Zuo Zhi-Tian, Wang Yuan-Zhong, Yao Zeng-Yu
Forestry College, Southwest Forestry University, Kunming 650224, China.
Medicinal Plants Research Institute, Yunnan Academy of Agricultural Sciences, Kunming 650200, China.
ACS Omega. 2025 Feb 11;10(7):7242-7255. doi: 10.1021/acsomega.4c10816. eCollection 2025 Feb 25.
() is a traditional medicinal plant with high medicinal and economic values. The authenticity of often determines its quality, and the quality of geographical indication (GI)-producing areas is usually superior to that of other producing areas, which are exploited by unscrupulous traders and affect the market order. The aim of this study was to characterize and identify the geographic origin of using Fourier transform near-infrared (FT-NIR) spectroscopy, with rapid detection combined with multivariate analysis. The use of principal component analysis and correlation spectral analysis enabled the initial differential characterization and identification of from different production areas. Then, random forest (RF) and support vector machine (SVM) models were established, and the results show that the results showed that the second-order derivative preprocessing and successive projection algorithm feature extraction achieved 100% classification correctness and the model training time is the shortest. Further constructing the image recognition model, synchronous two-dimensional correlation spectroscopy (2DCOS) image combined with residual convolutional neural network achieved accurate classification (accuracy of 100%) and did not require complex preprocessing and artificial feature extraction process, to maximize the avoidance of errors caused by human factors. The recognition results of the externally validated set showed that the image recognition method has a strong generalization ability and has a high potential for application in the identification of production areas.
（）是一种具有很高药用和经济价值的传统药用植物。（）的真伪往往决定其质量，地理标志（GI）产区的质量通常优于其他产区，而其他产区正被无良商人利用，影响市场秩序。本研究的目的是利用傅里叶变换近红外（FT-NIR）光谱对（）的地理来源进行表征和识别，将快速检测与多变量分析相结合。主成分分析和相关光谱分析的使用能够对来自不同产区的（）进行初步的差异表征和识别。然后，建立了随机森林（RF）和支持向量机（SVM）模型，结果表明，二阶导数预处理和连续投影算法特征提取实现了100%的分类正确率，且模型训练时间最短。进一步构建图像识别模型，同步二维相关光谱（2DCOS）图像与残差卷积神经网络实现了准确分类（准确率达100%），且无需复杂的预处理和人工特征提取过程，最大限度地避免了人为因素造成的误差。外部验证集的识别结果表明，该图像识别方法具有很强的泛化能力，在（）产区识别中具有很高的应用潜力。
