EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Multimodal deep learning with hyperspectral imaging for accurate origin classification of wolfberries

Bo Li, Rui Xia, Juanli Li, Jing Zhang, Zhixing Zhang, Jun Chen, Yu Chen

Food Chemistry: X · 2025-10 · 31 · 103166

DOI: 10.1016/j.fochx.2025.103166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Food Chemistry: X, 2025-10. Verfasst von Bo Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Shanxi Provincial Key Research and Development Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate classification of wolfberry geographical origin is essential for assessing its nutritional and medicinal properties. A multimodal convolutional neural network (MTCNN) with a cross-attention mechanism was proposed to effectively fuse spectral and image features, achieving a test accuracy of 99.88 %. Traditional feature extraction methods such as and principal component analysis (PCA) were combined with support vector machine (SVM) and k-nearest neighbor (KNN) classifiers. The SVM model using gradient boosting decision tree (GBDT) -extracted spectral features and fused image data achieved the highest accuracy of 96.68 %. The comparison results highlight the superior performance of multimodal deep learning over conventional methods, demonstrating its potential for robust agricultural product traceability, authentication, and quality assurance. Beyond achieving higher accuracy, our model improves upon previous architectures by reducing computational complexity through the use of a simplified attention mechanism and enhancing interpretability, making the model more efficient and accessible for practical applications.

Schlagwörter

Stichwörter der Autor:innen

Deep learningGeographical origin recognitionHyperspectral imagingWolfberries

Autor:innen und Institutionen

  • College of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, China.
  • College of Innovation and Entrepreneurship (Engineering Training Center), Taiyuan University of Technology, Taiyuan 030024, China.
  • Shanxi Tangdi Technology Co., Ltd, Taiyuan 030032, China.
  • College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, China.

Förderung

  • Shanxi Provincial Key Research and Development Project

Zitieren

APA

Li, B., Xia, R., Li, J., Zhang, J., Zhang, Z., Chen, J., & Chen, Y. (2025). Multimodal deep learning with hyperspectral imaging for accurate origin classification of wolfberries. Food Chemistry: X, 31, 103166. https://doi.org/10.1016/j.fochx.2025.103166

Vancouver

Li B, Xia R, Li J, Zhang J, Zhang Z, Chen J, et al. Multimodal deep learning with hyperspectral imaging for accurate origin classification of wolfberries. Food Chemistry: X. 2025;31:103166. doi:10.1016/j.fochx.2025.103166

BibTeX
@article{Li2025,
  author = {Li, Bo and Xia, Rui and Li, Juanli and Zhang, Jing and Zhang, Zhixing and Chen, Jun and Chen, Yu},
  title = {Multimodal deep learning with hyperspectral imaging for accurate origin classification of wolfberries},
  journal = {Food Chemistry: X},
  year = {2025},
  volume = {31},
  pages = {103166},
  doi = {10.1016/j.fochx.2025.103166}
}
Kostenlos starten →