首页 | 本学科首页   官方微博 | 高级检索  
     检索      

DPLS和SVM的掺假花椒粉近红外光谱定性鉴别
引用本文:吴习宇,祝诗平,王谦,龙英凯,徐丹,唐超.DPLS和SVM的掺假花椒粉近红外光谱定性鉴别[J].光谱学与光谱分析,2018,38(8):2369-2373.
作者姓名:吴习宇  祝诗平  王谦  龙英凯  徐丹  唐超
作者单位:1. 西南大学工程技术学院,重庆 400716
2. 国网重庆市电力公司电力科学研究院,重庆 401123
3. 西南大学食品科学学院,重庆 400716
基金项目:国家自然科学基金项目(30671198,31771670),西南大学基本科研业务费项目(XDJK2015C137),国网重庆市电力公司电力科学研究院科技项目(SGCQDKOOPJJS1600081)资助
摘    要:花椒是我国的八大调味料之一。目前花椒市场掺假现象较为多见,为实现掺假花椒粉的快速定性鉴别,采用了近红外光谱结合化学计量学方法进行了探讨。将麦麸粉、稻糠粉、玉米粉和松香粉以1 Wt/Wt.%的递增梯度分别掺入红花椒粉和青花椒粉中,制备掺假浓度范围为1~54 Wt/Wt.%的掺假花椒粉样品,以掺假花椒粉和纯花椒粉共462份样品依次采集其800~2 500 nm范围的漫反射近红外光谱。采用主成分分析法(PCA)对光谱数据进行分析,前3个主成分累计贡献率达98.72%,做出的得分图表明PCA法对掺假的花椒粉具有较好的区域划分。347份样本作为校正集,以特征谱区2 000~2 200 nm范围的257个采样点的光谱信号作为输入,采用判别偏最小二乘法(DPLS)和支持向量机(SVM)建立定性鉴别模型,经不同光谱预处理,对115份验证集样本进行预测,总体鉴别正确率在97.39%~100%之间,表明该方法是快速定性鉴别掺假花椒粉的一个有效手段。

关 键 词:花椒粉  近红外光谱  主成分分析  判别偏最小二乘法  支持向量机  掺假  
收稿时间:2017-04-19

Qualitative Identification of Adulterated Huajiao Powder Using Near Infrared Spectroscopy Based on DPLS and SVM
WU Xi-yu,ZHU Shi-ping,WANG Qian,LONG Ying-kai,XU Dan,TANG Chao.Qualitative Identification of Adulterated Huajiao Powder Using Near Infrared Spectroscopy Based on DPLS and SVM[J].Spectroscopy and Spectral Analysis,2018,38(8):2369-2373.
Authors:WU Xi-yu  ZHU Shi-ping  WANG Qian  LONG Ying-kai  XU Dan  TANG Chao
Institution:1. College of Engineering and Technology, Southwest University, Chongqing 400716, China 2. Chongqing Electric Power Corporation Research Institute, Chongqing 401123, China 3. College of Food Science, Southwest University, Chongqing 400716, China
Abstract:Huajiao is one of the “eight famous condiments” in China. Some cheaper adulterants were found to be added into Huajiao powder and in order to identify adulterated Huajiao powder qualitatively and quickly, a direct detecting method using near infrared (NIR) spectroscopy coupled with discriminant partial least squares (DPLS) and support vector machine (SVM) had been developed in this study. Wheat bran, rice bran, corn flour and rosin powder with 1 Wt/Wt.% incremental concentration gradient were mixed with red Huajiao powder and green Huajiao powder separately and the adulterated Huajiao powder with range of 1~54 Wt/Wt.% were prepared. Diffuse NIR spectra (800~2 500 nm) of pure and adulterated Huajiao powder were acquired. Principal component analysis (PCA) on the spectral data of all 462 samples was used and the first three principal components accounted for 98.72% of total variation. It was effective for clustering different adulterated Huajiao powder from the main composition PC1, PC2 and PC3 score plot. 347 samples as a calibration set and with the characteristic band spectrum 2 000~2 200 nm as input, kinds of qualitative models with different spectra pretreatment were established using DPLS and SVM analysis, which were for predicting the rest 115 samples. Results showed that, using different pretreatment methods, and the qualitative identification accuracy of the validation set were between 97.39%~100%, in which adulterated Huajiao powder could be identified totally. NIRS based on DPLS and SVM is a rapid and nondestructive tool for the qualitative analysis of adulterated Huajiao powder.
Keywords:Huajiao powder  Near infrared spectroscopy  Principal component analysis  Discriminant partial least squares  Support vector machine  Adulterants  
本文献已被 CNKI 等数据库收录!
点击此处可从《光谱学与光谱分析》浏览原始摘要信息
点击此处可从《光谱学与光谱分析》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号