FTIR spectra were collected in the mid-infrared (MIR) region of
4000–650 cm1 because of its sensitivity to baseband vibration
and its specificity. The FTIR spectra of 32 samples appeared fairly
similar, and it was very difficult to differentiate walnut oils from
other oils. Therefore, classification models were necessary to be
built by extracting the detailed information from spectral data.
Meanwhile, to remove undesirable factors in the raw data, derivatives
and SNV were used to optimize data preprocessing to reduce
the influence of spectral variations caused by baseline shifts and
scattering effects.