1. Rapid determination of rice protein content using near-infrared spectroscopy coupled with feature wavelength selection.
- Author
-
Liu, Jinming, Luo, Xin, Zhang, Dongjie, Wang, Chunqi, Chen, Zhengguang, and Zhao, Xiaoyu
- Subjects
- *
RICE quality , *PARTICLE swarm optimization , *NEAR infrared spectroscopy , *SIMULATED annealing , *STANDARD deviations , *RICE - Abstract
• Rapid determination of rice protein content was completed using NIR spectroscopy. • BiPLS-GSA and BiPLS-SABPSO was proposed to select feature wavelengths of protein. • BiPLS-SABPSO was superior to BiPLS-GSA in feature wavelengths selection. • Detection accuracy of regression model was efficiently improved using BiPLS-SABPSO. Protein content is a key indicator for rice nutritional value, and its accurate determination has become a necessary tool for rice quality evaluation and breeding. To solve the shortcomings of slow and costly testing by traditional methods, a rapid detection model of rice protein content was constructed based on near-infrared spectroscopy coupled with feature wavelength selection. The backward interval partial least squares (BiPLS) was combined with the genetic simulated annealing algorithm (GSA) and the simulated annealing binary particle swarm optimization algorithm (SABPSO), respectively, to construct BiPLS-GSA and BiPLS-SABPSO for selecting protein feature wavelengths, thereby establishing a corresponding partial least squares quantitative calibration model. Among them, the regression model established using feature wavelengths selected by BiPLS-SABPSO had the best performance. The determination coefficient of the model for the validation set and the independent test set were 0.949 and 0.956, the root mean square error were 0.174% and 0.214%, the relative root mean square error were 2.621% and 3.118%, and the residual predictive deviation being 4.235 and 4.500, respectively, which could meet the requirement for rapid and accurate determination of rice protein content. The combination of BiPLS-SABPSO and near-infrared spectroscopy has developed into a new method to achieve fast and reliable determination of rice protein content, providing an alternative strategy for rapid qualitative detection of related agricultural products. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF