太赫兹时域光谱结合主成分分析线性判别和支持向量机用于大黄样品鉴定（英文）

发布时间：2018-07-31 12:41

【摘要】：太赫兹时域光谱技术(THz-TDS)结合主成分分析-线性判别分析(PCA-LDA)和支持向量机(SVM)用于正品大黄样品的鉴定。在时域测量41个大黄样品的太赫兹时域透射光谱,然后将这些时域信号转换成频域的吸收系数系数。根据样本的吸收系数建立了主成分分析-线性判别分析和支持向量机的定性分类模型,并对正品和非正品大黄样本的分类模型进行了交叉验证。模型的预测能力和稳定性使用自助拉丁配分进行评价,使用50次自助拉丁配分,配分数为4。使用主成分分析-线性判别分析和支持向量机均得到了满意的结果。提出的方法证明是一种方便、无污染、准确和无需化学处理的鉴定大黄样本的方法。该文提出的步骤可以应用于其他中草药分类和生产的质量控制。
[Abstract]:Terahertz time-domain spectroscopy (THz-TDS) combined with principal component analysis-linear discriminant analysis (PCA-LDA) and support vector machine (SVM) were used to identify authentic rhubarb samples. The terahertz time-domain transmission spectra of 41 rhubarb samples were measured in time domain, and then these time-domain signals were converted into absorption coefficients in frequency domain. The qualitative classification models of principal component analysis linear discriminant analysis and support vector machine are established according to the absorption coefficient of samples and the classification models of authentic and non-genuine rhubarb samples are cross-validated. The prediction ability and stability of the model were evaluated with self-help Latin partition, 50 times self-help Latin partition with a score of 4. 5%. The principal component analysis (PCA)-linear discriminant analysis (LDA) and support vector machine (SVM) are used to obtain satisfactory results. The proposed method is proved to be a convenient, pollution-free, accurate and chemical free method for identification of rhubarb samples. The steps proposed in this paper can be applied to the classification and quality control of other Chinese herbal medicines.
【作者单位】：首都师范大学化学系;中央民族大学理学院;Center
【基金】：the National Instrumentation Program(2012YQ140005) Natural Science Foundation of China(21275101)
【分类号】：O657.3;R282.5

【相似文献】