HackStack

Project Info

Winner

[MLH - MongoDB] Best Use of MongoDB Atlas

RecycleThis

Devpost

This project did not submit a demo video on Devpost.

Inspiration

While walking around CruzHacks, we found many items misplaced in incorrect bins. We decided that if we wanted to solve environmental issues, we might as well start with those which are closest to us.

What it does

RecycleThis is an iOS application that classifies proper disposal of items, and provides waste management tips. In addition, it further decreases the challenge of sustainability by providing locations for the nearest recycling bins in your area! With a single tap, users can effortlessly help maintain a clean community for themselves and those around them.

How we built it

RecycleThis is a React Native application that utilizes a combined model of Google Cloud Platform and openAI APIs to assist users in their sustainability goals. With a custom AI Tensorflow model, the application can also classify the proper disposal classification for items, and display the Geo-location of relevant bins with Google Places..

Challenges we ran into

This was the first hackathon for many of our members, and we all have little experience with our chosen platform of React Native. One particular issue we ran into was the deprecation and incompatibility of several libraries, requiring novel solutions that deviated from documentation.

Accomplishments we're proud of

We have a working Speech Recognition System, that is able to record and log voice conversations while in range of the microphone. Also, our ability to quickly adapt and learn new frameworks exceeded our expectations. Coming to this event with little experience in creating machine learning models, we managed to research, develop, and train models within the deadline.

What we learned

We learned a lot about Front-End Development in React Native, particularly in IOS development using Expo. We also learned the importance of the initial brainstorming phase of product development, as our first hurdle was surprisingly difficult.

What's next

Throughout this weekend, we found some notable aspects we hope to improve upon in the future. General performance fixes in speed of the program and accuracy of the models would be helpful, as well as increased compatibility to account for non-ios users. RecycleThis also aims to further improve through a more accessible and appealing UI interface and additional features in later updates.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • JavaScriptIn code
  • PythonIn code
  • ReactIn code
  • JavaClaimed
  • MongoDBClaimed
  • Node.jsClaimed
  • TypeScriptClaimed

3 of 7 appear in the indexed code. 4 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

33 KB

Source files

13

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars