Bottle Recycling Machine Using Convolutional Neural Network

Authors

  • Samir Lohani Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal
  • Saroj Kumar Shrestha Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal
  • Rahul Kumar Singh Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal
  • Baikuntha Kumar Acharya Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal
  • Bharat Bhatta Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal
  • Bipin Thapa Magar Sagarmatha Engineering College, Tribhuvan University, Lalitpur, Nepal

DOI:

https://doi.org/10.3126/injet.v1i1.60895

Keywords:

Reverse Vending Machine (RVM), Bottle Recycling Machine (BRM), Machine Learning, Convolutional Neural Network (CNN), Solid Waste Management

Abstract

Every day, billions of plastic bottles and cans are used worldwide. Most of these wastes end up in landfills or as litter. These plastic bottles and aluminium cans can be recycled, to transform into other household products. As plastic bottles are cheaper to produce than to recycle, recycling is not preferred. In the meantime, people are neglecting the adverse effects of plastics and cans. For recycling plastic bottles and cans effective segregation is the major issue which requires high accuracy and precision. Most of the segregation is done manually to separate plastic bottles from other waste, which increases labor costs thus, making recycling unreliable economically. Here we have proposed a system that employs machine vision to distinguish bottles and cans using a CNN. There isn’t any sensor that can accurately identify plastic bottles with high accuracy. So, we have tried to complete this task using a deep learning algorithm. Being an automated system, it doesn't require a full-fledged team to manage which makes the recycling process feasible from monetary perspective. Different compartments are allocated for plastics and cans. When an item is accurately identified by the system, it is placed in the respective compartments. A reward is given to the user as a redeemable code to encourage recycling behavior. The system has an accuracy of 96% in identifying items and proves to be an effective pre-recycling process.

Downloads

Download data is not yet available.
Abstract
200
PDF
100

Downloads

Published

2023-12-21

How to Cite

Lohani, S., Shrestha, S. K., Singh, R. K., Acharya, B. K., Bhatta, B., & Magar, B. T. (2023). Bottle Recycling Machine Using Convolutional Neural Network. International Journal on Engineering Technology, 1(1), 1–10. https://doi.org/10.3126/injet.v1i1.60895

Issue

Section

Articles