Development and Interpretability Analysis of Near-Infrared Spectroscopy Models for Fat and Protein Prediction in Foxtail Millet [Setaria italica (L.) Beauv.]
Foods · 11.02.2026 · 15 (4) · 649
DOI: 10.3390/foods15040649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Foods, online erschienen am 11.02.2026. Verfasst von Anqi Gao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Shanxi Houji Laboratory, Taiyuan 030031, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Construction Project of the National Modern Agricultural Industry Technology System, the National Key Research and Development Program of China, the Construction Project of the Modern Agricultural Industrial Technology System in Shanxi Province.
Abstract (Originalsprache)
Foxtail millet is a nutritionally important cereal whose fat and protein content directly influence its nutritional quality and processing properties. To overcome the limitations of traditional detection methods, developing rapid, non-destructive, and interpretable models is essential. A total of 214 samples of the foxtail millet cultivar “Changnong No. 47” were used in this study. The Sparrow Search Algorithm was introduced to screen stable key wavelengths by statistically analyzing their selection frequency. Based on the selected wavelengths, quantitative models were constructed using Partial Least Squares Regression (PLS), Random Forest (RF), and Support Vector Machine. The SHapley Additive exPlanations method was employed to quantify the direction and magnitude of contributions of the key wavelengths within the model. Results show the selection of 13 key wavelengths for fat and 15 for protein. The RF model delivered the best prediction for fat content (RP2 = 0.797, RMSEP = 0.218%, RPDP = 2.219), while the PLS model performed best for protein content (RP2 = 0.695, RMSEP = 0.268%, RPDP = 1.811). The methodology established in this study can not only be applied to the rapid quality assessment of millet but also be extended to analyze the nutritional components of other grains.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shanxi Houji Laboratory, Taiyuan 030031, China.
- Millet Research Institute, Shanxi Agricultural University, Changzhi 046000, China.
- Key Laboratory of Minor Crop Germplasm Innovation and Molecular Breeding (Co-Construction by Ministry and Province), Ministry of Agriculture and Rural Affairs, Taiyuan 030801, China.
- Department of Mechanical Engineering, Shanxi Institute of Engineering Technology, Yangquan 045000, China.
- Department of Scientific Research Management, Shanxi Agricultural University, Taiyuan 030801, China.
ORCID-Profile: Guoliang Wang
Förderung
- the Construction Project of the National Modern Agricultural Industry Technology System
- the National Key Research and Development Program of China
- the Construction Project of the Modern Agricultural Industrial Technology System in Shanxi Province
- The key research and development project of Shanxi Province
- Shanxi Agricultural University Academic Revitalization Project
- Construction Project of the National Modern Agricultural Industry Technology System
- National Key Research and Development Program of China
- Construction Project of the Modern Agricultural Industrial Technology System in Shanxi Province
Zitieren
APA
Gao, A., Guo, E., Wang, B., Zhang, D., Cheng, K., Wang, X., Zhang, A., & Wang, G. (2026). Development and Interpretability Analysis of Near-Infrared Spectroscopy Models for Fat and Protein Prediction in Foxtail Millet [Setaria italica (L.) Beauv.]. Foods, 15(4), 649. https://doi.org/10.3390/foods15040649
Vancouver
Gao A, Guo E, Wang B, Zhang D, Cheng K, Wang X, et al. Development and Interpretability Analysis of Near-Infrared Spectroscopy Models for Fat and Protein Prediction in Foxtail Millet [Setaria italica (L.) Beauv.]. Foods. 2026;15(4):649. doi:10.3390/foods15040649
BibTeX
@article{Gao2026,
author = {Gao, Anqi and Guo, Erhu and Wang, Bin and Zhang, Dongxu and Cheng, Kai and Wang, Xiaofu and Zhang, Aiying and Wang, Guoliang},
title = {Development and Interpretability Analysis of Near-Infrared Spectroscopy Models for Fat and Protein Prediction in Foxtail Millet [Setaria italica (L.) Beauv.]},
journal = {Foods},
year = {2026},
volume = {15},
number = {4},
pages = {649},
doi = {10.3390/foods15040649}
}
EUVIMED