Discrimination of Adulterated Milk Using NPLSDA Combined with Twodimensional Correlation Nearinfrared Spectroscopy

In order to develop a rapid,cost-effective and high-throughput analysis method for detecting adulterants in milk,adulterated milk discriminant models are established by combing two-dimensional(2D) correlation near-infrared spectroscopy with multi-way partial least squares-discriminant analysis(NPLS-DA).40 adulterated milk samples with melamine(0.01~3 g/L)and 40 adulterated milk samples with urea(1~20 g/L)are prepared respectively,then the absorption spectra of all samples are measured.Based on quantization of 2D correlation spectrum,the NPLS-DA models of urea-tainted milk,melamine-tainted milk and two types adulterated milk are constructed.The recognition rates of unknown samples are 95%,90%,and 92.5% by calibration models individually.At the same time,PLS-DA and OPLS-DA models are established.The results show that NPLS-DA model has better predictive ability than PLS-DA model and OPLS-DA model,and this method can also be applied to other food safety detection areas.