Overview / Usage

Because of the Corona Virus Disease (COVID-19) pandemic scenario that the world is going through right now, there has been a surge in the requirement for emergency life support systems like ventilators. Con- ventional ventilators used in Intensive Care Unit (ICU)s tend to be bulky and expensive, and demand high power consumption and trained experts to operate. The aim of the project is to deliver a solution for the grow- ing demand for portable ventilators and a viable replacement for nurse assisted artificial resuscitation. Mechanical ventilation is the process of supplying scheduled breaths to a patient who lacks the ability to do the Work of Breathing (WOB) himself/herself. The pattern of breathing for every patient is identified using sensor(s) and the required volume of air is supplied by compressing a Bag Valve Mask (BVM) device. A machine learning algorithm learns the pattern of breathing and adjusts the pressure and volume controls specific to every patient. All operations and control mode switching for the device can be done using an Android app, hence making it user friendly.

Methodology / Approach

Our solution is capable to support the 1. Static Ventilation, 2. Dynamic Ventilation and has a fail-safe mechanism. Request you to see the demo. The demo - https://youtu.be/XJsvNUQOpOY

The entire system is implemented on the Cloud. We have chosen Amazon Web Services (AWS), the number one cloud service provider, for our implementation. Since we need data to be sent and received over a secure channel with very low latency, we use the fully managed MQTT broker which is provided by the AWS IoT Core service. The data which flows in and out of the system and the number of connection attempts can be visualized in the console itself.

The following steps were followed to establish a connection with the Cloud:

1. Generated and downloaded the necessary certificates from the Console and configuring the necessary policies to connect to the corresponding AWS account securely.

2. Converted the certificates into a proper format that can be comprehended by the microcontroller once flashed onto it, using OpenSSL.

3. In order for the Android application to communicate with the AWS account, we set up similar policies using the AWS Cognito service, which would act in place of the certificates that would be used in the microcontroller.

4. Configured the MQTT Client, where one can publish/subscribe to any topic, with messages of any specified format.

Once the Cloud set-up was complete, we moved on to writing the code that would be flashed on to the microcontroller, which would cover basic operations such as connecting to the Internet, communicating with the AWS Cloud, and controlling the stepper motor. After the completion, the entire code along with the certificates had to be bundled together and finally flashed onto the NodeMCU microcontroller.

The data generated by the microcontroller is pushed onto the MQTT broker and saved in real-time on a NoSQL Database called AWS DynamoDB, which can further be used for processing and analysis that would provide necessary intuition for the implementation of any further modules or extensions to the system. Once ready, the entire system was rigorously tested, including communication and data transfer to and from both the microcontroller and the Android application. We were able to track down errors and finally verify that all the modules work in sync with one another. A noticeable feature is that there is no latency that occurs during the communication that happens over the Cloud, as this is one of the crucial factors that has to be kept in mind while building any medical application.

Technologies Used

IoT, AI, Python, ML

Repository

https://github.com/achuth10/Smart-Ventilator

Collaborators