.png){kind=icon}
.png){kind=icon}
Return
GAN-driven NIR-to-Raman spectral generation and multispectral fusion for geographical origin traceability of goji berry
.png){kind=icon}
PRE
AI
Z
M
S
R
H
Z
J
Y
P
DOI：10.1016/j.measurement.2026.122815.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• GAN-MSNet converts low-cost NIR spectra into Raman-like fingerprints. • Spectral peak GAN preserves key Raman features with R2 = 0.9348. • Attention-gated fusion captures complementary NIR and Raman information. • The model achieves 98.47 % accuracy for five-origin goji berry authentication. • External yam validation confirms transferable food origin traceability.
Keywords:
Geographical origin traceability
Cross-modal spectral generation
NIR-Raman Spectral fusion
Multispectral learning
Journal
IF:
5.6
Papers:
1.9W
Citations:
5.4W
Organization
Cited Papers