Material sorting using hyperspectral imaging for biocomposite recycling

Tuomas Sormunen; Sari Järvinen; Arttu Lämsä; Kirsi Immonen; Juha Mannila; Johannes Peltola

Material sorting using hyperspectral imaging for biocomposite recycling

Tuomas Sormunen, Sari Järvinen, Arttu Lämsä, Kirsi Immonen, Juha Mannila, Johannes Peltola

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract in proceedings › Scientific

81 Downloads (Pure)

Abstract

The impending exhaustion of non-renewable natural resources emphasizes the importance of sustainable materials. One environmentally friendlier alternative to plastics are biocomposite materials, which are composed of recycled or virgin polymer and a natural fiber material. In order to be to be truly sustainable, the material has to be efficiently recycled, a task which demands a means for their sorting. This paper outlines a method for distinguishing different plastic and biocomposite samples from one another based on hyperspectral imaging. The developed regression model correctly classified 96 % of the samples in the dataset. In the case of biocomposite samples, the accompanying polymer was quite accurately recognized.

Original language	English
Title of host publication	4th International Conference on Natural Fibers – Smart Sustainable Solutions, ICNF 2019
Subtitle of host publication	Book of Abstracts
Editors	Raul Fanguiero
Publisher	Universidade do Minho
Pages	250-251
ISBN (Electronic)	978-972-8600-30-3
Publication status	Published - 2019
MoE publication type	Not Eligible

Access to Document

ICNF2019_sormunen_split_pdfFinal published version, 460 KB

Cite this

@inbook{1f0102dae9ad4e88b0d0952fb7898648,

title = "Material sorting using hyperspectral imaging for biocomposite recycling",

abstract = "The impending exhaustion of non-renewable natural resources emphasizes the importance of sustainable materials. One environmentally friendlier alternative to plastics are biocomposite materials, which are composed of recycled or virgin polymer and a natural fiber material. In order to be to be truly sustainable, the material has to be efficiently recycled, a task which demands a means for their sorting. This paper outlines a method for distinguishing different plastic and biocomposite samples from one another based on hyperspectral imaging. The developed regression model correctly classified 96 % of the samples in the dataset. In the case of biocomposite samples, the accompanying polymer was quite accurately recognized.",

author = "Tuomas Sormunen and Sari J{\"a}rvinen and Arttu L{\"a}ms{\"a} and Kirsi Immonen and Juha Mannila and Johannes Peltola",

year = "2019",

language = "English",

pages = "250--251",

editor = "Raul Fanguiero",

booktitle = "4th International Conference on Natural Fibers – Smart Sustainable Solutions, ICNF 2019",

publisher = "Universidade do Minho",

address = "Portugal",

}

Material sorting using hyperspectral imaging for biocomposite recycling. / Sormunen, Tuomas ; Järvinen, Sari ; Lämsä, Arttu et al.
4th International Conference on Natural Fibers – Smart Sustainable Solutions, ICNF 2019: Book of Abstracts. ed. / Raul Fanguiero. Universidade do Minho, 2019. p. 250-251.

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract in proceedings › Scientific

TY - CHAP

T1 - Material sorting using hyperspectral imaging for biocomposite recycling

AU - Sormunen, Tuomas

AU - Järvinen, Sari

AU - Lämsä, Arttu

AU - Immonen, Kirsi

AU - Mannila, Juha

AU - Peltola, Johannes

PY - 2019

Y1 - 2019

N2 - The impending exhaustion of non-renewable natural resources emphasizes the importance of sustainable materials. One environmentally friendlier alternative to plastics are biocomposite materials, which are composed of recycled or virgin polymer and a natural fiber material. In order to be to be truly sustainable, the material has to be efficiently recycled, a task which demands a means for their sorting. This paper outlines a method for distinguishing different plastic and biocomposite samples from one another based on hyperspectral imaging. The developed regression model correctly classified 96 % of the samples in the dataset. In the case of biocomposite samples, the accompanying polymer was quite accurately recognized.

AB - The impending exhaustion of non-renewable natural resources emphasizes the importance of sustainable materials. One environmentally friendlier alternative to plastics are biocomposite materials, which are composed of recycled or virgin polymer and a natural fiber material. In order to be to be truly sustainable, the material has to be efficiently recycled, a task which demands a means for their sorting. This paper outlines a method for distinguishing different plastic and biocomposite samples from one another based on hyperspectral imaging. The developed regression model correctly classified 96 % of the samples in the dataset. In the case of biocomposite samples, the accompanying polymer was quite accurately recognized.

M3 - Conference abstract in proceedings

SP - 250

EP - 251

BT - 4th International Conference on Natural Fibers – Smart Sustainable Solutions, ICNF 2019

A2 - Fanguiero, Raul

PB - Universidade do Minho

ER -

Material sorting using hyperspectral imaging for biocomposite recycling

Abstract

Access to Document

Fingerprint

Cite this