Cover Image

DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK

Recycling is one of the most important approaches to safeguard the environment since it aims to reduce waste in landfills while conserving natural resources. Using deep Learning networks, this group of wastes may be automatically classified on the belts of a waste sorting plant. However, a basic set...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammed A.B., Al-Mafrji A.A.M., Yassen M.S., Sabry A.H.
Other Authors: 57686887900
Format: Article
Published: Technology Center 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-27197
record_format dspace
spelling my.uniten.dspace-271972023-05-29T17:40:49Z DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK Mohammed A.B. Al-Mafrji A.A.M. Yassen M.S. Sabry A.H. 57686887900 57686888000 57686375400 56602511900 Recycling is one of the most important approaches to safeguard the environment since it aims to reduce waste in landfills while conserving natural resources. Using deep Learning networks, this group of wastes may be automatically classified on the belts of a waste sorting plant. However, a basic set of connected layers may not be adequate to give satisfactory accuracy for such multi output classifier tasks. To optimize the gradient flow and enable deeper training for network design with multi label classifier, this study suggests a residual-based deep learning convolutional neural network. For network training, ten classes have been explored. The Directed Acyclic Graph (DAG) is a structure with hidden layers that have inputs, outputs, and other layers. The DAG network�s residual-based architecture features shortcut connections that bypass some levels of the network, allowing gradients of network parameters to travel freely among the network output layers for deeper training. The methodology includes: 1. preparing the data and creating an augmented image data store; 2. defining the main serially-connected branches of the network architecture; 3. defining the residual interconnections that bypass the main branch layers; 4. defining layers, and finally; creating a residual-based deeper layer graph. The concept is to split down the multiclass classification problem into minor binary states, where every classifier performs as an expert by concentrating on discriminating between only two labels, improving total accuracy. The results achieve (2.861 %) training error and (9.76 %) a validation error. The training results of this classifier are evaluated by finding the training error, validation error, and showing the confusion matrix of validation data � Copyright � 2022, Authors. This is an open access article under the Creative Commons CC BY license Final 2023-05-29T09:40:49Z 2023-05-29T09:40:49Z 2022 Article 10.15587/1729-4061.2022.254285 2-s2.0-85130033669 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130033669&doi=10.15587%2f1729-4061.2022.254285&partnerID=40&md5=e8eb0e32ded63833958313bbfea65645 https://irepository.uniten.edu.my/handle/123456789/27197 2 10-116 42 49 All Open Access, Gold, Green Technology Center Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Recycling is one of the most important approaches to safeguard the environment since it aims to reduce waste in landfills while conserving natural resources. Using deep Learning networks, this group of wastes may be automatically classified on the belts of a waste sorting plant. However, a basic set of connected layers may not be adequate to give satisfactory accuracy for such multi output classifier tasks. To optimize the gradient flow and enable deeper training for network design with multi label classifier, this study suggests a residual-based deep learning convolutional neural network. For network training, ten classes have been explored. The Directed Acyclic Graph (DAG) is a structure with hidden layers that have inputs, outputs, and other layers. The DAG network�s residual-based architecture features shortcut connections that bypass some levels of the network, allowing gradients of network parameters to travel freely among the network output layers for deeper training. The methodology includes: 1. preparing the data and creating an augmented image data store; 2. defining the main serially-connected branches of the network architecture; 3. defining the residual interconnections that bypass the main branch layers; 4. defining layers, and finally; creating a residual-based deeper layer graph. The concept is to split down the multiclass classification problem into minor binary states, where every classifier performs as an expert by concentrating on discriminating between only two labels, improving total accuracy. The results achieve (2.861 %) training error and (9.76 %) a validation error. The training results of this classifier are evaluated by finding the training error, validation error, and showing the confusion matrix of validation data � Copyright � 2022, Authors. This is an open access article under the Creative Commons CC BY license
author2 57686887900
author_facet 57686887900
Mohammed A.B.
Al-Mafrji A.A.M.
Yassen M.S.
Sabry A.H.
format Article
author Mohammed A.B.
Al-Mafrji A.A.M.
Yassen M.S.
Sabry A.H.
spellingShingle Mohammed A.B.
Al-Mafrji A.A.M.
Yassen M.S.
Sabry A.H.
DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
author_sort Mohammed A.B.
title DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
title_short DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
title_full DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
title_fullStr DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
title_full_unstemmed DEVELOPING PLASTIC RECYCLING CLASSIFIER BY DEEP LEARNING AND DIRECTED ACYCLIC GRAPH RESIDUAL NETWORK
title_sort developing plastic recycling classifier by deep learning and directed acyclic graph residual network
publisher Technology Center
publishDate 2023
_version_ 1806424396119670784
score 13.211869

Similar Items