Neural Network Based Method for Melamine Analysis in Liquid Milk

Author

Smirnov, Sergey V.

Author_Institution

Unimilk Joint Stock Co., Russia

Volume

2

fYear

2011

fDate

28-29 March 2011

Firstpage

999

Lastpage

1002

Abstract

We propose the use of spectroscopy data-produced by near-infrared (near-IR/NIR) and mid-infrared (mid-IR/MIR) spectroscopies, in particular-for melamine detection in complex dairy matrixes. It was found that infrared spectroscopy is an effective tool to detect melamine in liquid milk. The limit of detection (LOD) below 1 ppm (0.75 ppm) can be reached if a correct spectrum pre-processing (pre-treatment) technique and a correct multivariate (MDA) algorithm: partial least squares regression (PLS), polynomial PLS (Poly-PLS), or artificial neural network (ANN)-is used for spectrum analysis. It can be concluded that mid- and near-infrared spectroscopy can be regarded as a quick, sensitive, robust, and low-cost method for liquid milk analysis. The technique can be applied for the automation of milk analysis.

Keywords

dairy products; food safety; infrared spectroscopy; least squares approximations; neural nets; regression analysis; artificial neural network based method; liquid milk; melamine analysis; mid-infrared spectroscopies; multivariate algorithm; near-infrared spectroscopies; polynomial partial least squares regression; spectroscopy data; Artificial neural networks; Calibration; Dairy products; Petroleum; Powders; Spectroscopy; artificial neural network (ANN); food; liquid milk; partial least squares regression (PLS);

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on

Conference_Location

Shenzhen, Guangdong

Print_ISBN

978-1-61284-289-9

Type

conf

DOI

10.1109/ICICTA.2011.535

Filename

5751060