Comparison of classification methods performance for defining the best reuse of waste wood material using NIR spectroscopy

Manuela Mancini*, Veli-Matti Taavitsainen, Åsmund Rinnan

*Corresponding author af dette arbejde

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

2 Citationer (Scopus)
12 Downloads (Pure)

Abstract

Recycling of post-consumer waste wood material is becoming an increasingly appealing alternative to disposal. However, its huge heterogeneity is calling for an assessment of the material characteristics in order to define the best recycling option and intended reuse. In fact, waste wood comes into a variety of uses/types of wood, along with several levels of contamination, and it can be divided into different categories based on its composition and quality grade. This study provides the measurement of more than a hundred waste wood samples and their characterisation using a hand-held NIR spectrophotometer. Three classification methods, i.e. K-nearest Neighbours (KNN), Principal Component Analysis – Linear Discriminant Analysis (PCA-LDA) and PCA-KNN, have been compared to develop models for the sorting of waste wood in quality categories according to the best-suited reuse. In addition, the classification performance has been investigated as a function of the number of the spectral measurements of the sample and as the average of the spectral measurements. The results showed that PCA-KNN performs better than the other classification methods, especially when the material is ground to 5 cm of particle size and the spectral measurements are averaged across replicates (classification accuracy: 90.9 %). NIR spectroscopy, coupled with chemometrics, turned out to be a promising tool for the real-time sorting of waste wood material, ensuring a more accurate and sustainable waste wood management. Obtaining real-time information about the quality and characteristics of waste wood material translates into a decision of the best recycling option, increasing its recycling potential.

OriginalsprogEngelsk
TidsskriftWaste Management
Vol/bind178
Sider (fra-til)321-330
Antal sider10
ISSN0956-053X
DOI
StatusUdgivet - 2024

Bibliografisk note

Funding Information:
The project leading to this application has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 838560.

Funding Information:
The project leading to this application has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 838560.

Publisher Copyright:
© 2024 The Author(s)

Citationsformater