Inspiration
The compound library has lots of vial misplacement errors. A researcher like Kelsey would sometimes undergo a lot of wasted time trying to hunt down missing/misplaced vials.
What it does
Our solution eliminates missing/misplaced vials by cross-referencing them with other vials by taking a picture and comparing the picture to other pictures in a machine learning database. We also have other components for the solution such as an interface that scans and displays information about the vial.
Accomplishments that we're proud of
We can safely call what we created a minimum viable product. Despite only using a handful of vials in our training set, and despite some front-end glitches, everything is function and ready to go.
What's next for A-RoomBA
It's an improvement to the current system, and we think that it could very well be implemented in the compound library in the future to revolutionize quality control and database management.
Log in or sign up for Devpost to join the conversation.