TY  - JOUR
T1  - Neural Network and Control for Arterial Oxygen Saturation in Neonatal Infants
AU - Alkurawy, Lafta E.J. 
JO  - Journal of Engineering and Applied Sciences
VL  - 14
IS  - 13
SP  - 4532
EP  - 4541
PY  - 2019
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2019.4532.4541
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2019.4532.4541
KW  - minimun peak
KW  -infants
KW  -Mathematic model
KW  -neural network
KW  -control
KW  -oxygenated
AB  - This study describes the blood Oxygen Saturation (SpO2) for neonatal infant’s by modeling and
control methods. Out of analyzing and study the biological and modeling system, the mechanisms of ventilation
helped the blood to be oxygenated. The oxygenation of the blood affected by Fraction of inspired Oxygen
(FiO<sub>2</sub>), rate of respiratory and rate of heart had an effect on the oxygenation. The SpO2 was modeled by two 2
different methods. The models discussed are a neural network model and mathematic model. The best acting
model was mathematic model because it was capable to detect to changes the biological in the infant&#146;s and
precisely predict the SpO2 for an extended time and is related to apply input FiO<sub>2</sub>. Two different controllers were designed. The controllers are PI and PID controller and they were designed by using the model of dynamic in
mathematical way and with neural network. The controllers were structured to control the SpO2 with altering
the values of FiO<sub>2</sub>. The control of two models were tested to get the response of output for SpO2 at zero steady state error, minimum peak overshoot and minimum rise time. The control of two models were tested on data to
be simulated. The controllers for two models was got to be PID to get SpO2 at 80-90% with changing values
of the FiO<sub>2</sub> is at 20-30%. The values of SpO2 and FiO<sub>2</sub> submitted are contrast between value of the nominal actual and value of comparing which is the best for controllers.
ER  -