期刊
FOOD AND BIOPROCESS TECHNOLOGY
卷 5, 期 4, 页码 1402-1410出版社
SPRINGER
DOI: 10.1007/s11947-010-0492-4
关键词
Near infrared (NIR) spectroscopy; Mid-infrared (MIR) spectroscopy; Calcium; Powdered milk; Uninformation variable elimination (UVE); Successive projections algorithm (SPA)
资金
- Natural Science Foundation of China [31072247]
- Zhejiang Provincial Natural Science Foundation of China [Y3100205]
- Fundamental Research Funds for the Central Universities
- Open Foundation of Zhejiang Key Lab of Exploitation and Preservation of Coastal Bioresource [J2010001]
Near infrared (NIR) and mid-infrared (MIR) spectroscopy techniques were evaluated to determine calcium content in powdered milk. A hybrid spectral variable selection algorithm combined with uninformation variable elimination (UVE) and successive projections algorithm (SPA) selected 11 NIR and 15 MIR variables from full 2,756 NIR and 3,727 MIR variables, respectively. Predicted results of least-squares support vector machine models for the samples in the prediction set show that the 15 MIR variables obtained much better results (0.930 for coefficient of determination (r (2)), 3.703 for residual predictive deviation (RPD), 30.162 for root mean square error of prediction set (RMSEP) and 5.22% for relative errors of prediction (RSEP)) than 11 NIR variables did (0.636 for r (2), 1.587 for RPD, 78.815 for RMSEP, and 13.40% for RSEP). The overall results indicate that MIR spectroscopy could be applied as a precision and rapid method to determine calcium content in powdered milk. The good performance shows a potential application using UVE-SPA to select NIR and MIR effective variables.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据