Variable selection coupled to PLS2, ANN and SVM for simultaneous detection of multiple adulterants in milk using spectral data

Rani, Amsaraj and Neha Dilip, Ambade and Sarma, Mutturi (2021) Variable selection coupled to PLS2, ANN and SVM for simultaneous detection of multiple adulterants in milk using spectral data. Journal of International Dairy, 123. pp. 1-11.

PDF 1-s2.0-S0958694621002004-main.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Fourier transform infrared (FT-IR) spectroscopy combined with chemometric methods was used to detect multiple adulterants in milk samples simultaneously. PLS-DA (partial least squares discriminant analysis) and SVM (support vector machine) were used for the 100% accurate classification of samples to differ- entiate the adulterants. RCGA (real coded genetic algorithm) was used to obtain 20, 30, and 40 different fingerprint wavenumbers from milk FT-IR spectra when spiked with starch, urea, and sucrose. Amongst the four algorithms tested, the performance of LS-SVM was observed to be superior having higher values for correlation coefficient (R2p ) for prediction of 0.9843, 0.9763, and 0.9964 and lower root-mean-square error of prediction (RMSEP) of 0.4197, 0.2617, and 0.3771 for starch, urea, and sucrose, respectively. RCGA was established as an efficient feature selection algorithm for obtaining user-defined fingerprints. Also, LS-SVM was demonstrated as a robust non-linear regression algorithm for simultaneous detection of milk adulterants.

Item Type:	Article
Uncontrolled Keywords:	milk adulterants, Food safety, spectral data
Subjects:	600 Technology > 08 Food technology > 13 Quality control 600 Technology > 08 Food technology > 27 Dairy products
Divisions:	Food Microbiology
Depositing User:	Somashekar K S
Date Deposited:	11 Mar 2025 06:31
Last Modified:	11 Mar 2025 06:31
URI:	http://ir.cftri.res.in/id/eprint/19258

Actions (login required)

View Item