Carpal Tunnel Rehabilitation Monitoring Device

This is the general UI For our project. This is the main menu for our project
This is the preliminary view of the raw data in (Angular velocity, 'qualifying condition') format.
This is the exported csv file in (Angular velocity, 'qualifying condition') format.
This is the accuracy data from the machine learning model, detailing the current approximation of accuracy for our mechanism.
This is the export data pop up describing that the user has completed their export successfully
Photo of device with glove
Photo of electronic parts of device

Inspiration

Carpal Tunnel is a disease that affects many people both in America and abroad. Many types of motions that are repetitive and intense may cause this, such as the labor done by farmworkers. We were inspired to better allow clinicians to track the rehabilitation process.

What it does

This device has an imu which tracks the speed of the hand. After being trained on what is a good and bad value, the device flags these data points and sends it to an application that can be used by a clinician.

How we built it

We first used an arduino to collect the data. This data is then exported to a csv which the machine learning algorithm is trained on and classifies. Everything is then shown on the application.

Challenges we ran into

We ran into several issues such as how to get all the different software to work. The arduino we use runs in C, while the rest of the project was in python. We also had trouble creating the machine learning model because of the time limit.

Accomplishments that we're proud of

We are very proud that we were able to incorporate machine learning, microcontrollers, 3d printing, and ux into a working project within the time span.