Team 100; Apple Software

• 

  Internal workings of the application

• 

  Deployment

• 

  Apple Software in action

Inspiration: There is a lot of food wastage in the world and we would like to use ML to aid us in better allocating resources without the need for human intervention.

What it does: Uses a Web application running CNN compiled from Edge Impulse to classify apples into 3 categories (Ripe, Unripe, Rotten)

How we built it: Edge Impulse, Python, Flask

Challenges: we ran into: Lack of dataset for effective machine learning,

Accomplishments that we're proud of: Satisfied with prototype finished within 45H

What we learned: Basics of CNN, Web programming, Data augmentation, Data cleaning

What's next for: Apple Software Hardware integration to automatically remove rotten food, and to have a larger dataset to better remove fruits other than apples.

References: https://www.nature.com/articles/s41598-021-96103-2; https://www.kaggle.com/sriramr/fruits-fresh-and-rotten-for-classification; https://www.kaggle.com/raghavrpotdar/fresh-and-stale-images-of-fruits-and-vegetables;

Built With

• edgeimpluse
• github
• python