基于近红外光谱技术的茶油原产地快速鉴别

为研究茶油原产地溯源问题,维护其市场秩序,促进公平竞争。该文利用近红外光谱技术采集湖南、江西、安徽和浙江4个不同产地茶油的光谱数据,并运用Savitzky-Golay平滑（savitzky-golay,SG）、多元散射校正（multiplicative scatter correction,MSC）、一阶导数（first derivation,FD）和矢量归一化（vector normalization,VN）等4种方法对其进行预处理。采用偏最小二乘法（partial least squares,PLS）提取最佳主成分,构建PLS回归模型;同时,采用主成分分析（principal compon...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 32; no. 16; pp. 293 - 299
Main Author 文韬 郑立章 龚中良 李立君 谢洁飞 马强
Format Journal Article
LanguageChinese
Published 中南林业科技大学机电工程学院,长沙,410004%中南林业科技大学理学院,长沙,410004 2016
Subjects
原产地
模型
油脂
茶油
近红外光谱
鉴别
预处理
预处理
models
油脂
鉴别
preprocessing
近红外光谱
模型
oils and fats
原产地
茶油
camellia oil
identification
near infrared spectroscopy
geographical origin
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2016.16.040

Cover

More Information
Summary:为研究茶油原产地溯源问题,维护其市场秩序,促进公平竞争。该文利用近红外光谱技术采集湖南、江西、安徽和浙江4个不同产地茶油的光谱数据,并运用Savitzky-Golay平滑（savitzky-golay,SG）、多元散射校正（multiplicative scatter correction,MSC）、一阶导数（first derivation,FD）和矢量归一化（vector normalization,VN）等4种方法对其进行预处理。采用偏最小二乘法（partial least squares,PLS）提取最佳主成分,构建PLS回归模型;同时,采用主成分分析（principal component analysis,PCA）和PLS算法提取最佳主成分,作为BP人工神经网络（BP artificial neural network,BPANN）输入变量,构建PCA-BPANN和PLS-BPANN模型。以验证集相关系数RP和验证集均方根误差RMSEP为模型的评价指标,分别优选最佳PLS和BPANN模型。试验结果表明,SG-PLS-DA和SG-PLS-BPANN-DA模型对未知样本的整体分类准确率均大于90%。其中,SG-PLS-BPANN-DA的鉴别效果优于前者,其建模集相关系数RC、均方根误差RMSEC分别为0.974、0.170,验证集相关系数RP、均方根误差RMSEP分别为0.972、0.172,对上述两类样本集的总体分类准确率分别为98.15%、95.83%,该模型能较准确鉴别茶油原产地。研究结果可为快速辨别茶油原产地提供参考。
Bibliography:11-2047/S
Wen Tao,Zheng Lizhang,Gong Zhongliang,Li Lijun,Xie Jiefei,Ma Qiang （1. School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha 410004, China; 2. School of Science, Central South University of Forestry and Technology, Changsha 410004, China）
The identification of geographical origin of camellia oil is very significant in food market to maintain the market order and promote fair competition. The objective of this research was to evaluate the feasibility of a high efficient and nondestructive detection of the geographical origin of camellia oil by using near infrared spectroscopy combined with chemometrics methods. In this paper, 4 kinds of camellia oil samples obtained from Hunan, Jiangxi, Anhui and Zhejiang Province were tested with 39 samples for each kind. The samples were randomly divided into 2 groups, i.e. calibration set（30, 27, 27 and 24 were respectively for Hunan, Jiangxi, Anhui and Zhejiang） and validation set（9, 12, 12 and 15 were respec
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2016.16.040