-
App Mockup
-
App Mockup
-
Computer vision link
Inspiration
We got inspired by a real-life story of Maria and Amine, who waited for 8 years to get their first baby, but one night when he was 3 weeks old, they woke up finding him dead. Their baby is not the only one, more than 1 million babies over the world die because of SIDS, and since SIDS has forms and signs we wanted to help prevent them from this sudden death and keep them safe.
What it does
Mahd is an IOT System created for parents to monitor their babies all time and anywhere to prevent them from getting SIDS. It is composed of a wearable device for babies that is connected to Terra's APIs, a mobile app that helps parents receive alert signals, and keep track of their babies, and a computer vision smart camera that helps to detect the baby's position.
How we built it
We used Terra’s API to feed Real time collected data to our program that will be able to keep track on the baby's biotic signs, that are related to the Sudden infant death syndrome such as : Hydration, heartbeats, breathing and SPO2, Body temperature...all those will be projected, compared and then displayed on a mobile app for the parents so they can check on their baby’s situation anytime. Our app will be also connected to our monitoring camera which is provided by a computer vision system that will be detecting the flip movements that is one of the main forms of SIDS and set an instant to the application to notify the parents.
Challenges we ran into
Finding the right way to use the run-time APIs of Terra was a big challenge for us especially to provide an impactful solution. Accuracy problems for our computer vision models were detected but we could have an accurate one, in the end, we also tried to implement some IoT sensors and raspberries which took us some time.
Accomplishments that we're proud of
We are so proud that our app is able to detect all the vital signs of the baby at run-time and provide them to the app so that parents can be notified of any inconvenience.
What we learned
We learned a lot about how to use real-time data to predict and detect health issues like SIDS, and use them to save lives.
What's next for MAHD ( an Arabic name that means a safe baby bed )
We tried to use Quantum for machine learning in order to run our models and gain more rapidity. We used Terra's library in Qiskit, we didn't finish it but we are aiming to do that in the future.
Log in or sign up for Devpost to join the conversation.