Fast Measurement of Protein and Fat Content in Milk Powder Based on Infrared Spectroscopy Technique and LS-SVM
Protein and fat are two important components of milk powder. The fast and non-destructive detection of protein and fat content in milk powder is important. Infrared spectroscopy technique was applied to achieve this purpose. Least-squares support vector machines (LS-SVM) was applied to building the prediction model based on infrared spectral transmission rate. Based on LS-SVM, when it is to protein content, the determination coefficient for prediction (Rp2) was 0.9517 and root mean square error for prediction (RMSEP) was 0.520201. While it is to fat, Rp2 was 0.9796, and RMSEP was 0.836708. It is concluded that infrared spectroscopy technique can do the quantification of protein and fat content. The process is simple and easy to operate, and the performance of LS-SVM is better than that of back propagation artificial neural networks (BP-NN). Based on this study, a simple and non-destructive spectra sensor can be designed for the quantification of protein and fat content in milk powder.
infrared spectroscopy SVM fat protein
Di Wu Shuijuan Feng Yong He
国际会议
The International Conference Information Computing and Automation(2007国际信息计算与自动化会议)
成都
英文
404-407
2007-12-19（万方平台首次上网日期，不代表论文的发表时间）