Health Monitoring and Breathing Support System


  • Muhammad Awais Department of Electrical Engineering, The University of Lahore, Pakistan
  • Muhammad Nasir Khan Department of Electrical Engineering, The University of Lahore, Pakistan
  • Muhammad Hassan Khan School of Computing and Mathematics, Charles Sturt University Sydney, Australia
  • Sadaat Abbas Department of Electrical Engineering, The University of Lahore, Pakistan



Pulse oximeter, oxygen saturation, microcontroller, signal processi


The objective of this project is design and implementation of a health monitoring system using pulse oximeter which measures pulse rate and oxygen level. Before and especially during Covid-19 pandemic pulse oximeter is most necessary in intensive care units (ICU) and in operation rooms but there is a general shortage of such equipment and the one that is available is very expensive. In this project we aim to create an affordable device that allows a person to measure their physiological parameters and provide breathing support so that it may be used in homes and in medical facilities. This device is controlled by programmable microcontroller with some peripherals and sensor. First, the device was built in breadboard afterward it was built on vero board. This device is based on the variation of photon. This device measures pulse rate, body temperature and oxygen level with oxygen saturation of hemoglobin in blood. This device allows a patient to monitor their health at home which is especially useful for Covid patients observing self-isolation and it can be easily set up in remote areas and can be operated on battery. It is an affordable method of allowing people to monitor their health and avoid frequent visits to hospitals and clinics. The device contains a bag valve mask (BVM) that is compressed using a motor to allow for breathing supports for patients in critical condition.

'Drought,' 'After Drought,' and 'No Drought.' DenseNet, ResNet, InceptionV3, Xception, and VGG19 deep learning architectures were utilized for training the models. Accuracy, Precision, Recall, F1-Score, and ROC curves were used to evaluate all models. According to the experimental results, DenseNet and ResNet were the best-performing models with an accuracy of 70%, while VGG19 was the lowest-performing model with an accuracy of 60%.




How to Cite

Awais, M. ., Khan, M. N., Khan, M. H. ., & Abbas, S. (2022). Health Monitoring and Breathing Support System. Pakistan Journal of Scientific Research, 2(1), 11–16.