Neural network based method for melamine analysis in liquid milk
We propose the use of spectroscopy data - produced by near-infrared (near-IR/NIR) and mid-infrared (midIR/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.
food liquid milk partial least squares regression (PLS) artificial neural network (ANN)
Sergey V. Smimov
Unimilk Joint Stock Co.Moscow region, Russia
国际会议
深圳
英文
999-1002
2011-03-28（万方平台首次上网日期，不代表论文的发表时间）