基于近红外光谱和新型变量筛选策略的砂糖橘产地无损鉴别  

Nondestructive Identification of‘Shatangju’Mandarin from Different Origins Based on Near-infrared Spectroscopy Combined with the Variable Screening Strategy

作　　者：邱熙文 杨清华 谌佳琪 唐辉 李跑[1,3] 杜国荣 QIU Xiwen;YANG Qinghua;ZHAN Jiaqi;TANG Hui;LI Pao;DU Guorong(College of Food Science and Technology,Hunan Agricultural University,Changsha 410128,China;China Certification&Inspection Group Hunan Co.,Ltd.,Changsha 410021,China;Guangdong Provincial Key Laboratory of Utilization and Conservation of Food and Medicinal Resources in Northern Region,Shaoguan 512005,China;Shanghai Tobacco Group Co.,Ltd.Technical Center Beijing Workstation,Beijing 101121,China)

机构地区：[1]湖南农业大学食品科学与技术学院,湖南长沙410128 [2]中国检验认证集团湖南有限公司,湖南长沙410021 [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]上海烟草集团有限责任公司技术中心北京工作站,北京101121

出　　处：《中国果菜》2025年第3期6-11,共6页China Fruit & Vegetable

基　　金：湖南省自然科学基金(2023JJ30290);2024年度湖南省大学生创新训练计划一般项目(s202410-537029);广东省食药资源利用与保护重点实验室2023年度开放基金课题重点项目(FMR2023012Z);湖南农业大学2024年学科交叉研究青年引导项目(2024XKJC10)。

摘　　要：本研究基于近红外(NIR)光谱技术与变量筛选-线性判别分析(LDA)方法,建立了一种砂糖橘产地无损鉴别方法。在25、45 ms和65 ms三个积分时间下,分别采集了广西、云南和广东砂糖橘的近红外光谱。利用光谱预处理消除干扰,采用主成分分析(PCA)和LDA方法建立砂糖橘产地的鉴别模型。此外,通过竞争性自适应重加权采样法(CARS)、蒙特卡罗非信息变量消除法(MCUVE)、连续投影算法(SPA)和随机检验(RT)等变量筛选方法进一步简化模型,提高模型的鉴别率。结果表明,光谱预处理方法可以消除光谱中的干扰,仅依靠无监督模式识别无法实现对不同产地砂糖橘的准确鉴别;45 ms和65 ms积分时间下的模型优于25 ms下的模型,基于优化预处理的LDA模型可以获得95.10%的鉴别率;采用变量筛选方法的模型鉴别率得到明显提升,其中65 ms积分时间下,去偏移(de-bias)-RT-LDA、标准正态变量变换(SNV)-RT-LDA、原始光谱-SPA-LDA和一阶导(1st)-SPA-LDA模型,以及45 ms积分时间下,原始光谱-MCUVE-LDA模型鉴别率均达到99.02%。以上结果表明,基于便携式NIR光谱技术与变量筛选-LDA方法可实现砂糖橘产地准确无损鉴别。A non-destructive traceability method for‘Shatangju’mandarin(Citrus reticulata Blanco cv.Shatangju)from different origins was established based on near-infrared(NIR)spectroscopy technology and variable screening-linear discriminant analysis(LDA)method.Spectra of‘Shatangju’mandarin from Guangxi,Yunnan,and Guangdong at the integration times of 25,45 ms,and 65 ms were collected.Spectral preprocessing was used to eliminate interferences,while principal component analysis(PCA)and LDA methods were used to establish identification the models for‘Shatangju’mandarin from different origins.Competitive adaptive reweighted sampling(CARS),Monte carlo non informative variable elimination(MCUVE),continuous projection algorithm(SPA),and randomized trial method(RT)were used to further simplify the model and improve the identification accuracy.The results indicated that spectral preprocessing methods could eliminate the interferences in spectra.The unsupervised pattern recognition could not achieve the identification of‘Shatangju’mandarin from different origins.The models of 45 ms and 65 ms were better than those of 25 ms.95.10%identification rate could be obtained with LDA and spectral preprocessing methods.The accuracies of model identification using variable screening method were significantly improved.99.02%identification rate could be obtained with 65 ms-debias correction(de-bias)-RT-LDA,65 ms-standard normal variate transformation(SNV)-RT-LDA,65 ms-original spectra-SPA-LDA,65 ms-first-order derivative(1st)-SPA-LDA models,and 45 ms-original spectra-MCUVE-LDA models.The above results indicated that the portable NIR spectroscopy technology and variable screening-LDA method could achieve accurate and non-destructive identification of‘Shatangju’mandarin from different origins.

关 键 词：砂糖橘 便携式近红外光谱 产地 变量筛选 无损鉴别 

分 类 号：O657.33[理学—分析化学]