WasteWatchers

WasteWatchers

The Problem

Food loss and waste (FLW) is a leading contributor to greenhouse gas emissions, emitting equivalent CO2 amounts as 42 coal-fired power plants1. It is imperative that we remain conscious of just how much food we throw away. According to data collected from last year, in only one hour, students here at Boston University accumulated 40lbs of edible food waste.

Our Solution

Our solution was to prototype an application that would track how much waste you produce. The goal of this app is to help students and young adults minimize their food waste through healthy competition that may help maintain good habits long term!

What it does

Our team and I brainstormed ways to allow university students to have information on the waste they produce on a daily basis, and encourage them to reduce it. We plan on including Image classification through CNN algorithm and transfer learning model to categorize the type of waste. We looked at various data sets relating to different types of waste (including of food, plastic, paper waste) and correlated the various carbon footprints associated with each of them. Based on this, we assigned scores for the user to understand their daily progress. We provide incentives to the users if they their sustainability role, they will be given points which can be redeemed at university stores.

How we built it

The project was made using angular 17 and Bootstrap. It has the landing page for the app 'Waste Watchers'. It was deployed on netlify and the site is live on https://earth-savior.netlify.app/. It's usable on mobile devices only.

Challenges we ran into

We were not able to integrate all the aspects of our solution, and made individual aspects like a Figma wireframe, Web Application, ML Algorithm for Image Classification, and an excel sheet to assign sustainability scores.

Accomplishments that we're proud of

We are proud of using different strengths of our team to build an application that will help individuals be more mindful of the waste that they were generating.

What we learned

During the process, each of us learned something new and we were able to expand our skill sket. It also gave us an opportunity to collaborate on a technical project and create impact. We learned about how carbon emission footprints differ for different types of waste, build an image classification model, use web application to integrate all aspects of our solution, and build a prototype using UI/UX. Moreover, we learned angular and mobile responsive bootsrap framework, figma, and deployment on netlify

What's next for WasteWatchers

In a fully developed version of the WasteWatcher prototype, users could create networks with their friends and families to compete against each other. Additionally, we would implement a streak system to motivate users to maintain consistent usage. Inspired by Duolingo, a popular language learning app, utilizing a streak model to encourage application usage will create steady progress towards environmentally conscious adults.