Rapid Evaluation of Wet Gluten Content in Wheat Using Hyperspectral Technology Combined with Machine Learning Algorithms
Yan Lai, Yan-Yan Li, Min Sha, Peng Li, Zheng-Yong Zhang · 2025
Read Rapid Evaluation of Wet Gluten Content in Wheat Using Hyperspectral Technology Combined with Machine Learning Algorithms by Yan Lai, Yan-Yan Li, Min Sha, Peng Li, Zheng-Yong Zhang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12785360.txt.
Description
Yan Lai and four co-authors build a fast test for the gluten content of wheat, in a 2025 study. Wet gluten share is a key quality grade for wheat, but the standard lab test is slow. The team used hyperspectral imaging, which records how grain and flour reflect many wavelengths of light, paired with machine learning. Several algorithms were trained and tuned to predict gluten levels from the spectra.
A random forest model performed best in two setups: on visible light spectra alone, and on fused visible plus near-infrared data. Near-infrared data alone did worse. Extra steps, such as taking derivatives of the spectra and smoothing them, sharpened the results further. A light-based test could let mills grade wheat in seconds instead of hours.
Catalog record
| CREATOR | Yan Lai, Yan-Yan Li, Min Sha, Peng Li, Zheng-Yong Zhang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |