EUVIMEDEUVIMED entdecken
Crossref

Classification of Gallic Acid Based on Raman Spectroscopy and Deep Learning

Yujia Ren, Ruijun Chen, Wei Zhang, Yan Liu, Yan Liu, Jie Tang, Mingtao Wu, Xiaoyi Lv, Chen Chen

Advances in Engineering Technology Research · 20.03.2026 · 16 (1) · 134

DOI: 10.56028/aetr.16.1.134.2026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Engineering Technology Research, online erschienen am 20.03.2026. Verfasst von Yujia Ren und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Against the backdrop of rapid global technological advancement, artificial intelligence has opened new avenues for modern research and application of gallic acid—a bioactive molecule extracted from natural products like gallnuts. Despite its long history of medicinal use, gallic acid still faces significant challenges in quality control and mechanism-of-action studies. Issues such as herbal adulteration and “homonyms” severely hinder its standardization process. Traditional identification methods, such as manual sensory evaluation and microscopic observation, are not only inefficient but also highly subjective, failing to meet the demands of modern quality control systems. Raman spectroscopy, with its advantages of rapid, accurate, and non-destructive detection, offers a viable technical solution to these challenges. This study developed a gradient boosting-based ensemble learning model (GEA model) using Raman spectral data from 12 medicinal components, including gallic acid, and their mixtures. This model integrates the strengths of Gradient Boosting, Extra Trees, and AdaBoost algorithms by weighting the prediction probabilities of each base learner to make the final decision. Experimental results demonstrate the GEA model's superior performance across multiple metrics: accuracy of 90.91%, precision of 92.2%, recall of 90.91%, F1 score of 89.56%, and an AUC value of 91.39%. Following parameter optimization, the model effectively handles high-dimensional, imbalanced spectral data, significantly enhancing classification performance and robustness. This provides an efficient, reliable AI-driven solution for quality control of gallic acid and related medicinal materials.

Zitieren

APA

Ren, Y., Chen, R., Zhang, W., Liu, Y., Liu, Y., Tang, J., Wu, M., Lv, X., & Chen, C. (2026). Classification of Gallic Acid Based on Raman Spectroscopy and Deep Learning. Advances in Engineering Technology Research, 16(1), 134. https://doi.org/10.56028/aetr.16.1.134.2026

Vancouver

Ren Y, Chen R, Zhang W, Liu Y, Liu Y, Tang J, et al. Classification of Gallic Acid Based on Raman Spectroscopy and Deep Learning. Advances in Engineering Technology Research. 2026;16(1):134. doi:10.56028/aetr.16.1.134.2026

BibTeX
@article{Ren2026,
  author = {Ren, Yujia and Chen, Ruijun and Zhang, Wei and Liu, Yan and Liu, Yan and Tang, Jie and Wu, Mingtao and Lv, Xiaoyi and Chen, Chen},
  title = {Classification of Gallic Acid Based on Raman Spectroscopy and Deep Learning},
  journal = {Advances in Engineering Technology Research},
  year = {2026},
  volume = {16},
  number = {1},
  pages = {134},
  doi = {10.56028/aetr.16.1.134.2026}
}
Kostenlos starten →