Providing efficient ventilation to patients in emer- gency situations can be challenging, particularly in settings with limited resources. This research aims to address this issue by proposing an automated AMBU bag system that can determine the ventilation rate based on the patient’s pulse rate and blood oxygen level. The proposed system consists of a microcontroller, a sensor, cloud services, a stepper motor driver, and a stepper motor. The system reads the patient’s pulse rate and blood oxygen level using a sensor, processes the data using an equation, and adjusts the stepper motor’s ventilation rate accordingly. Another aim of the project is to create a system that can help maintain a dataset using the integration of AWS for future research. By creating a dataset for further research, this project can lead to the development of more advanced machine learning models that can improve the efficiency of ventilation systems. Furthermore, the proposed system can be customized to fit the specific needs of different healthcare settings, allowing for widespread adoption of this technology. Overall, the automated AMBU bag system has the potential to greatly improve patient care in emergency situations.

AMBU Bag, Machine Learning, MAX30100 Sensor, 3D Printing, Ventilator, Dataset, Raspberry Pi, Amazon Web Services