A Novel IoT-Enabled Oxygen Delivery System with Neural Network-Based Predictive Control

In this research study, a hardware is designed to monitor and control oxygen delivery based on physiological parameters, blood Oxygen saturation, and heart rate for real time applications. The development and evaluation of an intelligent portable Oxygen Concentrator system that integrates a Sensor, Motor driver Controller, and ESP8266 microcontroller. The controller measures SPO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> and heart rate. Data from these sensors are processed by neural network model implemented on the ESP8266 which predicts the optimal Oxygen flow rate constrained internet of things (IoT) applications such as wireless sensor networks. Therefore, in this paper, the design steps to build a model in NodeMCU ESP8266 using an artificial neural network (ANN) are presented. Controller is used in our study and NodeMCU ESP8266 is chosen because it is suitable to be used as a sensor node or sink in WSN applications. ANN with a Levenberg Marquardt algorithm is used as it can model the non - linearity with high accuracy. This intelligent system effectively manages Oxygen delivery, optimizing patient care, and has demonstrated high accuracy MSE of 0.0588 in predicting Oxygen flow requirements using a dataset of 1178 data points. For physiological metrics like SPO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>, heart rate, respiration rate, and temperature, combining neural networks with data sets can help lower mistakes and increase the precision of predictions generated using these methods.