Modeling the control of the central nervous system over the cardiovascular system using support vector machines
The control of the central nervous system (CNS) over the cardiovascular system (CS) has been modeled using different techniques, such as fuzzy inductive reasoning, genetic fuzzy systems, neural networks, and nonlinear autoregressive techniques; the results obtained so far have been significant, bu...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , |
| Format: | Artículo |
| Language: | spa |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://doi.org/10.1016/j.compbiomed.2017.12.008 https://www.sciencedirect.com/science/article/pii/S0010482517304055?via%3Dihub#! |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The control of the central nervous system (CNS) over the cardiovascular system (CS) has been modeled using
different techniques, such as fuzzy inductive reasoning, genetic fuzzy systems, neural networks, and nonlinear
autoregressive techniques; the results obtained so far have been significant, but not solid enough to describe the
control response of the CNS over the CS. In this research, support vector machines (SVMs) are used to predict the
response of a branch of the CNS, specifically, the one that controls an important part of the cardiovascular system.
To do this, five models are developed to emulate the output response of five controllers for the same input signal,
the carotid sinus blood pressure (CSBP). These controllers regulate parameters such as heart rate, myocardial
contractility, peripheral and coronary resistance, and venous tone. The models are trained using a known set of
input-output response in each controller; also, there is a set of six input-output signals for testing each proposed
model. The input signals are processed using an all-pass filter, and the accuracy performance of the control models
is evaluated using the percentage value of the normalized mean square error (MSE). Experimental results reveal
that SVM models achieve a better estimation of the dynamical behavior of the CNS control compared to others
modeling systems. The main results obtained show that the best case is for the peripheral resistance controller,
with a MSE of 1.20e-4%, while the worst case is for the heart rate controller, with a MSE of 1.80e-3%. These novel
models show a great reliability in fitting the output response of the CNS which can be used as an input to the
hemodynamic system models in order to predict the behavior of the heart and blood vessels in response to blood
pressure variations. |
|---|