中宁枸杞品种的近红外光谱快速鉴别  

Rapid variety discrimination of Lycium barbarum L.by near-infrared spectrum

作　　者：龙若兰 李朵 李佩佩 胡娜[1,2] 冯丹 孙菁[1,2] LONG Ruolan;LI Duo;LI Peipei;HU Na;FENG Dan;SUN Jing(Qinghai Provincial Key Laboratory of Qinghai-Tibet Plateau Biological Resources,Northwest Institute of Plateau Biology,Chinese Academy of Sciences,Xining 810008,China;Key Laboratory of Tibetan Medicine Research,Northwest Institute of Plateau Biology,Chinese Academy of Sciences,Xining 810008,China;College of Life Sciences,University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院西北高原生物研究所青海省青藏高原特色生物资源研究重点实验室,青海西宁810008 [2]中国科学院西北高原生物研究所中国科学院藏药研究重点实验室,青海西宁810008 [3]中国科学院大学生命科学学院,北京100049

出　　处：《食品与发酵工业》2023年第20期274-279,共6页Food and Fermentation Industries

基　　金：国家自然科学基金项目(32270402);青海省科研基础条件平台项目(2020-ZJ-T05);青海省重点实验室建设专项(2022-ZJ-Y18);青海省创新平台建设专项(2020-0407-NCC-0001)。

摘　　要：利用2种不同采集方式(光纤、积分球)进行近红外光谱采集,优化并建立了12种不同枸杞品种的品种判别模型,实现了对中宁枸杞品种的快速准确判别。在获取得到12种中宁枸杞品种的近红外光谱的基础上,比较不同采集方式下的光谱差异。分别建立了距离匹配(distance match,DM)、判别分析(discriminant analysis,DA)、支持向量机(support vector machine,SVM)等3个不同的品种判别模型。结果表明,以积分球采集方式下的谱图质量较好,在此采集方式下所建的DM、DA、SVM品种判别模型的识别率、预测率和准确率均达到100.00%;而用光纤所采集的谱图只有DA模型的识别率、预测率和准确率达到100.00%。积分球采集方式下所建判别方法可快速、高效地实现中宁枸杞品种判别,为生产实践的应用提供技术支撑。As a kind of Solanaceae plant,Lycium barbarum L.is not only a food material but also has medicinal functions of health preservation and anticancer,and it is also listed in the“Pharmacopoeia of the People′s Republic of China”.In this study,12 different varieties of L.barbarum were considered as the research objects.The similarities and differences of the near-infrared spectrum(NIR)under different acquisition methods(optical fiber and integrating sphere)were compared,and the classification models were established by different methods,including distance match(DM),discriminant analysis(DA),and support vector machine(SVM)with TQ analyst and Python software.By optimizing the near-infrared spectrum collection method of the various discrimination model,the rapid discrimination of L.barbarum varieties was realized.Results showed that the integrating sphere outperformed optical fiber in both the spectral quality and effect of variety discrimination modeling.The recognition rate,prediction rate,and accuracy rate of DM,DA,and SVM variety discrimination models established by this collection method all reach 100.00%,which indicated that the established method was fast and efficient for the discrimination of L.barbarum.However,only the DA model achieved 100.00%recognition,prediction,and accuracy for the spectra collected with optical fibers.This study can provide technical support for the application in production practice.

关 键 词：近红外光谱 光谱采集方式 品种判别 中宁枸杞品种 

分 类 号：O657.33[理学—分析化学] TS255.7[理学—化学]