Rui Zhang
Research Subjects
Rui Zhang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Bin Luo
Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
3 shared publications Dayu Pan
2 shared publicationsHongyan Sun
2 shared publicationsLihua Liu
2 shared publicationsPingping Qu
2 shared publicationsGuoqing Feng
1 shared publication
Latest Publications
- Open Access
- 5 October 2026
- Published by Elsevier in Food Chemistry: X
- Vol. 39
Bilinear surface model-enhanced determination of gluten quality in whole wheat flour by NIR spectroscopy
- 5 October 2026
- Published by Elsevier in Food Chemistry: X
- Vol. 39
Open AccessBilinear surface model-enhanced determination of gluten quality in whole wheat flour by NIR spectroscopy
- Open Access
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
Non-destructive quantification of vitamin C in lettuce by NIR spectroscopy using an optimized machine learning approach
Rapid and non-destructive monitoring of Vitamin C (VC) content in lettuce across different growth stages is essential for intelligent precision harvesting and post-harvest quality management. This study aimed to develop a highly accurate and robust model for predicting VC content in lettuce using near-infrared (NIR) spectroscopy. Spectral data in the 1350-1800 nm range were collected from 326 lettuce samples at the critical stages-191 from the seedling stage and 135 from the maturity stage, along with their VC values determined by chemical methods. Stratified random sampling selected total 97 samples from seedling and maturity stages as an independent external validation set for generalization assessment. Normalization correction (NC) and direct orthogonal signal correction (DOSC) were applied for preprocessing to remove background and noise interference. Three effective wavelengths (EWs) algorithms and one spectral feature extraction algorithm were employed for model optimization comparison, with the deep belief network (DBN) method yielding the best results.Five regression models were constructed for comparison, the improved whale optimization algorithm-optimized least squares support vector machine (IWOA-LSSVM) model exhibited superior predictive performance. The results show that the optimal model yielded overall Rp2 of 0.9252, RMSE of 0.3712 and MAE of 0.2990 on the external set, while for seedling and maturity stages the metrics were 0.8800, 0.4608, and 0.4027 and 0.9500, 0.3341, and 0.2436, respectively. These results demonstrated that the VC content detection model of lettuce, founded on DBN-IWOA-LSSVM, provided a modelling foundation for internal quality detection of lettuce and other vegetables.
- 1 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessNon-destructive quantification of vitamin C in lettuce by NIR spectroscopy using an optimized machine learning approach
Rapid and non-destructive monitoring of Vitamin C (VC) content in lettuce across different growth stages is essential for intelligent precision harvesting and post-harvest quality management. This study aimed to develop a highly accurate and robust model for predicting VC content in lettuce using near-infrared (NIR) spectroscopy. Spectral data in the 1350-1800 nm range were collected from 326 lettuce samples at the critical stages-191 from the seedling stage and 135 from the maturity stage, along with their VC values determined by chemical methods. Stratified random sampling selected total 97 samples from seedling and maturity stages as an independent external validation set for generalization assessment. Normalization correction (NC) and direct orthogonal signal correction (DOSC) were applied for preprocessing to remove background and noise interference. Three effective wavelengths (EWs) algorithms and one spectral feature extraction algorithm were employed for model optimization comparison, with the deep belief network (DBN) method yielding the best results.Five regression models were constructed for comparison, the improved whale optimization algorithm-optimized least squares support vector machine (IWOA-LSSVM) model exhibited superior predictive performance. The results show that the optimal model yielded overall Rp2 of 0.9252, RMSE of 0.3712 and MAE of 0.2990 on the external set, while for seedling and maturity stages the metrics were 0.8800, 0.4608, and 0.4027 and 0.9500, 0.3341, and 0.2436, respectively. These results demonstrated that the VC content detection model of lettuce, founded on DBN-IWOA-LSSVM, provided a modelling foundation for internal quality detection of lettuce and other vegetables.
- Open Access
- 11 June 2026
- Published by Elsevier in SSRN Electronic Journal
Surface model-enhanced determination of gluten characteristics 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 cluster sampling (CGSCS) algorithm for partitioning multi-indicator small sample sets. Furthermore, a novel analytical framework combining a surface model with machine learning algorithms is presented to simultaneously detect gluten content and strength indicators. The results showed that the surface model 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 surface model constructed in this study, incorporating the core principles of machine learning algorithms, provides a novel approach for the quantitative and rapid simultaneous detection of gluten characteristics in whole wheat flour.- 11 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSurface model-enhanced determination of gluten characteristics 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 cluster sampling (CGSCS) algorithm for partitioning multi-indicator small sample sets. Furthermore, a novel analytical framework combining a surface model with machine learning algorithms is presented to simultaneously detect gluten content and strength indicators. The results showed that the surface model 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 surface model constructed in this study, incorporating the core principles of machine learning algorithms, provides a novel approach for the quantitative and rapid simultaneous detection of gluten characteristics in whole wheat flour.