For the data analysis, principal component analysis (PCA) was
carried out on the SNV- and MSC-processed spectra from both FTNIR
and FT-IR. PCA can readily be applied to spectroscopic data to
perceive the nature and scattering level of the data. The first principal
component (PC1) describes the maximum of variation or spread in
the samples. A second principal component (PC2), orthogonal to the
first (i.e., completely uncorrelated), describes the maximum of the
variation not described by the first eigenvector, and so on. With this
procedure, the most important features of the data set can be seen in a
low-dimensionality plot.19 A multivariate calibration model of a partial
least-squares regression (PLSR) was then developed using all of the
preprocessed spectral data to predict the extent of adulteration in the
pure onion and adulterated onion powder samples. PLSR is
particularly suited when the matrix of predictors has more variables
than observations, such as from spectral data. PLSR has been used in
food authentication studies based in spectroscopic data.11 Multivariate
analysis was performed using MATLAB software version 7.0.4 (The
Mathworks, Natick, MA, USA)