New algorithm developed to improve transfer efficiency of near-infrared spectroscopic qualitative models

Recently, a research team from Hefei Institutes of Physical Science (HFIPS), Chinese Academy of Sciences (CAS) developed a new algorithm in the direction of near-infrared spectroscopy technology, which is used for improving the transfer efficiency of near-infrared qualitative analysis models between instruments.

The related results were published online in Infrared Physics & Technology.

Near-infrared spectroscopy (NIRS) is a rapid and non-destructive detection technology. The calibration models are the key to NIRS analysis, and the accuracy of the models transfer between instruments determines the effectiveness of the popularization and application of this technology. In order to ensure that the predictive performance of the models is not affected when they are transferred between instruments, new calibration algorithms and techniques need to be continuously developed. In previous studies, researchers mainly focused on the transfer of near-infrared quantitative models, while there were few reports on the transfer of qualitative models.

To solve this problem, the team comparatively studied various transfer algorithms with the near-infrared identification of unsound kernels in wheat and maize kernels as examples, aiming to optimize the performance of near-infrared qualitative models during the transfer of different instruments, and to improve the robustness of NIRS prediction.

The research team proposed a wavelength selection method based on correlation analysis (CAWS) in previous study to improve the transfer efficiency of near-infrared quantitative models by screening stable and consistent wavebands between instruments.

This time, researchers further improved the CAWS algorithm to make it equally applicable to the qualitative discrimination models.

The results show that the validation Matthews correlation coefficients of the wheat and corn discriminant models optimized by CAWS are 0.718 and 1 respectively, ranking second and first in various algorithm processing conditions, which verifies the effectiveness of the proposed method.

This study proposes an algorithm to improve the transfer efficiency of near-infrared qualitative models between instruments, which is beneficial to the further popularization and application of near-infrared spectroscopy.