Discrimination of Milk Adulterated with Urea Using Voltammetric Electronic Tongue coupled with PCA-LSSVM

摘要

This paper proposed a novel method for qualitative analysis of urea-tainted milk samples based onvoltammetric electronic tongue coupled with multivariable analysis method. The electronic tongueadopted three kinds of metals, such as gold, platinum, and palladium, as working electrodes. 26 puremilk samples and 26 urea-tainted milk samples with different concentration values were prepared. Themeasurement principles involved the extraction of information from cyclic voltammograms recordedin unadulterated and adulterated milk samples. The response current for different working electrodeshas been considered for data analysis. A mean-centering and normalization method was employed forthe raw current data. The classification algorithm of this system is separated into two phases: (1) thefeature reduction by principal component analysis (PCA); (2) the classification by least square supportvector machine (LSSVM). When principal component factors are equal to 10, the optimal PCA- LSSVM model was obtained and discrimination rate of the LSSVM model are 100% and 94.12% inthe calibration set and the prediction set, respectively. The results demonstrated that the voltammetricelectronic tongue technology with PCA-LSSVM multivariable data analysis method can besuccessfully applied to the classification between unadulterated milk samples and adulterated milksamples.