Improving Waste Sorting Systems: Enhancing Sustainability and Resource Recovery

Deshmukh, Arshil Khalid (2024) Improving Waste Sorting Systems: Enhancing Sustainability and Resource Recovery. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (635kB) | Preview

Abstract

This research investigates through the design and implementation of the deep learning techniques for advanced waste classification system using hybrid transfer learning to enhance resource recovery and sustainability in environment. By using deep learning methods such as InceptionV3, MobileNetv2, ResNet50, VGG16 and EfficientB0, the study develops a multi-class classification model to categories the diverse waste categories. A dataset compromising real world data and augmented images for better training and evaluating the models, addressing challenges like class imbalances, diverse data types and low quality images. The models like InceptionV3 and VGG16 achieves high accuracy with high precision and recall on the pre trained models using weights. Results demonstrates InceptionV3 as champion model which gives us accuracy of 91%, precision and recall of 91% as well. This study highlights the advancement in pre processing, light weight model optimization and precise image detection. These findings and results gets us to sustainable practice by minimizing landfill dependency and promoting circular economy principles through effective waste sorting.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haycock, Barry UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 10:06
Last Modified:	02 Sep 2025 10:06
URI:	https://norma.ncirl.ie/id/eprint/8691

Actions (login required)

View Item