摘要
收集6个产地凌霄花样品的近红外光谱,构建支持向量机(SVM)模型进行产地鉴别.运用竞争自适应重加权采样(CARS)算法提取特征波长变量,在此基础上建立CARS-SVM产地判别模型.将该判别模型与线性判别分析、偏最小二乘判别分析和簇类独立软模式法3种模型进行比较.结果表明,SVM模型对不同产地凌霄花样品的鉴别结果良好,经CARS提取特征波长后,波长变量数从1557减小至52,所构建的CARS-SVM模型对6个产地样品的判别准确率较高,明显优于上述3种模型.因此,近红外光谱技术可快速准确判别凌霄花的产地,为凌霄花的产地鉴别与质量评价提供一种新的方法.
The near-infrared(NIR)spectra of 271 samples from six geographical origins were collected and analyzed in this study.Support vector machine(SVM),was used to establish a model.Competitive adaptive reweighted sampling(CARS)was applied to extract characteristic wavelength variables.The CARS-SVM model was established and compared with the linear discriminant analysis,partial least squares discriminant analysis and soft independent modelling of class analogy.The results showed that SVM model had a good discriminant effect on Campsis grandiflora from different origins.When the characteristic wavelength variables were sharply reduced from 1557 to 52 by CARS,the constructed CARS-SVM model can achieve an optimal classification accuracy which was obviously superior to that of other three models.Therefore,NIR spectroscopy can quickly and accurately identify the origin of Campsis grandiflora,and provide a certain reference for the geographical origin discrimination and quality assessment of Campsis grandiflora.
作者
王燕
李颖
叶桦珍
李泳宁
徐杰
林振宇
WANG Yan;LI Ying;YE Huazhen;LI Yongning;XU Jie;LIN Zhenyu(College of Pharmacy,Fujian Health College,Fuzhou,Fujian 350101,China;College of Marine Biology,Xiamen Ocean Vocational College,Xiamen,Fujian 361102,China;Jiangsu Institute for Food and Drug Control,Nanjing,Jiangsu 210019,China;Key Laboratory Technology for Analytical Science of Food Safety and Biology,Ministry of Education,Fujian Provincial Key Laboratory of Analysis and Detection Technology for Food Safety,Fuzhou University,Fuzhou,Fujian 350108,China)
出处
《福州大学学报（自然科学版）》
CAS
北大核心
2022年第4期568-573,共6页
Journal of Fuzhou University(Natural Science Edition)
基金
国家重点研发计划资助项目(2019YFC1604701)
福建省教育厅中青年教师教育科研项目(JAT191298)
福建省教育厅2018年国内访问学者资助项目。
关键词
凌霄花
产地鉴别
CARS-SVM模型
近红外光谱
支持向量机
Campsis grandiflora
geographical origin discrimination
CARS-SVM model
nearinfrared spectroscopy
support vector machine
