Incorporating Chemical Band-Assignment in near Infrared Spectroscopy Regression Models

Abstract

In this paper, we present an approach for incorporating chemical band assignment information in regression models between spectra and constituents. It is shown how the matrices in this L-shaped data structure can be combined and give direct information of the relationships between theoretical chemical band assignment, spectral wavelengths and the responses. The chosen application is NIR spectroscopic measurements of canola seeds. Variable selection based on partial least squares regression using jack-knifing within a cross-model validation (CMV) framework is applied for removing non-relevant spectral regions. Extended multiplicative scatter correction was applied as a spectral pre-treatment to remove physical scatter effects in the spectra. The results show a high degree of correspondence between the objectively found wavelength bands from CMV and the reported chemical interpretation found in the literature.

Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network

“…In the Spectral range 2, the wavelengths at 1136, 1177, 1251, 1325, 1386, 1440, 1494 and 1619 nm showed greater differences. The wavelengths at 1136, 1177 and 1251 nm are attributed to the second overtone of C-H stretching mode [26]. The wavelength at 1386 nm (around 1387 nm) might be attributed to the first overtone of stretching and anti-symmetric O-H bond [27].…”

Towards enhancing sustainable reuse of pre-treated drill cuttings for construction purposes by near-infrared analysis: A review

“…Spectral preprocessing techniques that have been applied include (but not limited to) the following: (1) averaging replicate spectra, (2) maximum normalisation, (3) fitting a weighted (inverse measurement variance) smoothing spline to each spectra with direct extraction of smoothed reflectance, (4) use of first and second derivatives of the original spectra, (5) individually combining the resulting average reflectance with the first-and second-derivatives, (6) multiplicative and extended multiplicative scatter correction, (7) Savitzky-Golay, and (8) standard normal variate Dematte et al, 2004;Viscarra-Rossel et al, 2006b;Westad et al, 2008;Yu et al, 2008;Sundaram et al, 2010;Chen et al, 2010;Kuang and Mouazen, 2011). Alternatively, variableselection techniques, which minimize the number of simultaneous variables to be used in modelling, have also been applied in this regard.…”

“…Usually, the calibration methods that provide the largest accuracy are optimized using cross-validation procedures (Westad et al, 2008) and validated independently with independent validation set not used in the crossvalidation procedure. The model performance in terms of the root mean square error (RMSE) of validation or prediction, as well as residual prediction deviation (RPD) and the corresponding coefficient of determination (r 2 ) may be evaluated.…”

Predicting rapeseed oil content with near-infrared spectroscopy

“…This is a result of the stretching vibrations of the functional groups that are more intense in this region, due to atoms with different electronegativity values, such as hydroxyl atoms (Westad et al, 2008). Therefore, because of its association with water, that region may not be adequate for establishing the calibration equation.…”