Comparison Between MIR and NIR Spectroscopic Techniques for the Determination of Fat and Protein Contents in Milk  

作　　者：张学典 常敏 马真 彭丹 徐可欣 

机构地区：[1]State Key Laboratory of Precision Measuring Technology and Instruments,Tianjin University

出　　处：《Transactions of Tianjin University》2007年第5期375-378,共4页天津大学学报（英文版）

基　　金：Supported by National Natural Science Foundation of China(No.30170261);the 10th Five-Year Plan of China(No.2004BA706B12).

摘　　要：To compare mid-infrared(MIR)and near-infrared(NIR)spectroscopies for the determination of the fat and protein contents in milk,the same sample sets with varying concentrations of fat and protein were measured in the MIR range of 3 200-700 cm-1 and NIR range of 9 000-4 000 cm-1.The spectral features in the two regions were analyzed.The MIR spectra of milk were characteristic due to the MIR inherent molecular specificity,whereas the NIR spectra were relatively characterless due to the NIR low selectivity.Partial least squares(PLS)regression models for fat and protein were developed by using both MIR and NIR spectra.MIR data with no pretreatment gave better results than NIR data.The square correlation coefficient(R2)and the root mean square error of prediction(RMSEP)were 0.98 and 0.10 g/dL for fat and 0.97 and 0.11 g/dL for protein.With NIR techniques,satisfactory results were not obtained with raw data.However,NIR data after pretreatment gave similarly good results to the ones using MIR method.This paper indicates that either of the MIR and NIR spectral methods is reliable for the determination of the fat and protein contents.To compare mid-infrared （MIR） and near-infrared （NIR） spectroscopies for the determination of the fat and protein contents in milk, the same sample sets with varying concentrations of fat and protein were measured in the MIR range of 3 20（0700 cm^-1 and NIR range of 9 000-4 000 cm^-1. The spectral features in the two regions were analyzed. The MIR spectra of milk were characteristic due to the MIR inherent molecular specificity, whereas the NIR spectra were relatively characterless due to the NIR low selectivity. Partial least squares （PLS） regression models for fat and protein were developed by using both MIR and NIR spectra. MIR data with no pretreatment gave better results than NIR data. The square correlation coefficient （R2） and the root mean square error of prediction （RMSEP） were 0.98 and 0.10 g/dL for fat and 0.97 and 0.11 g/dL for protein. With NIR techniques, satisfactory results were not obtained with raw data. However, NIR data after pretreatment gave similarly good results to the ones using MIR method. This paper indicates that either of the MIR and NIR spectral methods is reliable for the determination of the fat and protein contents.

关 键 词：mid-infrared spectroscopy near-infrared spectroscopy MILK FAT PROTEIN 

分 类 号：R151[医药卫生—营养与食品卫生学]