EUVIMEDEUVIMED entdecken
Crossref

Deep learning-assisted Raman spectroscopic quantification of total terpenes in Curcuma kwangsiensis

Zhiyong Zhang, Yan Liang, Xiaoli Qin, Xuefei Jiao, Zhangning Lu, Zhongnan Su, Mengna Yang, Chunmeng Li, Xinyuan Wu, Qi Zeng, Bo Li

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-07 · 355 · 127668

DOI: 10.1016/j.saa.2026.127668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-07. Verfasst von Zhiyong Zhang und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Pharmacy, Guilin Medical University, Guilin 541199, China. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Curcuma, Terpenes, Deep Learning. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Guilin Medical University, Guangxi Natural Science Foundation, National College Students Innovation and Entrepreneurship Training Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A rapid and efficient strategy was developed to quantify the total terpene content of Curcuma kwangsiensis by combining Raman spectroscopy with a Residual-Squeeze-and-Excitation one-dimensional convolutional neural network (Res-SE 1D-CNN). A dataset of 1400 spectra obtained from 26 batches across 6 production areas in Guangxi was constructed. Major terpenoids were determined by HPLC, and UV-based total terpene content served as the reference. Density functional theory calculations were performed to verify the theoretical Raman peaks of Germacrone and support spectral band assignments. Compared with Partial Least Squares Regression, Support Vector Machine, and Backpropagation Neural Network models, the proposed Res-SE 1D-CNN achieved superior predictive accuracy (R2 = 0.998, RMSE = 0.360). This study establishes a robust quantitative tool for evaluating complex traditional Chinese medicine systems and provides practical support for geographical traceability and rapid on-site quality control, with potential for extension to multi-marker natural product analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spectrum Analysis, RamanCurcumaTerpenesDeep LearningLeast-Squares AnalysisConvolutional Neural Networks

Stichwörter der Autor:innen

Curcuma kwangsiensisDFTRaman spectroscopyRapid quantificationRes-SE 1D-CNNTotal terpenes

Substanzen

Terpenes

Autor:innen und Institutionen

  • School of Pharmacy, Guilin Medical University, Guilin 541199, China.
  • Center for Biomedical-phonetics and Molecular Imaging, Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Institutions in Shaanxi Province, School of Life Science and Technology, Xid…
  • School of Pharmacy, Guilin Medical University, Guilin 541199, China. Electronic address: glzylibo@163.com.

Förderung

  • Guilin Medical University
  • Guangxi Natural Science Foundation
  • National College Students Innovation and Entrepreneurship Training Program

Zitieren

APA

Zhang, Z., Liang, Y., Qin, X., Jiao, X., Lu, Z., Su, Z., Yang, M., Li, C., Wu, X., Zeng, Q., & Li, B. (2026). Deep learning-assisted Raman spectroscopic quantification of total terpenes in Curcuma kwangsiensis. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 355, 127668. https://doi.org/10.1016/j.saa.2026.127668

Vancouver

Zhang Z, Liang Y, Qin X, Jiao X, Lu Z, Su Z, et al. Deep learning-assisted Raman spectroscopic quantification of total terpenes in Curcuma kwangsiensis. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;355:127668. doi:10.1016/j.saa.2026.127668

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhiyong and Liang, Yan and Qin, Xiaoli and Jiao, Xuefei and Lu, Zhangning and Su, Zhongnan and Yang, Mengna and Li, Chunmeng and Wu, Xinyuan and Zeng, Qi and Li, Bo},
  title = {Deep learning-assisted Raman spectroscopic quantification of total terpenes in Curcuma kwangsiensis},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {355},
  pages = {127668},
  doi = {10.1016/j.saa.2026.127668}
}
Kostenlos starten →