您好,欢迎访问云南省农业科学院 机构知识库!

Geographical origin identification of Dendrobium Officinale based on FT-NIR and ATR-FTIR spectroscopy

文献类型: 外文期刊

作者: Han, Jiaqi 1 ; Hu, Qiang 1 ; Wang, Yuanzhong 1 ;

作者机构: 1.Yunnan Acad Agr Sci, Med Plants Res Inst, Kunming 650200, Peoples R China

关键词: Spectral analysis; Data fusion; Two-dimensional correlation spectroscopy; The residual convolutional neural network; Dendrobium officinale Kimura & Migo

期刊名称:FOOD BIOSCIENCE ( 影响因子:5.9; 五年影响因子:6.1 )

ISSN: 2212-4292

年卷期: 2025 年 63 卷

页码:

收录情况: SCI

摘要: Dendrobium officinale Kimura & Migo (D. officinale) is a valuable medicinal and food plant, and accurate certification of its origin is a prerequisite to protect consumer interests and maintain the market. In order to realize the fast and effective authentication of D. officinale origin, a discrimination model based on attenuated total reflection-Fourier transform infrared (ATR-FTIR) and Fourier transform near-infrared (FT-NIR) was constructed and combined with individual spectra and data fusion strategies. The results showed that the PLS-DA and SVM models built by the fusion of FT-NIR and ATR-FTIR data processed in second-order derivatives all reach 100% in terms of test set and accuracy, respectively. The residual convolutional neural network (ResNet) model based on Two-dimensional correlation spectroscopy(2DCOS) constructed using FT-NIR spectra and spectral fusion of raw data achieves 100% accuracy on the training set, test set, and external test set. Due to the generalization ability of the ResNet model and the simplicity and efficiency of the subsequent validation, it is a powerful, non-destructive, fast, and feasible preferred tool for D. officinale geographic origin classification and brand protection. This work is expected to be a potential methodology for origin identification analysis and quality monitoring in the food and pharmaceutical industries.

  • 相关文献
作者其他论文 更多>>