Determination of gossypol content in cottonseeds by near infrared spectroscopy based on Monte Carlo uninformative variable elimination and nonlinear calibration methods

详细信息    查看全文

• 作者：Cheng Li ^{licheng20080921@zju.edu.cn} ; Tianlun Zhao ^{tlzhao@zju.edu.cn} ; Cong Li ^{lenilc@163.com} ; Lei Mei ^{meileihzr@163.com} ; En Yu ^{yuen@zju.edu.cn} ; Yating Dong ^{tingy36@sina.com} ; Jinhong Chen ^{jhchen@zju.edu.cn} ; Shuijin Zhu ; ^{shjzhu@zju.edu.cn}
• 关键词：Cottonseed ; Gossypol content ; Monte Carlo uninformative variable elimination (MC-UVE) ; Nonlinear calibration methods ; Near infrared (NIR)
• 刊名：Food Chemistry
• 出版年：2017
• 出版时间：15 April 2017
• 年：2017
• 卷：221
• 期：Complete
• 页码：990-996
• 全文大小：2457 K
• 卷排序：221

文摘

The NIR models were optimized by MC-UVE and nonlinear methods. The optimal model was obtained by the MC-UVE-WLS-SVM method. The optimal NIR model was good enough to replace the traditional methods. The combination of nonlinear methods and MC-UVE was a trend for NIR technology.