Interpretable Spectral Evidence Learning from Vis/NIR Imaging for Non-Destructive Authentication of Herbal Medicines
Molecules · 2026
DOI: 10.3390/molecules31142444 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, 2026. Verfasst von Zhihui Fan und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China. Hauptthemen laut MEDLINE: Herbal Medicine, Drugs, Chinese Herbal, Plants, Medicinal. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Rapid and non-destructive authentication of herbal medicines is important for quality control and market supervision. This study established an interpretable spectral evidence learning framework for visible and near-infrared (Vis/NIR) imaging-based authentication of Codonopsis Radix (CR) and Aurantii Fructus (AF). Compact 31-band mean gray-value spectra were analyzed at ROI and sample levels. CR sample-level spectra were obtained by ROI-group averaging, whereas AF records were retained as individual sample spectra with image-group information used for leakage-controlled validation. Raw spectra, Savitzky–Golay smoothing, multiplicative scatter correction, and standard normal variate correction were compared with machine-learning and deep-learning classifiers. A fold-contained lightweight diffusion (LD) module was further introduced to provide class-conditioned spectral augmentation and denoising-error evidence. Under grouped cross-validation, the strongest non-LD Linear SVM models achieved accuracy/macro-F1 values of 0.9231/0.9238 for CR and 0.9025/0.9018 for AF. After LD augmentation, the best LD-augmented SVM models reached macro-F1 values of 0.9427 and 0.9197, respectively. Across all evaluated model–dataset combinations, LD increased the overall mean macro-F1 from 0.7302 to 0.8189. Model-aligned wavelength evidence and top-wavelength subset tests further showed that selected LED-band subsets retained useful discriminative information within the present imaging configuration. These results support the feasibility of compact Vis/NIR image-based authentication of herbal materials under grouped validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China.
- College of Electronics and Information Engineering, South China University of Technology, Guangzhou 510641, China.
ORCID-Profile: Zhihui Fan
Zitieren
APA
Fan, Z., Ma, C., Jing, S., Huang, J., & Zhang, M. (2026). Interpretable Spectral Evidence Learning from Vis/NIR Imaging for Non-Destructive Authentication of Herbal Medicines. Molecules. https://doi.org/10.3390/molecules31142444
Vancouver
Fan Z, Ma C, Jing S, Huang J, Zhang M. Interpretable Spectral Evidence Learning from Vis/NIR Imaging for Non-Destructive Authentication of Herbal Medicines. Molecules. 2026. doi:10.3390/molecules31142444
BibTeX
@article{Fan2026,
author = {Fan, Zhihui and Ma, Chao and Jing, Shaowen and Huang, Jiayu and Zhang, Mingkun},
title = {Interpretable Spectral Evidence Learning from Vis/NIR Imaging for Non-Destructive Authentication of Herbal Medicines},
journal = {Molecules},
year = {2026},
doi = {10.3390/molecules31142444}
}
EUVIMED