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

Rani, Amsaraj and Sarma, Mutturi (2023) Rapid detection of sunset yellow adulteration in tea powder with variable selection coupled to machine learning tools using spectral data. Journal of Food Science and Technology, 60 (5). pp. 1530-1540. ISSN 0022-1155

PDF J Food Sci Technol (May 2023) 60(5)1530–1540.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

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

Item Type:	Article
Uncontrolled Keywords:	Tea-adulteration · Sunset yellow · RCGA · LS-SVM · RF · XGBoost
Subjects:	600 Technology > 07 Beverage Technology > 08 Tea 600 Technology > 08 Food technology > 31 Food Additives
Divisions:	Food Microbiology
Depositing User:	Food Sci. & Technol. Information Services
Date Deposited:	24 May 2023 11:22
Last Modified:	24 May 2023 11:22
URI:	http://ir.cftri.res.in/id/eprint/16462

Actions (login required)

View Item