首页 > 论文 > 激光与光电子学进展 > 55卷 > 6期(pp:63003--1)

中红外光谱法结合支持向量机快速鉴别蜂蜜品种

Mid-Infrared Spectroscopy Analysis Combined with Support Vector Machine for Rapid Discrimination of Botanical Origin of Honey

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为快速鉴别5种蜂蜜(椴树蜜、荆条蜜、油菜蜜、洋槐蜜、荔枝蜜)的品种, 首次提出了基于主成分分析(PCA)方法结合线性支持向量机(SVM)或最小二乘支持向量机(LSSVM)的中红外光谱法鉴别蜂蜜品种的新方法。用傅里叶变换中红外光谱仪测定5种蜂蜜样本的中红外光谱, 并进行归一化预处理, 然后用主成分分析降维方法分别提取经预处理后的光谱数据中的5维、10维、15维、20维特征数据, 最后设计了线性SVM和基于网格搜索优化算法的径向基函数(RBF)的LSSVM分类器模型。利用不同分类器模型, 识别未知蜂蜜样本光谱数据降维到不同维数的特征数据, 并进行实验验证。结果表明:应用主成分分析降维方法降维到20维的特征数据在SVM和LSSVM分类器上的平均识别率均高于97%, 最高识别率均可达到100%, 且稳定性很好;利用较低维数数据进行分类时, LSSVM分类器比SVM的识别精度更高, 稳定性更好。研究证明将中红外光谱与线性SVM或LSSVM结合用于快速鉴别蜂蜜品种是可行的。

Abstract

To achieve the fast discrimination of five varieties of honeys, namely linden honey, vitex honey, rape honey, acacia honey and litchi honey, we propose a new method in this article by using the mid-infrared spectra based on principle component analysis (PCA) combined with linear support vector machine (SVM) or least squares support vector machine (LSSVM). The mid-infrared spectra of five varieties of honey samples are determined by Fourier transform infrared spectroscopy and normalized. Then the 5-dimensional, 10-dimensional, 15-dimensional, and 20-dimensional feature data will be extracted from spectra with the use of dimension reduction method of PCA after normalization. Finally, the two classifier models, linear SVM and LSSVM with radial basis function (RBF) based on the grid search optimization, are designed. Using different classifier model, we identify the different dimensional feature data extracted from spectra data of unknown honey samples. Then the results of different dimension feature data and different support vector machines are validated. Experimental results show that for the 20-dimensional feature data obtained by the dimension reduction method of PCA, an average recognition rate of higher than 97% on SVM and LSSVM classifiers is achieved, the highest recognition rate can reach 100%, and classifier stability is very good. LSSVM classifier has higher recognition accuracy and better stability than linear SVM classifier in classification with lower dimension data. Hence, it proves the feasibility of rapid identification of five varieties of honeys with mid-infrared spectra combined with linear SVM or LSSVM.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O657.33

DOI:10.3788/lop55.063003

所属栏目:光谱学

基金项目:国家自然科学基金面上项目(331772070)、中国农业科学院创新工程项目(CAAS-ASTIP-2017-IAR)、国家特色农产品风险评估专项(GJFP2017010)、国家蜂产业技术体系(CARS-45-KXJ10)

收稿日期:2017-11-23

修改稿日期:2018-01-05

网络出版日期:--

作者单位    点击查看

徐天扬:中国农业科学院蜜蜂研究所, 北京 100093农业部蜂产品质量安全控制重点实验室(北京), 北京 100093农业部蜂产品质量安全风险评估实验室, 北京 100093
杨娟:中国农业科学院蜜蜂研究所, 北京 100093
孙晓荣:北京工商大学计算机与信息工程学院, 北京 100048食品安全大数据技术北京市重点实验室, 北京 100048
刘翠玲:北京工商大学计算机与信息工程学院, 北京 100048食品安全大数据技术北京市重点实验室, 北京 100048
李熠:中国农业科学院蜜蜂研究所, 北京 100093农业部蜂产品质量安全控制重点实验室(北京), 北京 100093农业部蜂产品质量安全风险评估实验室, 北京 100093
周金慧:中国农业科学院蜜蜂研究所, 北京 100093农业部蜂产品质量安全控制重点实验室(北京), 北京 100093农业部蜂产品质量安全风险评估实验室, 北京 100093
陈兰珍:中国农业科学院蜜蜂研究所, 北京 100093农业部蜂产品质量安全控制重点实验室(北京), 北京 100093农业部蜂产品质量安全风险评估实验室, 北京 100093

