Estimation of the Physical Wood Properties of Pinus Taeda L. Radial Strips Using Least Squares Support Vector Machines

Near infrared (NIR) spectroscopy offers a rapid method for estimating many important wood properties, including air-dry density, microfibril angle (MFA) and SilviScan estimated stiffness (EL(SS)). Wood property calibrations may be improved by using non-linear calibration methods. In this study, we compare calibrations developed using partial least squares (PLS) regression and least-squares support vector machine (LS-SVM) regression, a relatively new technique for modelling multivariate, non-linear systems. LS-SVM regression provided the strongest calibration statistics for all wood properties. For an equivalent number of latent variables, the predictive performance of the MFA LS-SVM calibrations were superior to those of the corresponding PLS calibration, while predictive results for air-dry density and EL(SS) were similar for both calibration methods.

[1]  Johan A. K. Suykens,et al.  Nonlinear modeling : advanced black-box techniques , 1998 .

[2]  Robert Evans,et al.  Estimation of Eucalyptus delegatensis wood properties by near infrared spectroscopy , 2001 .

[3]  Robert Evans,et al.  ESTIMATION OF WOOD STIFFNESS OF INCREMENT CORES BY NEAR INFRARED SPECTROSCOPY: THE DEVELOPMENT AND APPLICATION OF CALIBRATIONS BASED ON SELECTED CORES , 2002 .

[4]  P. Williams,et al.  Comparison of Commercial near Infrared Transmittance and Reflectance Instruments for Analysis of Whole Grains and Seeds , 1993 .

[5]  Roger Meder,et al.  Stiffness Prediction of Radiata Pine Clearwood Test Pieces Using near Infrared Spectroscopy , 2001 .

[6]  Anto Rimbawanto,et al.  Near infrared spectroscopy for cost effective screening of foliar oil characteristics in a Melaleuca cajuputi breeding population. , 2003, Journal of agricultural and food chemistry.

[7]  Robert Evans,et al.  Estimation of Pinus radiata D. Don tracheid morphological characteristics by near infrared spectroscopy , 2004 .

[8]  J. A. Wright,et al.  Prediction of pulp yield and cellulose content from wood samples using near infrared reflectance spectroscopy , 1990 .

[9]  S. Wold,et al.  Nonlinear PLS modeling , 1989 .

[10]  Robert Evans,et al.  ESTIMATION OF MICROFIBRIL ANGLE OF INCREMENT CORES BY NEAR INFRARED SPECTROSCOPY , 2002 .

[11]  Robert Evans,et al.  Estimation of air-dry density of increment cores by near infrared spectroscopy , 2003 .

[12]  T. P. Schultz,et al.  Rapid secondary analysis of lignocellulose: comparison of near infrared (NIR) and Fourier transform infrared (FTIR). , 1990 .

[13]  Robert P. Cogdill,et al.  Least-Squares Support Vector Machines for Chemometrics: An Introduction and Evaluation , 2004 .

[14]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[15]  Alfred Teischinger,et al.  The Relationship between near Infrared Spectra of Radial Wood Surfaces and Wood Mechanical Properties , 2001 .

[16]  Robert Evans,et al.  Rapid Measurement of the Transverse Dimensions of Tracheids in Radial Wood Sections from Pinus radiata , 1994 .

[17]  Laurence R. Schimleck,et al.  Development of near infrared reflectance analysis calibrations for estimating genetic parameters for cellulose content in Eucalyptus globulus , 2002 .

[18]  A. J. Michell.  Pulpwood quality estimation by near-infrared spectroscopic measurements on eucalypt woods , 1995 .

[19]  John S. Shenk,et al.  Population Definition, Sample Selection, and Calibration Procedures for Near Infrared Reflectance Spectroscopy , 1991 .

[20]  V. Vapnik.  The Support Vector Method of Function Estimation , 1998 .

[21]  Roger Meder,et al.  Sawmill Trial of At-Line Prediction of Recovered Lumber Stiffness by NIR Spectroscopy of Pinus Radiata Cants , 2003 .

[22]  T. Sonoda,et al.  Non-destructive Determination of Wood Constituents by Fourier Transform Raman Spectroscopy , 1997 .

[23]  Lisbeth G. Thygesen,et al.  Determination of Dry Matter Content and Basic Density of Norway Spruce by near Infrared Reflectance and Transmittance Spectroscopy , 1994 .

[24]  Laurence R. Schimleck,et al.  Applications of NIR spectroscopy to forest research , 2000 .

[25]  T. Sonoda,et al.  Non-Destructive Determination of Hemicellulosic Neutral Sugar Composition in Native Wood by Fourier Transform Raman Spectroscopy , 1998 .

[26]  Richard F. Daniels,et al.  Estimation of the physical wood properties of green Pinus taeda radial samples by near infrared spectroscopy , 2003 .

[27]  T. Næs,et al.  Locally weighted regression and scatter correction for near-infrared reflectance data , 1990 .

[28]  T. Sonoda,et al.  Non-destructive determination of lignin syringyl/guaiacyl monomeric composition in native wood by Fourier transform Raman spectroscopy , 1998 .

[29]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[30]  R Evans,et al.  木材でのミクロフィブリル角のX線回折測定法による算定への分散近似法 | 文献情報 | J-GLOBAL 科学技術総合リンクセンター , 1999 .

[31]  C. B. Lucasius,et al.  Understanding and using genetic algorithms Part 1. Concepts, properties and context , 1993 .