Simultaneous determination of melamine and dicyandiamide in milk by UV spectroscopy coupled with chemometrics

A simple, rapid and accurate method for simultaneous determination of melamine and dicyandiamide in milk by UV spectroscopy coupled with chemometrics was proposed. In total, 1728 sample solutions were designed and prepared with 3 kinds of milk powder samples and 3 kinds of liquid milk samples to demonstrate this method. Six spectral pretreatment methods, including the smoothing method of Savitzky–Golay (Smoothing-SG), area normalization (Nor), standard normal variate (SNV), multiplicative scatter correction (MSC), first derivative Savitzky–Golay (1d + SG) and second derivative gap-segment (2d + GS) were used to preprocess the raw spectra for building regression models by partial least squares (PLS) regression, support vector machine (SVM) and least-squares support vector machine (LS-SVM). For milk powder samples, the LS-SVM algorithm gave the best prediction of melamine and dicyandiamide with RSDs of 8.53% and 5.31%, respectively, and LODs of 14.2 mg kg⁻¹ and 8.84 mg kg⁻¹, respectively. For liquid milk samples, the best prediction of melamine and dicyandiamide was obtained by the SVM algorithm with RSDs of 4.97% and 3.46%, respectively, and LODs of 9.94 mg L⁻¹ and 6.91 mg L⁻¹, respectively.