Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants

Research output: Contribution to journalReviewpeer-review

Standard

Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants. / Caballero, Daniel; Bevilacqua, Marta; Amigo, José Manuel.

In: Journal of Spectral Imaging, Vol. 8, a1, 2019.

Research output: Contribution to journalReviewpeer-review

Harvard

Caballero, D, Bevilacqua, M & Amigo, JM 2019, 'Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants', Journal of Spectral Imaging, vol. 8, a1. https://doi.org/10.1255/jsi.2019.a1

APA

Caballero, D., Bevilacqua, M., & Amigo, J. M. (2019). Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants. Journal of Spectral Imaging, 8, [a1]. https://doi.org/10.1255/jsi.2019.a1

Vancouver

Caballero D, Bevilacqua M, Amigo JM. Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants. Journal of Spectral Imaging. 2019;8. a1. https://doi.org/10.1255/jsi.2019.a1

Author

Caballero, Daniel ; Bevilacqua, Marta ; Amigo, José Manuel. / Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants. In: Journal of Spectral Imaging. 2019 ; Vol. 8.

Bibtex

@article{aa8e31faf39c4f62ac2a8a71a0def519,
title = "Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants",
abstract = "Most plastics need to incorporate flame retardants to meet fire safety standards requirements. The amount and the type of flame retardants can differ, so that in waste plastics a large variety of polymers and flame retardants can be found. The recycling of plastics containing flame retardants is increasing. However, only plastics of the same polymer type and the same additive content can be recycled together. Three models based on different chemometrics techniques applied to hyperspectral imaging in the near infrared range were developed [partial least square-discriminant analysis, decision tree (DT) and hierarchical model (HM)]. Optimal results were obtained for all classification techniques. HM shows the highest error at all levels due to the noisy spectra of the black plastics. However, DT classification gave outstanding results, considering that the sensitivity was higher than 0.9 in all cases. Thus, the application of DT with hyperspectral imaging could be used to sort plastic samples with respect to the type of polymer and the flame retardant used with a high degree of accuracy in an automated way. These findings are highly valuable for the plastic and waste management industries.",
keywords = "Decision tree, Flame retardants, Hierarchical classification, NIR hyperspectral imaging, Partial least square-discrimination analysis, Plastics recycling, Polymer, Waste recycling",
author = "Daniel Caballero and Marta Bevilacqua and Amigo, {Jos{\'e} Manuel}",
year = "2019",
doi = "10.1255/jsi.2019.a1",
language = "English",
volume = "8",
journal = "Journal of Spectral Imaging",
issn = "2040-4565",
publisher = "IM Publications Open LLP",

}

RIS

TY - JOUR

T1 - Application of hyperspectral imaging and chemometrics for classifying plastics with brominated flame retardants

AU - Caballero, Daniel

AU - Bevilacqua, Marta

AU - Amigo, José Manuel

PY - 2019

Y1 - 2019

N2 - Most plastics need to incorporate flame retardants to meet fire safety standards requirements. The amount and the type of flame retardants can differ, so that in waste plastics a large variety of polymers and flame retardants can be found. The recycling of plastics containing flame retardants is increasing. However, only plastics of the same polymer type and the same additive content can be recycled together. Three models based on different chemometrics techniques applied to hyperspectral imaging in the near infrared range were developed [partial least square-discriminant analysis, decision tree (DT) and hierarchical model (HM)]. Optimal results were obtained for all classification techniques. HM shows the highest error at all levels due to the noisy spectra of the black plastics. However, DT classification gave outstanding results, considering that the sensitivity was higher than 0.9 in all cases. Thus, the application of DT with hyperspectral imaging could be used to sort plastic samples with respect to the type of polymer and the flame retardant used with a high degree of accuracy in an automated way. These findings are highly valuable for the plastic and waste management industries.

AB - Most plastics need to incorporate flame retardants to meet fire safety standards requirements. The amount and the type of flame retardants can differ, so that in waste plastics a large variety of polymers and flame retardants can be found. The recycling of plastics containing flame retardants is increasing. However, only plastics of the same polymer type and the same additive content can be recycled together. Three models based on different chemometrics techniques applied to hyperspectral imaging in the near infrared range were developed [partial least square-discriminant analysis, decision tree (DT) and hierarchical model (HM)]. Optimal results were obtained for all classification techniques. HM shows the highest error at all levels due to the noisy spectra of the black plastics. However, DT classification gave outstanding results, considering that the sensitivity was higher than 0.9 in all cases. Thus, the application of DT with hyperspectral imaging could be used to sort plastic samples with respect to the type of polymer and the flame retardant used with a high degree of accuracy in an automated way. These findings are highly valuable for the plastic and waste management industries.

KW - Decision tree

KW - Flame retardants

KW - Hierarchical classification

KW - NIR hyperspectral imaging

KW - Partial least square-discrimination analysis

KW - Plastics recycling

KW - Polymer

KW - Waste recycling

U2 - 10.1255/jsi.2019.a1

DO - 10.1255/jsi.2019.a1

M3 - Review

AN - SCOPUS:85070597134

VL - 8

JO - Journal of Spectral Imaging

JF - Journal of Spectral Imaging

SN - 2040-4565

M1 - a1

ER -

ID: 228375124