Abstract
In manufacturing, monitoring the mechanical properties of wood with near infrared spectroscopy (NIR) is an attractive alternative to more conventional methods. However, no attention has been given to see if models differ between juvenile and mature wood. Additionally, it would be convenient if multiple linear regression (MLR) could perform well in the place of more complicated multivariate models. Therefore, the purpose of this paper was to model the strength, stiffness and density of mature and juvenile longleaf pine to NIR spectra with MLR and principal component regression (PCR).
Keywords
Multivariate,
principal component,
multiple linear,
regression,
density,
modulus,
NIR,
spectroscopy,
wood,
lumber
Citation
Via, Brian K.; Shupe, Todd F.; Groom, Leslie H.; Stine, Michael; So, Chi-Leung. 2003. Multivariate modelling of density, strength, and stiffness from near infared for mature, juvenile, and pith wood of longleaf pine (
Pinus Palustris). Near Infared Spectroscopy 11:365-378