Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models

<p dir="ltr">The proper handling of waste is one of the biggest challenges of modern society. Municipal Solid Waste (MSW) requires categorization into a number of types, including bio, plastic, glass, metal, paper, etc. The most efficient techniques proposed by researchers so far inc...

Full description

Saved in:
Bibliographic Details
Main Author: Meena Malik (17542089) (author)
Other Authors: Sachin Sharma (25799) (author), Mueen Uddin (4903510) (author), Chin-Ling Chen (17542074) (author), Chih-Ming Wu (17542092) (author), Punit Soni (17542095) (author), Shikha Chaudhary (14145747) (author)
Published: 2022
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513531082178560
author Meena Malik (17542089)
author2 Sachin Sharma (25799)
Mueen Uddin (4903510)
Chin-Ling Chen (17542074)
Chih-Ming Wu (17542092)
Punit Soni (17542095)
Shikha Chaudhary (14145747)
author2_role author
author
author
author
author
author
author_facet Meena Malik (17542089)
Sachin Sharma (25799)
Mueen Uddin (4903510)
Chin-Ling Chen (17542074)
Chih-Ming Wu (17542092)
Punit Soni (17542095)
Shikha Chaudhary (14145747)
author_role author
dc.creator.none.fl_str_mv Meena Malik (17542089)
Sachin Sharma (25799)
Mueen Uddin (4903510)
Chin-Ling Chen (17542074)
Chih-Ming Wu (17542092)
Punit Soni (17542095)
Shikha Chaudhary (14145747)
dc.date.none.fl_str_mv 2022-06-13T03:00:00Z
dc.identifier.none.fl_str_mv 10.3390/su14127222
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Waste_Classification_for_Sustainable_Development_Using_Image_Recognition_with_Deep_Learning_Neural_Network_Models/24717537
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Environmental engineering
Information and computing sciences
Artificial intelligence
Machine learning
litter classification
convolution neural networks
machine learning
EfficientNet-B0
dc.title.none.fl_str_mv Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The proper handling of waste is one of the biggest challenges of modern society. Municipal Solid Waste (MSW) requires categorization into a number of types, including bio, plastic, glass, metal, paper, etc. The most efficient techniques proposed by researchers so far include neural networks. In this paper, a detailed summarization was made of the existing deep learning techniques that have been proposed to classify waste. This paper proposes an architecture for the classification of litter into the categories specified in the benchmark approaches. The architecture used for classification was EfficientNet-B0. These are compound-scaling based models proposed by Google that are pretrained on ImageNet and have an accuracy of 74% to 84% in top-1 over ImageNet. This research proposes EfficientNet-B0 model tuning for images specific to particular demographic regions for efficient classification. This type of model tuning over transfer learning provides a customized model for classification, highly optimized for a particular region. It was shown that such a model had comparable accuracy to that of EfficientNet-B3, however, with a significantly smaller number of parameters required by the B3 model. Thus, the proposed technique achieved efficiency on the order of 4X in terms of FLOPS. Moreover, it resulted in improvised classifications as a result of fine-tuning over region-wise specific litter images.</p><h2>Other Information</h2><p dir="ltr">Published in: Sustainability<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/su14127222" target="_blank">https://dx.doi.org/10.3390/su14127222</a></p><p dir="ltr">Disclaimer: The University of Doha for Science and Technology replaced the now-former College of the North Atlantic-Qatar after an Amiri decision in 2022. UDST has become and first national applied University in Qatar; it is also second national University in the country.</p>
eu_rights_str_mv openAccess
id Manara2_44c22ec8ea207ec10a4543e948970a9f
identifier_str_mv 10.3390/su14127222
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24717537
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network ModelsMeena Malik (17542089)Sachin Sharma (25799)Mueen Uddin (4903510)Chin-Ling Chen (17542074)Chih-Ming Wu (17542092)Punit Soni (17542095)Shikha Chaudhary (14145747)EngineeringEnvironmental engineeringInformation and computing sciencesArtificial intelligenceMachine learninglitter classificationconvolution neural networksmachine learningEfficientNet-B0<p dir="ltr">The proper handling of waste is one of the biggest challenges of modern society. Municipal Solid Waste (MSW) requires categorization into a number of types, including bio, plastic, glass, metal, paper, etc. The most efficient techniques proposed by researchers so far include neural networks. In this paper, a detailed summarization was made of the existing deep learning techniques that have been proposed to classify waste. This paper proposes an architecture for the classification of litter into the categories specified in the benchmark approaches. The architecture used for classification was EfficientNet-B0. These are compound-scaling based models proposed by Google that are pretrained on ImageNet and have an accuracy of 74% to 84% in top-1 over ImageNet. This research proposes EfficientNet-B0 model tuning for images specific to particular demographic regions for efficient classification. This type of model tuning over transfer learning provides a customized model for classification, highly optimized for a particular region. It was shown that such a model had comparable accuracy to that of EfficientNet-B3, however, with a significantly smaller number of parameters required by the B3 model. Thus, the proposed technique achieved efficiency on the order of 4X in terms of FLOPS. Moreover, it resulted in improvised classifications as a result of fine-tuning over region-wise specific litter images.</p><h2>Other Information</h2><p dir="ltr">Published in: Sustainability<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/su14127222" target="_blank">https://dx.doi.org/10.3390/su14127222</a></p><p dir="ltr">Disclaimer: The University of Doha for Science and Technology replaced the now-former College of the North Atlantic-Qatar after an Amiri decision in 2022. UDST has become and first national applied University in Qatar; it is also second national University in the country.</p>2022-06-13T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.3390/su14127222https://figshare.com/articles/journal_contribution/Waste_Classification_for_Sustainable_Development_Using_Image_Recognition_with_Deep_Learning_Neural_Network_Models/24717537CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/247175372022-06-13T03:00:00Z
spellingShingle Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
Meena Malik (17542089)
Engineering
Environmental engineering
Information and computing sciences
Artificial intelligence
Machine learning
litter classification
convolution neural networks
machine learning
EfficientNet-B0
status_str publishedVersion
title Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
title_full Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
title_fullStr Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
title_full_unstemmed Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
title_short Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
title_sort Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models
topic Engineering
Environmental engineering
Information and computing sciences
Artificial intelligence
Machine learning
litter classification
convolution neural networks
machine learning
EfficientNet-B0