Prediction of nutritional quality characteristics of faba bean based on deep learning method
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-12 · 362 · 128164
DOI: 10.1016/j.saa.2026.128164 ↗Kurz gefasst
Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-12. Verfasst von Bin Dang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory for Research and Utilization of Qinghai Tibet Plateau Germplasm Resources, College of Agricultural and Forestry Sciences, Qinghai Universi…. Hauptthemen laut MEDLINE: Vicia faba, Nutritive Value, Deep Learning. Die Arbeit nennt 29 Literaturangaben.
Abstract (Originalsprache)
This study established an integrated analytical method based on near-infrared spectroscopy (NIRS) for the rapid, non-destructive, and quantitative detection of four major nutritional components in faba beans: starch, protein, moisture, and dietary fiber. By systematically comparing individual and combined spectral preprocessing strategies, optimal preprocessing combinations for each component were identified. Seven feature wavelength selection algorithms, including Competitive Adaptive Reweighted Sampling (CARS), were employed to extract key spectral variables. Predictive models were subsequently developed using four modeling approaches: Partial Least Squares (PLS), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The results demonstrated that combined preprocessing methods significantly outperformed single techniques. The CARS algorithm exhibited the most robust performance in feature extraction, and the MLP model consistently surpassed traditional machine learning methods in predicting all components. The optimal modeling pipelines for each component were ultimately determined as follows: starch (MLP + CARS + MSC + SG + MSS, R2 = 0.92), protein (MLP + CARS + SD + SNV + MSC + MSS, R2 = 0.94), moisture (MLP + SPA + SG + SNV, R2 = 0.9973), and dietary fiber (MLP + PCA + FD + SNV, R2 = 0.9999). This study verifies the effectiveness of combining NIRS with deep learning for the simultaneous detection of multiple components in faba beans and provides a reliable methodological framework for the non-destructive quality assessment of agricultural products.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Laboratory for Research and Utilization of Qinghai Tibet Plateau Germplasm Resources, College of Agricultural and Forestry Sciences, Qinghai University, Qinghai, China.
- College of Food Science and Engineering, Northwest A&F University, Yangling 712100, PR China.
- College of Food Science and Engineering, Northwest A&F University, Yangling 712100, PR China. Electronic address: hanlin730@163.com.
Zitieren
APA
Dang, B., Jin, X., Zhang, J., Wu, H., Wang, M., & Han, L. (2026). Prediction of nutritional quality characteristics of faba bean based on deep learning method. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 362, 128164. https://doi.org/10.1016/j.saa.2026.128164
Vancouver
Dang B, Jin X, Zhang J, Wu H, Wang M, Han L. Prediction of nutritional quality characteristics of faba bean based on deep learning method. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;362:128164. doi:10.1016/j.saa.2026.128164
BibTeX
@article{Dang2026,
author = {Dang, Bin and Jin, Xiying and Zhang, Jie and Wu, Haiyu and Wang, Min and Han, Lin},
title = {Prediction of nutritional quality characteristics of faba bean based on deep learning method},
journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
year = {2026},
volume = {362},
pages = {128164},
doi = {10.1016/j.saa.2026.128164}
}
EUVIMED