Rapid detection of sunset yellow adulteration in tea powder with variable selection coupled to machine learning tools using spectral data.

In the present study sunset yellow (SY), a syn�thetic colour, which is a common adulterant in tea powders
has been analysed using FT-IR spectral data coupled to
machine learning tools for efcient classifcation and quanti�fcation of the SY adulteration. Earlier established real coded
genetic algorithm (RCGA) was used as variable selection
method to predict the key fngerprints of SY in the FT-IR
spectra. Here, RCGA was used to select 20, 30, 40, 50 and
60 characteristic wavenumbers for SY. Classifcation was
carried using support vector machine (SVM), random for�est (RF) and extreme gradient boosting (XGB) classifers.
SVM classifer using 50 variables could give an accuracy
of 0.90 amongst the three. Quantifcation of SY based on
PLS (partial least squares), LS-SVM (least squares-SVM),
RF and XGBoost were built on characteristic wavenumbers.
Both RF and LS-SVM models were observed to be supe�rior to PLS when coupled to RCGA obtained 20 fngerprint
variables. Overall, RCGA-LS-SVM model resulted in lowest
RMSECV (0.1956) with regression co-efcient values RC
2
= 0.9989 and RP
2
= 0.9979, when 50 fngerprint variables
were used. These results demonstrated that FT-IR combined
with RCGA-LS-SVM procedure could be a robust technique
for rapid detection of SY in tea powder