Rapid identification of adulterated cow milk by non-linear pattern recognition methods based on near infrared spectroscopy

• Published in: Food chemistry 2014-02, Vol.145, p.342-348
• Main Authors: Zhang, Li-Guo, Zhang, Xin, Ni, Li-Jun, Xue, Zhi-Bin, Gu, Xin, Huang, Shi-Xin
• Format: Article
• Language: English
• Subjects: Adulterants; Animals; Biological and medical sciences; Cattle; Female; Food Contamination - analysis; Food toxicology; Improved and simplified K nearest neighbours; Improved support vector machine; Mathematical models; Medical sciences; Milk; Milk - chemistry; Near infrared spectroscopy; Nonlinearity; Pattern recognition; Rapid identification of adulterated cow milks; Raw; Spectra; Spectroscopy, Near-Infrared - methods; Support Vector Machine; Support vector machines; Toxicology; Uniform design
• ISSN: 0308-8146; 1873-7072
• DOI: 10.1016/j.foodchem.2013.08.064

•NIR spectroscopy technique was applied to rapidly discriminate adulterated milks from raw milks.•The NIR models were validated by more than 800 representative milk samples.•Uniform design theory reduced 90% computation work of optimizing parameters of SVM.•Adulteration solution concentration and sample numbers greatly influence model result.•Complicated milk samples should be authenticated by non-linear pattern recognition methods. More than 800 representative milk samples, which consisted of 287 raw cow milk samples from different pastures surrounding Shanghai of China and 526 adulteration milk samples containing different pseudo proteins and thickeners, were collected and designed to demonstrate a method for rapidly discriminating adulterated milks based on near infrared (NIR) spectra. The NIR classification models were built by two non-linear supervised pattern recognition methods of improved support vector machine (I-SVM) and improved and simplified K nearest neighbours (IS-KNN). Uniform design theory was applied to optimize the parameters of SVM and thus the computation amount was reduced 90%. Both two methods exhibit good adaptability in discriminating adulterated milks from raw cow milks. Further investigation showed that the correction ratio for discriminating milk samples increased with the increasing of adulteration solutions’ level in the adulterated milk. The concentration of adulterants is an important factor of influencing milk discrimination results of the NIR pattern recognition models. The results demonstrated the usefulness of NIR spectra combined with non-linear pattern recognition methods as an objective and rapid method for the authentication of complicated raw cow milks.