摘要: 贝母是广泛应用于临床实践的中药材,其中川贝母尤为珍贵,存在掺假及伪冒现象,伪劣贝母会对用药者的健康产生不良影响。太赫兹时域光谱(Terahertz time domain spectroscopy)具有瞬态性、宽带性、安全性和穿透性等许多优越特性,近年来在药食无损检测领域十分活跃。以四种常见贝母(川贝母、平贝母、伊贝母、浙贝母)为研究对象,探究利用太赫兹时域光谱技术鉴别贝母品种的可行性。利用TAS7500TS太赫兹光谱系统采集贝母样品在0.6~3.0 THz范围内的光谱,并结合化学计量学方法进行预处理与建立分类模型。当分类数量为二时,称为二分类问题,当分类数量超过二时称为多分类问题。利用偏最小二乘判别分析(PLS-DA)建立四种贝母的二分类模型;使用Savitzky-Golay(S-G)平滑、多元散射校正(MSC)、标准正态变量变换(SNV)、移动平均、基线偏移校正(Baseline offset)对原始光谱进行预处理,再采用主成分分析(PCA)对预处理后的数据进行降维,以减少数据运算量、简化运算,最后建立随机森林(RF)、支持向量机(SVM)、反向传播神经网络(BPNN)多分类模型。结果显示:川-伊贝母二分类鉴别模型正确率为93.333%,平-浙贝母二分类鉴别模型正确率为98.333%,其他四种二分类鉴别模型正确率均为100%。对建立的多分类模型进行对比分析发现SVM结合SNV建模效果最好,其中川贝母正确率为95.349%,伊贝母正确率为96.552%,平贝母与浙贝母正确率均为100%,整体正确率高达97.490%。研究结果表明利用太赫兹时域光谱技术鉴别不同品种贝母是可行的,并建立了分类效果较好的SNV-SVM多分类模型,为把控中药材质量提供一种新的手段,对维护中药材市场的正常运转具有重要的意义。
关键词:太赫兹光谱技术;贝母;二分类;多分类
Abstract:Fritillary is widely used in clinical practice of Chinese medicinal materials, especially Fritillaria cirrhosa Don. There are adulteration and fake phenomenon, fake fritillary will have a negative impact on the health of the drug users. Terahertz Time-Domain spectroscopy has many advantages of transient, broadband, safety, penetration, etc. In recent years, Terahertz Time-Domain spectroscopy is very active in drug and food non-destructive detection. In this experiment, four common fritillaria species (Fritillaria cirrhosa Don, Fritillaria ussuriensis Maxim, Fritillaria pallidiflora Schrenk, and Fritillaria thunbergii) were taken as the research objects to explore the feasibility of using terahertz time-domain spectroscopy to identify fritillaria species. In this experiment, the TAS7500TS Terahertz spectrum system was used to collect the spectra of fritillate samples in the range of 0.6~3.0 THz, and the stoichiometric method was combined for pretreatment and classification model establishment. When the number of categories is 2, it is called Binary classification; when the number of categories exceeds 2, it is called Multiple classifications. Four kinds of fritillary were established by Partial Least Squares Discriminant Analysis (PLS-DA). Initial spectra are treated with Savitzky-Golay (S-G) smoothing, Multiplicative Scatter (MSC) Correction, Standard Normal Variable Transformations, moving averages, or Baseline. Principal Component Analysis is performed.PCA can reduce the dimensionality of the preprocessed data to reduce the amount of data computation and simplify the operation. Finally, a multi-classification model of Random Forest (RF), Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) can be established. The discriminant accuracy rate of the model was 93.333% for Fritillaria cirrhosa Don-Fritillaria pallidiflora Schrenk, 98.333% for Fritillaria cirrhosa Don-Fritillaria thunbergii, and 100% for all the other four biocalcification models. The accuracy of the other four dichotomies was 100%. By comparing and analyzing the established multi-classification models, it was found that the SVM combining SNV modeling effect is best, the Fritillaria cirrhosa Don accuracy is 95.349%, the Fritillaria pallidiflora Schrenk accuracy is 96.552%, the accuracy rate of Fritillaria ussuriensis Maxim and Fritillaria thunbergii was 100%. The overall accuracy rate was up to 97.490%. This research shows that it is feasible to use Terahertz Time-Domain spectroscopy to identify different fritillaria varieties, and a SNV-SVM multi-classification model with good classification effect is established, which provides a new means to control the quality of traditional Chinese medicine and is of great significance to maintain the normal operation of the traditional Chinese medicine market.
刘燕德,徐 振,胡 军,李茂鹏,崔惠桢. 基于太赫兹光谱技术的贝母品种鉴别方法研究[J]. 光谱学与光谱分析, 2021, 41(11): 3357-3362.
LIU Yan-de, XU Zhen, HU Jun, LI Mao-peng, CUI Hui-zhen. Research on Variety Identification of Fritillaria Based on Terahertz Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3357-3362.
[1] YANG Jian, LI Jing, XUE Wei-na, et al(杨 健, 李 靖, 薛维娜,等). Chinese Traditional Patent Medicine(中成药) , 2020, 42(5): 1262.
[2] WANG Hong-wei,FANG Bo,ZHANG Lei, et al(王宏伟, 方 波, 张 磊,等). Chinese Traditional Patent Medicine(中成药), 2020, 42(4): 986.
[3] LI Ran, LI Jing, TONG Qiao-zhen, et al(李 然, 李 静, 童巧珍,等). Journal of Guangdong Pharmaceutical University(广东药科大学学报), 2019, 35(5): 624.
[4] Li Rong, Zeng Canbiao, Li Junni, et al. Analytical Letters, 2020, 53(11): 1667.
[5] MA Pin, YANG Yu-ping(马 品, 杨玉平). Journal of Terahertz Science and Electronic Information Technology(太赫兹科学与电子信息学报), 2017, 15(1): 26.
[6] XU Zhe, HE Ming-xia, LI Peng-fei, et al(徐 哲, 何明霞, 李鹏飞, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(1): 42.
[7] Zhang H, Li Z, Chen T, et al. Journal of Applied Spectroscopy, 2018, 85(1): 197.
[8] LI Chen, WEI Cheng-hao, WANG Zhi-qi, et al(李 辰, 魏丞昊, 王志琪, 等). Journal of Shenzhen University·Science & Engineering(深圳大学学报·理工版), 2019, 36(2): 213.
[9] YANG Shao-zhuang, LI Can, LI Chen, et al(杨少壮, 李 灿, 李 辰,等). Modern Food Science & Technology(现代食品科技), 2019, 35(12): 258.
[10] Dorney T D, Baraniuk R G, Mittleman D M. J. Opt. Soc. Am. A, 2001, 18(7): 1562.
[11] Dragoman D, Dragoman M. Appl. Optics, 2004, 43(19): 3848.
[12] WANG Cheng, SHI Ji-yi, ZHENG Gang, et al(王 成, 史继毅, 郑 刚,等). Optical Instruments(光学仪器), 2020, 42(2): 26.
[13] Liu Jianjun, Mao Lili, Ku Jingfeng, et al. Optik, 2017, 142: 483.
[14] Poona N K, Van Niekerk A, Nadel R L, et al. Applied Spectroscopy, 2016, 70(2): 322.
[15] HU Jun, LIU Yan-de, SUN Xu-dong, et al(胡 军, 刘燕德, 孙旭东, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2020, 57(7): 073002.