Rapid Determination of Soybean Protein Content by Near-Infrared Spectroscopy Coupled with Multi-Learner Ensemble Wavelength Selection
Weida Wang, Chunqi Wang, Baocheng Zhao, Jiayi Shi, Changan Xu, Jinming Liu · 2026
Read Rapid Determination of Soybean Protein Content by Near-Infrared Spectroscopy Coupled with Multi-Learner Ensemble Wavelength Selection by Weida Wang, Chunqi Wang, Baocheng Zhao, Jiayi Shi, Changan Xu, Jinming Liu (2026) 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-13206442.txt.
Description
Weida Wang and co-authors read soybean protein content from near-infrared light in seconds. Lab chemistry is exact but slow and pricey. Their 2026 method first picks the wavelengths that carry the protein signal. An ensemble of simple learners scores each wavelength's worth. Rival pickers are raced against it. A partial least squares model then turns the picked bands into a protein number.
Just 29 wavelengths did the job. Test accuracy stayed high, with errors near half a percent of protein. A SHAP analysis shows the picked bands sit where protein bonds sing. Fewer bands mean cheaper sensors for graders and breeders. The team pitches the method for fast seed lot checks.
Catalog record
| CREATOR | Weida Wang, Chunqi Wang, Baocheng Zhao, Jiayi Shi, Changan Xu, Jinming Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |