Abstract | ||
---|---|---|
This article studies incremental prediction in the context of of a previously contributed model of the Hypothalamus-Pituitary-Adrenal gland (HPA) axis based on the particle filter algorithm. The model considers individual-level circadian rhythm in the context of three coupled nonlinear differential equations of the HPA axis, including Corticotropin-Releasing hormone (CRH), Adrenocorticotropic hormone (ACTH), and Cortisol as state variables. A particle filter approach is proposed to estimate and sample from model state in the context of incoming data in the context of non-linearity, non-Gaussian behavior, as well as stochastic parameters and process noise. The simulation results suggests a high potential for use of particle filtering in prediction of HPA axis state in the context of periodically incoming data. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ICHI.2018.00073 | 2018 IEEE International Conference on Healthcare Informatics (ICHI) |
Keywords | Field | DocType |
HPA axis,Particle Filter,Modeling | Data modeling,Adrenocorticotropic hormone,Computer science,Particle filter,Algorithm,Process noise,Nonlinear differential equations,Context model,State variable,Particle filtering algorithm | Conference |
ISBN | Citations | PageRank |
978-1-5386-5378-4 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amin Mohammadbagheri | 1 | 0 | 0.34 |
Connie Lillas | 2 | 0 | 0.34 |
Nathaniel D. Osgood | 3 | 23 | 9.92 |