.png){kind=icon}
.png){kind=icon}
Return
A deep learning-based generative model for NIR spectral data augmentation and herbal medicine-food homologous classification
.png){kind=icon}
PRE
AI
Y
H
F
Y
Z
D
L
P
DOI：10.1016/j.infrared.2025.106341.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• DDIM-NIR generates high-fidelity NIR spectra for MFH herb identification. • Labeled spectral data from 48 MFH herb species are effectively augmented. • DDIM-NIR outperforms GAN and WGAN-GP in spectral similarity and quality. • 1D-CNN achieves 98.82% accuracy using DDIM-NIR-augmented spectral data. • This work enables robust, small-sample NIR analysis for quality traceability.
Journal
I
IF:
3.4
Papers:
5.8K
Citations:
1.2W
Organization
Cited Papers