Kernel PLS regression on wavelet transformed NIR spectra for prediction of sugar content of apple

Abstract A kernel PLS algorithm was implemented to estimate the sugar content of Golden Delicious apples based on NIR reflectance spectra in the range of 800–1690 nm. Covariance, Gaussian and polynomial kernel functions were considered. All kernels, except the covariance kernel, incorporate tuning parameters which were optimised by computer experiments. The calibration results were insensitive to the actual value of the tuning parameters over a wide range. No significant difference between the RMSEP values obtained with different kernels was obtained, irrespective of the applied transformation (none, log(1/ R ), Kubelka–Munck) or first order derivative calculation. A wavelet compression procedure was implemented to speed up the computation of the kernel Gram matrices. It was shown that the kernel Gram matrix computed with the approximation and detail coefficients of the wavelet transformed spectra converges in norm to the real kernel Gram matrix. The time required for calculating the kernel Gram matrix is inversely proportional to the compression ratio. It was shown that a compression ratio of up to 25 did not affect the accuracy of the kernel PLS calibration models.

[1]  D. Massart,et al.  Application of wavelet transform to extract the relevant component from spectral data for multivariate calibration. , 1997, Analytical chemistry.

[2]  Tormod Næs,et al.  A user-friendly guide to multivariate calibration and classification , 2002 .

[3]  Kristin P. Bennett,et al.  An Optimization Perspective on Kernel Partial Least Squares Regression , 2003 .

[4]  Randolph M. Beaudry,et al.  Determination of firmness and sugar content of apples using near-infrared diffuse reflectance , 2000 .

[5]  Johan A. K. Suykens,et al.  Subset based least squares subspace regression in RKHS , 2005, Neurocomputing.

[6]  R. Manne,et al.  Fast regression methods in a Lanczos (or PLS-1) basis. Theory and applications , 2000 .

[7]  S. Wold,et al.  The kernel algorithm for PLS , 1993 .

[8]  D. Massart,et al.  The Radial Basis Functions — Partial Least Squares approach as a flexible non-linear regression technique , 1996 .

[9]  J. Roger,et al.  Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapes , 2004 .

[10]  A. Peirs,et al.  Effect of biological variability on the robustness of NIR models for soluble solids content of apples , 2003 .

[11]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[12]  Renfu Lu,et al.  A NEAR–INFRARED SENSING TECHNIQUE FOR MEASURING INTERNAL QUALITY OF APPLE FRUIT , 2002 .

[13]  C. Greensill,et al.  Sorting of Fruit Using near Infrared Spectroscopy: Application to a Range of Fruit and Vegetables for Soluble Solids and Dry Matter Content , 2004 .

[14]  Roman Rosipal,et al.  Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space , 2002, J. Mach. Learn. Res..

[15]  B. Nicolai,et al.  NON-DESTRUCTIVE MEASUREMENT OF ACIDITY, SOLUBLE SOLIDS, AND FIRMNESS OF JONAGOLD APPLES USING NIR-SPECTROSCOPY , 1998 .

[16]  J. Abbott,et al.  NEAR-INFRARED DIFFUSE REFLECTANCE FOR QUANTITATIVE AND QUALITATIVE MEASUREMENT OF SOLUBLE SOLIDS AND FIRMNESS OF DELICIOUS AND GALA APPLES , 2003 .

[17]  A. Peirs,et al.  Temperature compensation for near infrared reflectance measurement of apple fruit soluble solids contents , 2003 .

[18]  A. Peirs,et al.  PH—Postharvest Technology: Comparison of Fourier Transform and Dispersive Near-Infrared Reflectance Spectroscopy for Apple Quality Measurements , 2002 .

[19]  T. Næs,et al.  The Effect of Multiplicative Scatter Correction (MSC) and Linearity Improvement in NIR Spectroscopy , 1988 .

[20]  J. Vandewalle,et al.  Primal space sparse kernel partial least squares regression for large scale problems , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  Junbin Gao,et al.  Chemometrics: From Basics to Wavelet Transform , 2004 .

[22]  V. Mcglone,et al.  Transmission Measurements on Intact Apples Moving at High Speed , 2004 .

[23]  S. D. Jong.  SIMPLS: an alternative approach to partial least squares regression , 1993 .

[24]  A. Peirs,et al.  Light penetration properties of NIR radiation in fruit with respect to non-destructive quality assessment , 2000 .

[25]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[26]  Desire L. Massart,et al.  Chapter 7 – Joint Basis and Joint Best-basis for Data Sets , 2000 .

[27]  Desire L. Massart,et al.  Local modelling with radial basis function networks , 2000 .

[28]  Bhupinder S. Dayal,et al.  Improved PLS algorithms , 1997 .

[29]  D. Massart,et al.  Application of Radial Basis Functions — Partial Least Squares to non-linear pattern recognition problems: diagnosis of process faults , 1996 .

[30]  S. Wold,et al.  A PLS kernel algorithm for data sets with many variables and fewer objects. Part 1: Theory and algorithm , 1994 .

[31]  S. Wold,et al.  PLS regression on wavelet compressed NIR spectra , 1998 .

[32]  Beata Walczak,et al.  Wavelets in Chemistry , 2001 .

[33]  Desire L. Massart,et al.  Chapter 15 - Calibration in Wavelet Domain , 2000 .