Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images

In polyethylene terephthalate's (PET)'s recycling processes, separation from polyvinyl chloride (PVC) is of prior relevance due to its toxicity, which degrades the final quality of recycled PET. Moreover, the potential presence of some polymers in mixed plastics (such as PVC in PET) is a key aspect...

Descripción completa

Detalles Bibliográficos
Autores principales: Galdon-Navarro, Borja, Prats-Montalbán, José M., Cubero, Sergio, Blasco, José, Ferrer, Alberto
Formato: article
Lenguaje:Inglés
Publicado: 2019
Materias:
Acceso en línea:http://hdl.handle.net/20.500.11939/6210
_version_ 1855032386313519104
author Galdon-Navarro, Borja
Prats-Montalbán, José M.
Cubero, Sergio
Blasco, José
Ferrer, Alberto
author_browse Blasco, José
Cubero, Sergio
Ferrer, Alberto
Galdon-Navarro, Borja
Prats-Montalbán, José M.
author_facet Galdon-Navarro, Borja
Prats-Montalbán, José M.
Cubero, Sergio
Blasco, José
Ferrer, Alberto
author_sort Galdon-Navarro, Borja
collection ReDivia
description In polyethylene terephthalate's (PET)'s recycling processes, separation from polyvinyl chloride (PVC) is of prior relevance due to its toxicity, which degrades the final quality of recycled PET. Moreover, the potential presence of some polymers in mixed plastics (such as PVC in PET) is a key aspect for the use of recycled plastic in products such as medical equipment, toys, or food packaging. Many works have dealt with plastic classification by hyperspectral imaging, although only some of them have been directly focused on PET sorting and very few on its separation from PVC. These works use different classification models and preprocessing techniques and show their performance for the problem at hand. However, still, there is a lack of methodology to address the goal of comparing and finding the best model and preprocessing technique. Thus, this paper presents a design of experiments-based methodology for comparing and selecting, for the problem at hand, the best preprocessing technique, and the best latent variable-based and/or artificial intelligence classification method, when using NIR hyperspectral images. There is a lack of methodology to address the goal of comparing and finding the best model and preprocessing technique. Thus, this paper presents a design of experiments-based methodology for comparing and selecting, for the problem at hand, the best preprocessing technique, and the best latent variable-based and/or artificial intelligence classification method when using near-infrared hyperspectral images.
format article
id ReDivia6210
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2019
publishDateRange 2019
publishDateSort 2019
record_format dspace
spelling ReDivia62102025-04-25T14:46:30Z Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images Galdon-Navarro, Borja Prats-Montalbán, José M. Cubero, Sergio Blasco, José Ferrer, Alberto multivariate image analysis hyperspectral images In polyethylene terephthalate's (PET)'s recycling processes, separation from polyvinyl chloride (PVC) is of prior relevance due to its toxicity, which degrades the final quality of recycled PET. Moreover, the potential presence of some polymers in mixed plastics (such as PVC in PET) is a key aspect for the use of recycled plastic in products such as medical equipment, toys, or food packaging. Many works have dealt with plastic classification by hyperspectral imaging, although only some of them have been directly focused on PET sorting and very few on its separation from PVC. These works use different classification models and preprocessing techniques and show their performance for the problem at hand. However, still, there is a lack of methodology to address the goal of comparing and finding the best model and preprocessing technique. Thus, this paper presents a design of experiments-based methodology for comparing and selecting, for the problem at hand, the best preprocessing technique, and the best latent variable-based and/or artificial intelligence classification method, when using NIR hyperspectral images. There is a lack of methodology to address the goal of comparing and finding the best model and preprocessing technique. Thus, this paper presents a design of experiments-based methodology for comparing and selecting, for the problem at hand, the best preprocessing technique, and the best latent variable-based and/or artificial intelligence classification method when using near-infrared hyperspectral images. 2019-05-15T10:37:41Z 2019-05-15T10:37:41Z 2018 article acceptedVersion Galdon-Navarro, B.; Manuel Prats-Montalban, J.; Cubero, S.; Blasco, J.; Ferrer, A. (2018). Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images. Journal of Chemometrics, 32(1), e2980. http://hdl.handle.net/20.500.11939/6210 10.1002/cem.2980 en Atribución-NoComercial-SinDerivadas 3.0 España http://creativecommons.org/licenses/by-nc-nd/3.0/es/ electronico
spellingShingle multivariate image analysis
hyperspectral images
Galdon-Navarro, Borja
Prats-Montalbán, José M.
Cubero, Sergio
Blasco, José
Ferrer, Alberto
Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title_full Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title_fullStr Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title_full_unstemmed Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title_short Comparison of latent variable-based and artificial intelligence methods for impurity detection in PET recycling from NIR hyperspectral images
title_sort comparison of latent variable based and artificial intelligence methods for impurity detection in pet recycling from nir hyperspectral images
topic multivariate image analysis
hyperspectral images
url http://hdl.handle.net/20.500.11939/6210
work_keys_str_mv AT galdonnavarroborja comparisonoflatentvariablebasedandartificialintelligencemethodsforimpuritydetectioninpetrecyclingfromnirhyperspectralimages
AT pratsmontalbanjosem comparisonoflatentvariablebasedandartificialintelligencemethodsforimpuritydetectioninpetrecyclingfromnirhyperspectralimages
AT cuberosergio comparisonoflatentvariablebasedandartificialintelligencemethodsforimpuritydetectioninpetrecyclingfromnirhyperspectralimages
AT blascojose comparisonoflatentvariablebasedandartificialintelligencemethodsforimpuritydetectioninpetrecyclingfromnirhyperspectralimages
AT ferreralberto comparisonoflatentvariablebasedandartificialintelligencemethodsforimpuritydetectioninpetrecyclingfromnirhyperspectralimages