It is very challenging for family members to keep up with elderly/sick people’s health status without frequent direct communication (ex. via phone calls), especially during Covid-19.
What it does
It is an app which checks in with the user by asking simple questions and by asking to draw numbers (check to see if the user is emotionally/mentally stable), verifying the drawings using ML, and lets the user's family know if he/she needs medical attention.
How we built it
We used MIT App Inventor to build the User Interface of the app, to have a digital drawing board for the user to draw the numbers on, and to ask the user simple check-in questions. We wrote a Machine learning algorithm in Jupyter notebook which determines whether the number that the user was prompted to draw matches with the actual number that the user drew.
Challenges we ran into
We faced some challenges in determining how the user interface would actually look like. We also faced some challenges when trying to write the machine learning algorithm to be able to categorize digits correctly.
Accomplishments that we're proud of
We are proud of all that we could get done in such a short amount of time! We are extremely proud that the machine learning model predicted most digits correctly and we are also proud of our creative design of the app!
What we learned
We learned how to work collaboratively and how to work effectively on a team!
What's next for H-Status
Some future improvements that we would like to make in the app would be to connect the user interface in MIT App Inventor with the machine learning code in Jupyter notebook. This would automate the process so that the numerical drawings of the user automatically serve as testing data to the ML model.
(Please note that the .aia file can only be opened in the MIT App Inventor website). You can import the project on the website.