Beyond Conventional Methods: Rapid and Precise Quantification of Polyphenols in Vigna umbellata via Hyperspectral Imaging Enhanced by Multi-Scale Residual CNN
Sensors · 11.04.2026 · 26 (8) · 2356
DOI: 10.3390/s26082356 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 11.04.2026. Verfasst von Hao Liang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China. Hauptthemen laut MEDLINE: Polyphenols, Hyperspectral Imaging, Vigna. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Cooperative Forestry Science and Technology Project, Postdoctoral Research Program of Zhejiang Province, Natural Science Foundation of Zhejiang Province.
Abstract (Originalsprache)
Vigna umbellate, a typical edible and medicinal crop, is rich in polyphenolic compounds with antioxidant, antibacterial, anti-inflammatory, and lipid-regulating activities. However, traditional methods for polyphenol content detection rely on chemical analysis, which is cumbersome and time-consuming, making it difficult to meet the demands of high-throughput rapid detection. Although hyperspectral imaging technology offers the potential for non-destructive and rapid detection, existing analytical methods are often limited by issues such as high spectral band redundancy, insufficient feature extraction, and inadequate model stability, which constrain prediction accuracy and practical application potential. To address this, this study proposes a multi-scale residual convolutional neural network (MS-RCNN) based on competitive adaptive reweighted sampling (CARS) for feature band selection, combined with near-infrared hyperspectral imaging technology, to construct a rapid and non-destructive prediction model for the polyphenol content of Vigna umbellata. The model employs a parallel multi-scale convolutional module to extract spectral features with different receptive fields, and incorporates residual connections and adaptive pooling mechanisms to enhance feature reuse and robustness. Experiments compared the performance of partial least squares regression (PLSR), least squares support vector machine (LS-SVM), multi-scale convolutional neural network (MS-CNN), and MS-RCNN models. The results indicate that the MS-RCNN model based on CARS screening achieved the best prediction performance, with a coefficient of determination (R2) of 0.9467, a root mean square error of prediction (RMSEP) of 0.0448, and a residual predictive deviation (RPD) of 4.33. Compared with the optimal PLSR and LSSVM models, its R2 values were improved by 0.2078 and 0.1119, respectively. In summary, the MS-RCNN model proposed in this study enables rapid, non-destructive, and accurate prediction of polyphenol content in Vigna umbellata, providing an efficient technical approach for quality detection of edible and medicinal crops.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China.
- Institute of Modern Agriculture and Health Care Industry, Wencheng 325300, China.
- National Key Laboratory for Development and Utilization of Forest Food Resources, Zhejiang A&F University, Hangzhou 311300, China.
- Wenzhou Key Laboratory of AI Agents for Agriculture, Wenzhou Academy of Agricultural Sciences, Wenzhou 325006, China.
Förderung
- Zhejiang Provincial Cooperative Forestry Science and Technology Project
- Postdoctoral Research Program of Zhejiang Province
- Natural Science Foundation of Zhejiang Province
- Scientific Research Foundation of Zhejiang A&F University
Zitieren
APA
Liang, H., Yang, X., Wang, N., Lu, X., Zou, W., Zhou, A., Lou, X., & Lin, Y. (2026). Beyond Conventional Methods: Rapid and Precise Quantification of Polyphenols in Vigna umbellata via Hyperspectral Imaging Enhanced by Multi-Scale Residual CNN. Sensors, 26(8), 2356. https://doi.org/10.3390/s26082356
Vancouver
Liang H, Yang X, Wang N, Lu X, Zou W, Zhou A, et al. Beyond Conventional Methods: Rapid and Precise Quantification of Polyphenols in Vigna umbellata via Hyperspectral Imaging Enhanced by Multi-Scale Residual CNN. Sensors. 2026;26(8):2356. doi:10.3390/s26082356
BibTeX
@article{Liang2026,
author = {Liang, Hao and Yang, Xin and Wang, Nan and Lu, Xinyue and Zou, Wenwu and Zhou, Aicun and Lou, Xiongwei and Lin, Yufei},
title = {Beyond Conventional Methods: Rapid and Precise Quantification of Polyphenols in Vigna umbellata via Hyperspectral Imaging Enhanced by Multi-Scale Residual CNN},
journal = {Sensors},
year = {2026},
volume = {26},
number = {8},
pages = {2356},
doi = {10.3390/s26082356}
}
EUVIMED