Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine

A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based revers...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taeyoung Yoo, Seongjae Lee, Taehyoun Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	convolutional neural network neural network ensemble edge AI device reverse vending machine waste classification Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/0ccda1ae7f354ff8bbbcd2d7c2740b00
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0ccda1ae7f354ff8bbbcd2d7c2740b00
record_format	dspace
spelling	oai:doaj.org-article:0ccda1ae7f354ff8bbbcd2d7c2740b002021-11-25T16:43:20ZDual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine10.3390/app1122110512076-3417https://doaj.org/article/0ccda1ae7f354ff8bbbcd2d7c2740b002021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/11051https://doaj.org/toc/2076-3417A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based reverse vending machines suffer from a high configuration cost and the limited scope of target objects, and conventional single image-based reverse vending machines usually make erroneous predictions about intentional fraud objects. This paper proposes a dual image-based convolutional neural network ensemble model to address these problems. For this purpose, we first created a prototype reverse vending machine and constructed an image dataset containing two cross-sections of objects, top and front view. Then, we chose convolutional neural network models widely used in image classification as the candidates for building an accurate and lightweight ensemble model. Considering the size and classification performance of candidates, we constructed the best-fit ensemble combination and evaluated its classification performance. The final ensemble model showed a classification accuracy higher than 95% for all target classes, including fraud objects. This result proves that our approach achieves better robustness against intentional fraud objects than single image-based models and thus can broaden the scope for target resources. The measurement results on lightweight embedded platforms also demonstrated that our model provides a short inference time that is enough to facilitate the real-time execution of reverse vending machines based on low-cost edge artificial intelligence devices.Taeyoung YooSeongjae LeeTaehyoun KimMDPI AGarticleconvolutional neural networkneural network ensembleedge AI devicereverse vending machinewaste classificationTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 11051, p 11051 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	convolutional neural network neural network ensemble edge AI device reverse vending machine waste classification Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	convolutional neural network neural network ensemble edge AI device reverse vending machine waste classification Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Taeyoung Yoo Seongjae Lee Taehyoun Kim Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
description	A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based reverse vending machines suffer from a high configuration cost and the limited scope of target objects, and conventional single image-based reverse vending machines usually make erroneous predictions about intentional fraud objects. This paper proposes a dual image-based convolutional neural network ensemble model to address these problems. For this purpose, we first created a prototype reverse vending machine and constructed an image dataset containing two cross-sections of objects, top and front view. Then, we chose convolutional neural network models widely used in image classification as the candidates for building an accurate and lightweight ensemble model. Considering the size and classification performance of candidates, we constructed the best-fit ensemble combination and evaluated its classification performance. The final ensemble model showed a classification accuracy higher than 95% for all target classes, including fraud objects. This result proves that our approach achieves better robustness against intentional fraud objects than single image-based models and thus can broaden the scope for target resources. The measurement results on lightweight embedded platforms also demonstrated that our model provides a short inference time that is enough to facilitate the real-time execution of reverse vending machines based on low-cost edge artificial intelligence devices.
format	article
author	Taeyoung Yoo Seongjae Lee Taehyoun Kim
author_facet	Taeyoung Yoo Seongjae Lee Taehyoun Kim
author_sort	Taeyoung Yoo
title	Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
title_short	Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
title_full	Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
title_fullStr	Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
title_full_unstemmed	Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine
title_sort	dual image-based cnn ensemble model for waste classification in reverse vending machine
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0ccda1ae7f354ff8bbbcd2d7c2740b00
work_keys_str_mv	AT taeyoungyoo dualimagebasedcnnensemblemodelforwasteclassificationinreversevendingmachine AT seongjaelee dualimagebasedcnnensemblemodelforwasteclassificationinreversevendingmachine AT taehyounkim dualimagebasedcnnensemblemodelforwasteclassificationinreversevendingmachine
_version_	1718412998851166208

Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine

Ejemplares similares