联系人作者:陈兰珍(chenlanzhen2005@126.com)

备注:徐天扬(1985-), 女, 硕士, 科研助理, 主要从事数据处理与模式识别方面的研究。E-mail: goodgoodstudy0929@126.com

【1】Chen L Z. Study on quality evaluation for honey by near infrared spectroscopy[D]. Beijing: Institute of Quality Standards and Testing Technology for AGRO-Products of CAAS, 2010.
陈兰珍. 蜂蜜品质近红外光谱评价技术研究[D]. 北京: 中国农业科学院农业质量标准与检测技术研究所, 2010.

【2】Liu B J. The research of detection method about characteristic of honey producing area[D]. Baoding: Hebei University, 2010.
刘博静. 蜂蜜产地特征检测方法的研究[D]. 保定: 河北大学, 2010.

【3】Zhong Y P, Zhong Z S, Chen L Z, et al. Qualitative identification of floral origin and adulteration of honey by near-infrared spectroscopy[J]. Modern Food Science and Technology, 2010, 26(11): 1280-1282.
钟艳萍, 钟振声, 陈兰珍, 等. 近红外光谱技术定性鉴别蜂蜜品种及真伪的研究[J]. 现代食品科技, 2010, 26 (11): 1280-1282.

【4】Ruoff K, Luginbühl W, Künzli R, et al. Authentication of the botanical and geographical origin of honey by mid-infrared spectroscopy[J]. Journal of Agricultural and Food Chemistry, 2006, 54(18): 6873-6880.

【5】Bertelli D, Plessi M, Sabatini A G, et al. Classification of Italian honeys by mid-infrared diffuse reflectance spectroscopy (DRIFTS)[J]. Food Chemistry, 2007, 101(4): 1565-1570.

【6】Graa G, Moreira A S, Correia A J , et al. Mid-infrared (MIR) metabolic fingerprinting of amniotic fluid: a possible avenue for early diagnosis of prenatal disorders?[J]. Analytica Chimica Acta, 2013, 764: 24-31.

【7】Zhang W J, Chen L Z, Wu L M, et al.Study of mid-infrared spectroscopy analysis for rapid discrimination of botanical origin of honey[C]. Summit Forum of National Bee Industry, 2013.
张文娟, 陈兰珍, 吴黎明, 等. 中红外光谱法快速鉴别不同蜜源蜂蜜[C]. 全国蜂产业高峰论坛, 2013.

【8】Hu Y Q, Yin C L, Ma W K, et al. Identification of adulterated honey based on infrared spectroscopy and pattern recognition technology[J]. Chinese Journal of Applied Chemistry, 2011, 28(s1): 144-145.
胡乐乾, 尹春玲, 马渭奎, 等. 红外光谱法对蜂蜜掺伪的模式识别[J]. 应用化学, 2011, 28(s1): 144-145.

【9】Sun Y, Zhang H H, Wang Z. Application of infrared spectrum technology in Raohe honey characterization of traceability[J]. Chemical Analysis and Meterage, 2015, 24(3): 41-44.
孙燕, 张海华, 王铮. 中红外光谱技术应用于饶河蜂蜜产地溯源的表征[J]. 化学分析计量, 2015, 24(3): 41-44.

【10】Duan F H, Wang X H, Ye H H, et al. Carbon dioxide retrieval method based on statistics and optical path distribution[J]. Acta Optica Sinica, 2017, 37(5): 0501003.
段锋华, 王先华, 叶函函, 等. 基于统计与光程分布的二氧化碳反演方法[J]. 光学学报, 2017, 37(5): 0501003.

