Acta Photonica Sinica, Volume. 42, Issue 5, 580(2013)
Discrimination of Adulterated Milk Using NPLSDA Combined with Twodimensional Correlation Nearinfrared Spectroscopy
In order to develop a rapid, costeffective and highthroughput analysis method for detecting adulterants in milk, adulterated milk discriminant models are established by combing twodimensional (2D) correlation nearinfrared spectroscopy with multiway partial least squaresdiscriminant analysis (NPLSDA). 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 NPLSDA models of ureatainted milk, melaminetainted 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, PLSDA and OPLSDA models are established. The results show that NPLSDA model has better predictive ability than PLSDA model and OPLSDA model, and this method can also be applied to other food safety detection areas.
Get Citation
Copy Citation Text
YANG Renjie, LIU Rong, XU Kexin, YANG Yanrong. Discrimination of Adulterated Milk Using NPLSDA Combined with Twodimensional Correlation Nearinfrared Spectroscopy[J]. Acta Photonica Sinica, 2013, 42(5): 580
Received: Nov. 13, 2012
Accepted: --
Published Online: May. 22, 2013
The Author Email: Renjie YANG (rjyang1978@163.com)