FPGA neural identifier for insulin-glucose dynamics

Author

Romero-Aragon, Jorge C. ; Sanchez, Edgar N. ; Alanis, Alma Y.

Author_Institution

Unidad Guadalajara, CINVESTAV, Zapopan, Mexico

fYear

2014

fDate

3-7 Aug. 2014

Firstpage

675

Lastpage

680

Abstract

In this paper, the implementation of a discrete-time neural model in an field programmable gate array (FPGA) is proposed to model insulin-glucose dynamics of type 1 diabetes mellitus (T1DM) patients. The neural model is obtained from an on-line neural identifier, which uses a recurrent high-order neural network (RHONN) trained with an extended Kalman filter (EKF), which captures the nonlinear behavior of this dynamics. Experimental data given by continuous glucose monitoring (CGM) device are utilized for identification.

Keywords

Kalman filters; diseases; field programmable gate arrays; neural nets; nonlinear filters; patient monitoring; recurrent neural nets; CGM device; EKF; FPGA neural identifier; RHONN; T1DM patients; continuous glucose monitoring device; discrete-time neural model; extended Kalman filter; field programmable gate array; insulin-glucose dynamics; neural model; nonlinear behavior; on-line neural identifier; recurrent high-order neural network; type 1 diabetes mellitus patients; Diabetes; Field programmable gate arrays; Insulin; MATLAB; Mathematical model; Registers; Table lookup;

fLanguage

English

Publisher

ieee

Conference_Titel

World Automation Congress (WAC), 2014

Conference_Location

Waikoloa, HI

Type

conf

DOI

10.1109/WAC.2014.6936098

Filename

6936098