurrent high order neural network in order to identify and control a nonlinear dynamical system which represents the pancreas? beta-cells behavior of a virtual patient. The ANN which reproduces and identifies the dynamical behavior system, is configured as series parallel and trained on line using the extended Kalman filter algorithm to achieve a quickly convergence identification in silico. The control objective is to regulate the glucose-insulin level under different glucose inputs and is based on a nonlinear neural block control law. A safety block is included between the control output signal and the virtual patient with type 1 diabetes mellitus. Simulations include a period of three days. Simulation results are compared during the overnight fasting period in Open-Loop (OL) versus Closed- Loop (CL). Tests in Semi-Closed-Loop (SCL) are made feedforward in order to give information to the control algorithm. We conclude the controller is able to drive the glucose to target in overnight periods and the feedforward is necessary to control the postprandial period.

Más información

ID de Registro: 35099
Identificador DC: http://oa.upm.es/35099/
Identificador OAI: oai:oa.upm.es:35099
URL Oficial: http://www.seekdl.org/journal_page_papers.php?jourid=84&issueid=93
Depositado por: Memoria Investigacion
Depositado el: 18 Mar 2016 20:20
Ultima Modificación: 18 Mar 2016 20:20
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM