Cargando…
Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning
The quality control of thermally modified wood and identifying heat treatment intensity using nondestructive testing methods are critical tasks. This study used near-infrared (NIR) spectroscopy and machine learning modeling to classify thermally modified wood. NIR spectra were collected from the sur...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610413/ https://www.ncbi.nlm.nih.gov/pubmed/37896391 http://dx.doi.org/10.3390/polym15204147 |
_version_ | 1785128248952225792 |
---|---|
author | Nasir, Vahid Schimleck, Laurence Abdoli, Farshid Rashidi, Maria Sassani, Farrokh Avramidis, Stavros |
author_facet | Nasir, Vahid Schimleck, Laurence Abdoli, Farshid Rashidi, Maria Sassani, Farrokh Avramidis, Stavros |
author_sort | Nasir, Vahid |
collection | PubMed |
description | The quality control of thermally modified wood and identifying heat treatment intensity using nondestructive testing methods are critical tasks. This study used near-infrared (NIR) spectroscopy and machine learning modeling to classify thermally modified wood. NIR spectra were collected from the surfaces of untreated and thermally treated (at 170 °C, 212 °C, and 230 °C) western hemlock samples. An explainable machine learning approach was practiced using a TreeNet gradient boosting machine. No dimensionality reduction was performed to better explain the feature ranking results obtained from the model and provide insight into the critical wavelengths contributing to the performance of classification models. NIR spectra in the ranges of 1100–2500 nm, 1400–2500 nm, and 1700–2500 nm were fed into the TreeNet model, which resulted in classification accuracy values (test data) of 94.35%, 89.29%, and 84.52%, respectively. Feature ranking analysis revealed that when using the range of 1100–2500 nm, the changes in wood color resulted in the highest variation in NIR reflectance amongst treatments. As a result, associated features were given higher importance by TreeNet. Limiting the wavelength range increased the significance of features related to water or wood chemistry; however, these predictive models were not as accurate as the one benefiting from the impact of wood color change on the NIR spectra. The developed framework could be applied to different applications in which NIR spectra are used for wood characterization and quality control to provide improved insights into selected NIR wavelengths when developing a machine learning model. |
format | Online Article Text |
id | pubmed-10610413 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-106104132023-10-28 Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning Nasir, Vahid Schimleck, Laurence Abdoli, Farshid Rashidi, Maria Sassani, Farrokh Avramidis, Stavros Polymers (Basel) Article The quality control of thermally modified wood and identifying heat treatment intensity using nondestructive testing methods are critical tasks. This study used near-infrared (NIR) spectroscopy and machine learning modeling to classify thermally modified wood. NIR spectra were collected from the surfaces of untreated and thermally treated (at 170 °C, 212 °C, and 230 °C) western hemlock samples. An explainable machine learning approach was practiced using a TreeNet gradient boosting machine. No dimensionality reduction was performed to better explain the feature ranking results obtained from the model and provide insight into the critical wavelengths contributing to the performance of classification models. NIR spectra in the ranges of 1100–2500 nm, 1400–2500 nm, and 1700–2500 nm were fed into the TreeNet model, which resulted in classification accuracy values (test data) of 94.35%, 89.29%, and 84.52%, respectively. Feature ranking analysis revealed that when using the range of 1100–2500 nm, the changes in wood color resulted in the highest variation in NIR reflectance amongst treatments. As a result, associated features were given higher importance by TreeNet. Limiting the wavelength range increased the significance of features related to water or wood chemistry; however, these predictive models were not as accurate as the one benefiting from the impact of wood color change on the NIR spectra. The developed framework could be applied to different applications in which NIR spectra are used for wood characterization and quality control to provide improved insights into selected NIR wavelengths when developing a machine learning model. MDPI 2023-10-19 /pmc/articles/PMC10610413/ /pubmed/37896391 http://dx.doi.org/10.3390/polym15204147 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Nasir, Vahid Schimleck, Laurence Abdoli, Farshid Rashidi, Maria Sassani, Farrokh Avramidis, Stavros Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title | Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title_full | Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title_fullStr | Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title_full_unstemmed | Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title_short | Quality Control of Thermally Modified Western Hemlock Wood Using Near-Infrared Spectroscopy and Explainable Machine Learning |
title_sort | quality control of thermally modified western hemlock wood using near-infrared spectroscopy and explainable machine learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610413/ https://www.ncbi.nlm.nih.gov/pubmed/37896391 http://dx.doi.org/10.3390/polym15204147 |
work_keys_str_mv | AT nasirvahid qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning AT schimlecklaurence qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning AT abdolifarshid qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning AT rashidimaria qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning AT sassanifarrokh qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning AT avramidisstavros qualitycontrolofthermallymodifiedwesternhemlockwoodusingnearinfraredspectroscopyandexplainablemachinelearning |