Inspiration
We were inspired by our indigenous studies course, which advocated living in balance with nature. Foraging is an age-old practice deeply rooted in indigenous traditions, one that aligns perfectly with the concept of living sustainably. As urbanization and modernization have progressed, the ancient art of foraging, including mushroom hunting, has dwindled. However, the benefits of foraging, as espoused by indigenous wisdom, remain as relevant as ever. FungIDE was born out of the desire to bridge this gap and empower individuals to reconnect with nature through responsible foraging.
What it does
Taking inputs decribing your mushroom, our model predicts a binary value - poisonous or edible, with non-edible and non-poisonous mushrooms falling into the poisonous category.
How we built it
We trained our backend model (RandomForestClassifier from Tensorflow) on a mushroom database collected from the internet. We then planned on using a description of the mushroom (given by the user) and relaying it to our backend.
Challenges we ran into
Collecting information from the user and relaying to the backend of the program was a lot more difficult than expected. We tried many different techniques, such as REST api and Flask. In the end, we could not get it to work in the allocated time frame.
Accomplishments that we're proud of
We're both proud of learning how to use a lot of new technology in a short amount of time. In four days, our team of two learnt the basics of machine learning, python, HTML, and CSS from nothing, and troubleshooting the many issues that popped up during the duration of the hackathon.
What we learned
We learned the basics of machine learning, and front-end design.
What's next for FungIDE
The next step for FungIDE would be to learn how to relay information between the frontend and the backend, and with that, our product development could be considered to be truly complete.
Log in or sign up for Devpost to join the conversation.