Bilinear surface model-enhanced determination of gluten quality in whole wheat flour by NIR spectroscopy

Gluten content and strength are key indicators of whole wheat flour processing quality, and their rapid non-destructive detection is crucial for quality screening and wheat variety breeding. This paper proposed a covariance guided stratified sampling (CGSS) algorithm for partitioning multi-indicator small sample sets. Furthermore, a novel analytical framework combining a bilinear surface model with machine learning algorithms is presented to simultaneously detect gluten content and strength indicators. The results showed that the novel modeling approach combined with CARS-LASSO achieved optimal prediction, with test $R^2$ values of 0.98, 0.93, 0.89, 0.84, and 0.83 and RPD values of 6.73, 3.77, 3.08, 2.47, and 2.40 for WGS, GI, DGC, WGC, and WGC (14% MB), respectively. The proposed model, incorporating machine learning algorithms, provides a novel approach for the quantitative and rapid simultaneous detection of gluten properties in whole wheat flour.