Potential of hyperspectral imaging for nondestructive determination of chlorogenic acid content in Flos Lonicerae
Potential of hyperspectral imaging for nondestructive determination of chlorogenic acid content in Flos Lonicerae
复制标题
DOI：
10.1007/s11694-019-00180-x
复制
发表时间：
2019-12-01
影响因子：
3.4
通讯作者：
Yu，Huichun
中科院分区：
文献类型：
--
作者：
Wang，Qingqing;Liu，Yunhong;Yu，Huichun
绿原酸（Chlorogenic acid， CGA）作为一种主要活性成分，是评价龙葵药材质量的重要指标。采用高光谱成像（HSI）技术对龙葵中CGA含量进行了无损检测。为了获得校准模型的最佳性能，对基于偏最小二乘回归（PLSR）模型的9种不同预处理方法进行了研究和比较。确定最佳方法为标准正态变量（SNV）法，其thrp2值为0.9766，RMSEP值为2.711。为了简化标定模型，采用无信息变量消除（UVE）、逐次投影算法（SPA）、竞争自适应重加权采样（CARS）、UVE - CARS、UVE - SPA、CARS - SPA和UVE - CARS - SPA等不同的变量选择方法提取全光谱特征波长。然后分别基于全光谱和选择的特征波长建立PLSR和最小二乘支持向量机（LS-SVM）。结果表明，非线性UVE-CARS-LS-SVM模型（RP2= 0.9785, RMSEP = 2.496）是预测龙花中CGA含量的最佳模型。因此，本研究表明，HSI与SNV预处理方法、UVE-CARS变量选择方法和LS-SVM建模相结合，对无害化、快速测定金银花贮藏过程中CGA含量具有很大的潜力。
Chlorogenic acid (CGA), as a major active component, is an important index for evaluating the quality ofFlosLonicerae. Hyperspectral imaging (HSI) technology was applied for nondestructive estimating CGA content inFlosLonicerae. In order to obtain the best performance of calibration models, nine different pretreatment methods were investigated and compared based on partial least squares regression (PLSR) models. The optimal method was determined as a standard normal variable (SNV) method withRP2of 0.9766 and RMSEP of 2.711 for further analysis. To simplify calibration models, different variables selection methods, including the uninformative variable elimination (UVE), successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), UVE–CARS, UVE–SPA, CARS–SPA, and UVE–CARS–SPA, were used to extracted characteristic wavelengths from the full spectrum. And then PLSR and least squares support vector machine (LS-SVM) were established based on full spectrum and the selected characteristic wavelengths, respectively. The results showed that the nonlinear UVE–CARS–LS–SVM model (RP2= 0.9785 and RMSEP = 2.496) was the optimal model for predicting CGA content inFlosLonicerae. Therefore, this study revealed that the combination of HSI with SNV preprocessing method, UVE–CARS variable selection method and LS-SVM modeling had great potential to nondestructively and rapidly determine CGA content inFlos Loniceraeduring storage.