Back To Projects

AI in Recycling

Nicholas K.

By using a machine learning algorithm, we have been able to create a tool that can detect what type of material an item is and determine whether it is recyclable or not.


The plastic pollution issue is an issue that has been plaguing the earth for the past half century and longer. Despite this, it has only been brought to light in the 21st century, and technology to help solve the issue is still new and largely undeveloped. Being someone who is passionate about environmental conservation, I wanted to create a tool that could be used to more easily sort recycling items. By using a machine learning algorithm, we have been able to create a tool that can detect what type of material an item is and determine whether it is recyclable or not. This tool can be applied to many different industry sectors, whether it is sorting items in a recycling plant, building it into an app for people to use day to day, or even aiding the plastic oceans cleanup effort. By creating this tool, we help do our part in protecting our planet and helping those who are less educated in the field to do so as well. We have approached the problem by using various machine learning algorithms to identify the material of items in a dataset. Using a KNN and CNN algorithm, we created a tool that became more and more accurate in identifying the material of an item. After testing the KNN and the CNN algorithm, we found that the CNN algorithm was much more accurate reaching a 68 % accuracy compared to 46% accuracy

Explore More!

Nicholas K.
Shreyas Muralidharan
PhD Candidate in Electrical and Electronics Engineering at Stanford

Related Projects

workspace_premium
Predicting Climate Change Using an Autoregressive Long Short-Term Memory Model

This study aims to create a baseline machine learning model that utilizes an Autoregressive Recurrent Neural network with a Long Short term memory implementation for the purpose of predicting climate.
Seokhyun C.
Mentored by Victoria Lloyd
Smart Agriculture: Optimizing Soil pH and Crop Recommendations Using Machine Learning

This study explores how hyperparameter tuning enhances the performance of machine learning models, achieving a 99.5% accuracy in crop classification and highlighting the potential of AI-driven optimization for sustainable precision agriculture.
Pracheth G.
Mentored by Henry Cerbone
A Comprehensive Study of Machine Learning Models for the Prediction of pH in Fairfax County

Water quality is drastically declining as bodies of water become more and more acidic due to global warming. Because of this, it is crucial to understand what factors determine pH, and how to predict pH values. In this study, we determine which features are most important in determining pH, and also what combination of features and machine learning models give us the best accuracy in the prediction of pH values. We demonstrate that pH values from the previous year and the percentage of rehabilitated sanitary sewer lines are the most important features in determining pH. We also demonstrate that Decision Tree Models and Random Forest Models perform the best across all features and feature subsets.
Matthew N.
Mentored by Sarthak Kanodia