FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387359966> ?p ?o ?g. }

• W4387359966 endingPage "12" @default.
• W4387359966 startingPage "1" @default.
• W4387359966 abstract "ABSTRACTA chemistry-based explainable machine learning (ML) approach was used to predict wood properties using near infrared (NIR) spectral data collected from rough and smooth surfaces, and to provide better understanding of the role of important NIR wavelengths (features) in the performance of ML models. NIR spectra collected from western hemlock (Tsuga heterophylla) and coastal Douglas-fir (Pseudotsuga menziesii) boards with rough and smooth surfaces were fed into random forest and TreeNet; a gradient boosting machine algorithm, for predicting wood density, modulus of elasticity (MOE) and modulus of rupture (MOR). The TreeNet model could predict the MOE, MOR, and density with R2 of 0.66, 0.64, and 0.64 using spectra collected from rough surface and R2 of 0.54, 0.46, and 0.46 using spectra collected from smooth surface. TreeNet outperformed the random forest, and for both ML algorithms higher R2 and lower error were obtained using NIR data collected from rough surfaces. This suggested that for Douglass fir and western hemlock, NIR spectra could be collected on a sawn surface prior to surface planing. However, it is difficult to generalize the impact of surface roughness on the performance of predictive model as different factors (e.g. what constitutes a smooth or rough surface, variability of data set in terms of wood properties) impact the success of predictive models. NIR features having the greatest influence on TreeNet models were examined and consistently had wood chemistry specific band assignments. The most important features occurred in the O-H first overtone, and C–H second overtone regions and a narrow zone (approximately 2400–2500 nm) of the C–H stretch C–C stretch combination region. Important features also differed by property and with surface roughness. Explaining ML model performance using the relative importance of the NIR features showed the importance of wood chemistry related information when developing models, however MOE and MOR TreeNet models based on smooth surface NIR spectra showed an increased importance of water related features. Overall, the chemistry-based explainable machine learning model approach allows for identification of important NIR features, and regions, and aids in understanding how they contribute to the performance of NIR-based wood property predictive models.KEYWORDS: Wood materialsmechanical propertiesensemble learninggradient boosting machinenear-infrared spectroscopysurface roughness Disclosure statementNo potential conflict of interest was reported by the author(s)." @default.
• W4387359966 created "2023-10-06" @default.
• W4387359966 creator A5041076499 @default.
• W4387359966 creator A5045814524 @default.
• W4387359966 creator A5057412664 @default.
• W4387359966 creator A5069250833 @default.
• W4387359966 date "2023-10-05" @default.
• W4387359966 modified "2023-10-06" @default.
• W4387359966 title "A chemistry-based explainable machine learning model based on NIR spectra for predicting wood properties and understanding wavelength selection" @default.
• W4387359966 cites W1784941097 @default.
• W4387359966 cites W1972268602 @default.
• W4387359966 cites W1981601683 @default.
• W4387359966 cites W1981883640 @default.
• W4387359966 cites W2002163331 @default.
• W4387359966 cites W2032042699 @default.
• W4387359966 cites W2034568337 @default.
• W4387359966 cites W2037868419 @default.
• W4387359966 cites W2058645560 @default.
• W4387359966 cites W2065746048 @default.
• W4387359966 cites W2077341198 @default.
• W4387359966 cites W2095521908 @default.
• W4387359966 cites W2146459408 @default.
• W4387359966 cites W2170318131 @default.
• W4387359966 cites W2463592071 @default.
• W4387359966 cites W2526674818 @default.
• W4387359966 cites W2531958015 @default.
• W4387359966 cites W2610332124 @default.
• W4387359966 cites W2782812883 @default.
• W4387359966 cites W2789517267 @default.
• W4387359966 cites W2809520059 @default.
• W4387359966 cites W2967869210 @default.
• W4387359966 cites W2969387865 @default.
• W4387359966 cites W2970009524 @default.
• W4387359966 cites W2977224613 @default.
• W4387359966 cites W2981731882 @default.
• W4387359966 cites W3022390254 @default.
• W4387359966 cites W3028005548 @default.
• W4387359966 cites W3042063492 @default.
• W4387359966 cites W3088497682 @default.
• W4387359966 cites W3100340856 @default.
• W4387359966 cites W3114378343 @default.
• W4387359966 cites W3120640809 @default.
• W4387359966 cites W3126547908 @default.
• W4387359966 cites W3134290309 @default.
• W4387359966 cites W3134999114 @default.
• W4387359966 cites W3135707159 @default.
• W4387359966 cites W3158028120 @default.
• W4387359966 cites W3208877831 @default.
• W4387359966 cites W4205441376 @default.
• W4387359966 cites W4249358576 @default.
• W4387359966 cites W4285388434 @default.
• W4387359966 cites W4293763360 @default.
• W4387359966 cites W4296580937 @default.
• W4387359966 cites W4319298176 @default.
• W4387359966 cites W4385858713 @default.
• W4387359966 cites W74037523 @default.
• W4387359966 doi "https://doi.org/10.1080/17480272.2023.2265349" @default.
• W4387359966 hasPublicationYear "2023" @default.
• W4387359966 type Work @default.
• W4387359966 citedByCount "0" @default.
• W4387359966 crossrefType "journal-article" @default.
• W4387359966 hasAuthorship W4387359966A5041076499 @default.
• W4387359966 hasAuthorship W4387359966A5045814524 @default.
• W4387359966 hasAuthorship W4387359966A5057412664 @default.
• W4387359966 hasAuthorship W4387359966A5069250833 @default.
• W4387359966 hasConcept C107365816 @default.
• W4387359966 hasConcept C119857082 @default.
• W4387359966 hasConcept C120665830 @default.
• W4387359966 hasConcept C121332964 @default.
• W4387359966 hasConcept C127313418 @default.
• W4387359966 hasConcept C1276947 @default.
• W4387359966 hasConcept C154945302 @default.
• W4387359966 hasConcept C159390177 @default.
• W4387359966 hasConcept C159985019 @default.
• W4387359966 hasConcept C169258074 @default.
• W4387359966 hasConcept C186060115 @default.
• W4387359966 hasConcept C192562407 @default.
• W4387359966 hasConcept C2777983457 @default.
• W4387359966 hasConcept C2779237806 @default.
• W4387359966 hasConcept C33923547 @default.
• W4387359966 hasConcept C38615331 @default.
• W4387359966 hasConcept C39432304 @default.
• W4387359966 hasConcept C41008148 @default.
• W4387359966 hasConcept C43571822 @default.
• W4387359966 hasConcept C4839761 @default.
• W4387359966 hasConcept C49040817 @default.
• W4387359966 hasConcept C59822182 @default.
• W4387359966 hasConcept C6260449 @default.
• W4387359966 hasConcept C62649853 @default.
• W4387359966 hasConcept C86803240 @default.
• W4387359966 hasConceptScore W4387359966C107365816 @default.
• W4387359966 hasConceptScore W4387359966C119857082 @default.
• W4387359966 hasConceptScore W4387359966C120665830 @default.
• W4387359966 hasConceptScore W4387359966C121332964 @default.
• W4387359966 hasConceptScore W4387359966C127313418 @default.
• W4387359966 hasConceptScore W4387359966C1276947 @default.
• W4387359966 hasConceptScore W4387359966C154945302 @default.
• W4387359966 hasConceptScore W4387359966C159390177 @default.

• next