A nonlinear calibration transfer method based on joint kernel subspace

2021 ◽  
Vol 210 ◽  
pp. 104247
Author(s):  
Peng Shan ◽  
Yuhui Zhao ◽  
Qiaoyun Wang ◽  
Shuyu Wang ◽  
Yao Ying ◽  
...  
2019 ◽  
Vol 11 (35) ◽  
pp. 4481-4493 ◽  
Author(s):  
Congming Zou ◽  
Huimin Zhu ◽  
Junru Shen ◽  
Yue He ◽  
Jiaen Su ◽  
...  

A standard-free calibration transfer method has been developed for NIR spectroscopy based on variable penalty dynamic time warping.


NIR news ◽  
2018 ◽  
Vol 29 (8) ◽  
pp. 24-27 ◽  
Author(s):  
Jin Zhang ◽  
Xiaoyu Cui ◽  
Wensheng Cai ◽  
Xueguang Shao

Calibration transfer without standard samples is essential for practical applications of near infrared spectroscopy because, sometimes, it is difficult or even impossible to obtain the standard samples for measuring their spectra on the secondary instrument. In this work, a modified linear model correction method is proposed for improving the transfer accuracy and computational efficiency. The constraint of linear model correction was replaced by a robust convex equation to restrict the model similarity in the optimization. The near infrared dataset of pharmaceutical tablet measured with different instruments are used to test the performance of the method. The result shows that a modified linear model correction achieves a high efficiency of the transfer while the computational complexity can be considerably reduced. The method may provide a robust way in practical application.


Sign in / Sign up

Export Citation Format

Share Document