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