基于近红外光谱技术有监督模式识别的青皮产地溯源分析  

Traceability analysis of Pericarpium Citri Reticulatae Viride origin based on near infrared spectroscopy technology and supervised pattern recognition

作　　者：李跑[1,2,3] 谭惠珍 谢叔娥 苏光林 董怡青 唐辉 LI Pao;TAN Huizhen;XIE Shue;SU Guanglin;DONG Yiqing;TANG Hui(College of Food Science and Technology,Hunan Agricultural University,Changsha 410128,China;Hunan Agricultural Product Processing Institute,Hunan Academy of Agricultural Sciences,Changsha 410125,China;Guangdong Provincial Key Laboratory of Utilization and Conservation of Food and Medicinal Resources in Northern Region,Shaoguan 512005,China;Hunan Provincial Institute of Quality Supervision and Inspection of Product,Changsha 410007,China)

机构地区：[1]湖南农业大学食品科学技术学院,湖南长沙410128 [2]湖南省农业科学院湖南省农产品加工研究所,湖南长沙410125 [3]广东省粤北食药资源利用与保护重点实验室,广东韶关512005 [4]湖南省产商品质量监督检验研究院,湖南长沙410007

出　　处：《轻工学报》2024年第2期54-59,共6页Journal of Light Industry

基　　金：国家自然科学基金项目(31601551);湖南省自然科学基金项目(2023JJ30290);中国博士后科学基金面上项目(2019M650187);湖南省教育厅科学研究项目(21A0127);2022年湖南省研究生科研创新项目(QL20220173)。

摘　　要：利用便携式近红外光谱仪采集不同产地(安徽、广东、四川)青皮外壁和内囊光谱数据,采用单一预处理和组合预处理方法消除光谱中的多种干扰,结合主成分分析(PCA)、簇类独立软模式分类法(SIMCA)及Fisher线性判别分析(FLDA)等模式识别方法建立青皮产地溯源模型。结果表明,光谱预处理可以在一定程度上消除基线漂移、背景噪声和谱峰重叠干扰,但无法实现产地溯源。3种模式识别方法中,PCA无法实现青皮产地溯源;青皮外壁和内囊原始光谱的SIMCA模型获得的青皮产地溯源整体鉴别率分别为99.14%和98.28%;FLDA模型获得的整体鉴别率均为99.57%,优于SIMCA模型;经光谱预处理优化后的SIMCA和FLDA模型对青皮产地溯源的鉴别率均可达100%,即便携式近红外光谱技术结合有监督模式识别方法可实现青皮产地溯源的无损分析,可为食药同源物质产地溯源拓展新途径。Spectral data of the outer wall and inner capsule of Pericarpium Citri Reticulatae Viride from different regions(Anhui,Guangdong,and Sichuan)were collected with portable near infrared spectrometer.Multiple interferences in the spectra were eliminated using single and combined pretreatment methods.Pattern recognition methods such as principal component analysis(PCA),cluster independent soft pattern classification(SIMCA)and Fisher linear discriminant analysis(FLDA)were used to establish traceability models of Pericarpium Citri Reticulatae Viride origin.The results showed that spectral pretreatment could eliminate the interferences of baseline drift,background,and spectral peak overlap to a certain extent.However,the traceability analysis of the origin couldn′t be achieved.Among the three pattern recognition methods,accurate traceability analysis of Pericarpium Citri Reticulatae Virid couldn′t be achieved with PCA method.The whole identification rate of SIMCA model with the outer wall and inner capsule original spectra were 99.14%and 98.28%,respectively.The whole identification rates of FLDA models were both 99.57%,better than that of SIMCA models.The identification rates of SIMCA and FLDA models with appropriate spectral pretreatment were 100%.Therefore,portable near infrared spectroscopy technology combined with the supervised pattern recognition methods can achieve non-destructive traceability analysis of Pericarpium Citri Reticulatae Viride origin,expanding a new way for the traceability analysis of food and drug homologous substances origin.

关 键 词：青皮 溯源分析 近红外光谱技术 有监督模式识别方法 

分 类 号：TS218[轻工技术与工程—粮食、油脂及植物蛋白工程] O561.3[轻工技术与工程—食品科学与工程]