【11】Cheng L Y, Mi G Y, Li S, et al. Quality diagnosis of joints in laser brazing based on principal component analysis-support vector machine model[J]. Chinese Journal of Lasers, 2017, 44(3): 0302004.
程力勇, 米高阳, 黎硕, 等. 基于主成分分析-支持向量机模型的激光钎焊接头质量诊断[J]. 中国激光, 2017, 44(3): 0302004.

【12】Liao J S, Wang L G. Hyperspectral image classification method based on fusion with two kinds of spatial information[J]. Laser & Optoelectronics Progress, 2017, 54(8): 081002.
廖建尚, 王立国. 两类空间信息融合的高光谱图像分类方法[J]. 激光与光电子学进展, 2017, 54(8): 081002.

【13】Chen L Z, Sun Q, Ye Z H, et al. Determination of floral origin of honey by near infrared spectroscopy based on artificial neural network[J]. Food Science of Technology, 2009, 34(8): 287-289.
陈兰珍, 孙谦, 叶志华, 等. 基于神经网络的近红外光谱鉴别蜂蜜品种研究[J]. 食品科技, 2009, 34(8): 287-289.

【14】Zhang Y N, Chen L Z, Xue X F, et al. Discrimination of rice syrup adulterant of acacia honey based using near-infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2015, 35(9): 2536-2539.
张妍楠, 陈兰珍, 薛晓锋, 等. 基于近红外光谱检测技术鉴别洋槐蜜中掺入大米糖浆的可行性研究[J]. 光谱学与光谱分析, 2015, 35(9): 2536-2539.

【15】Chen B M, Fan X P, Zhou Z M, et al. The principle and prospect of support vector machine[J]. Manufacturing Automation, 2010, 32(12): 136-138.
陈冰梅, 樊晓平, 周志明, 等. 支持向量机原理及展望[J]. 制造业自动化, 2010, 32(12): 136-138.

【16】Chen W H. Research on classification of hyperspectral images based on support vector machine[D]. Harbin: Harbin Engineering University, 2008.
陈万海. 基于支持向量机的超谱图像分类技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2008.

【17】Chen H Z, Chen F, Xu L L, et al. Grid search parameter optimization applied to near infrared LSSVM modeling quantitative analysis of fishmeal ash[J]. Journal of Analytical Science, 2016, 32(2): 198-202.
陈华舟, 陈福, 许丽莉, 等. 基于网格搜索的参数优化方法用于鱼粉灰分的近红外LSSVM定量分析[J]. 分析科学学报, 2016, 32(2): 198-202.

【18】Vapnik V N. The nature of statistical learning theory[M]. New York: Springer-Verlag, 1998: 1-17.

【19】Duan K B, Rajapakse J C, Nguyen M N. One-Versus-One and One-Versus-Allmulticlass SVM-REF for gene selection in cancer classification[C]∥Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics. Valencia: [s.n.], 2007: 47-56.

【20】Chang C C, Lin C J. LIBSVM: a library for support vector machines[EB/OL]. (2010-03-01) [2017-11-20]. http:∥www.csie.ntu.edu.tw/~cjlin/libsvm.

【21】Tang X B. Seismic reservoir discrimination based on support vector machines[D]. Chengdu: Chengdu University of Technology, 2009.
唐小彪. 基于支持向量机的地震储层预测方法研究[D]. 成都: 成都理工大学, 2009.

引用该论文

Xu Tianyang,Yang Juan,Sun Xiaorong,Liu Cuiling,Li Yi,Zhou Jinhui,Chen Lanzhen. Mid-Infrared Spectroscopy Analysis Combined with Support Vector Machine for Rapid Discrimination of Botanical Origin of Honey[J]. Laser & Optoelectronics Progress, 2018, 55(6): 063003

徐天扬,杨娟,孙晓荣,刘翠玲,李熠,周金慧,陈兰珍. 中红外光谱法结合支持向量机快速鉴别蜂蜜品种[J]. 激光与光电子学进展, 2018, 55(6): 063003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF