Soybean Origin Identification Based by Near-Infrared Spectrum Based on Principal Component Analysis and Artificial Neural Network Model

Qiong TIAN; Xinhua MA; Junjie YUAN; Yang LONG; Wuxing HONG; Yunyu LU

doi:10.13386/j.issn1002-0306.2020060271

Volume 42 Issue 9

Apr. 2021

Turn off MathJax

Article Contents

Abstract

References

Science and Technology of Food Industry > 2021 > 42(9): 270-274. > DOI: 10.13386/j.issn1002-0306.2020060271

TIAN Qiong, MA Xinhua, YUAN Junjie, et al. Soybean Origin Identification Based by Near-Infrared Spectrum Based on Principal Component Analysis and Artificial Neural Network Model[J]. Science and Technology of Food Industry, 2021, 42(9): 270−274. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2020060271.

Citation:

PDF (871 KB)

Soybean Origin Identification Based by Near-Infrared Spectrum Based on Principal Component Analysis and Artificial Neural Network Model

Technology Center of Zhanjiang Customs District, Zhanjiang 524022, China

More Information

Received Date: June 21, 2020
Available Online: February 25, 2021

Graphical Abstract

Abstract

Abstract

In order to identify the geographical origin of soybeans accurately and quickly, the characteristics of soybean in different countries were studied by near infrared spectroscopy (NIRS), principal component analysis (PCA) and artificial neural network (ANN), and the identification model of imported soybean producing areas was established. The near-infrared reflectance spectrums of the 166 soybeans from Argentina, Brazil, Uruguay and the United States had been collected, then the twelve outliers of NIRS were eliminate by using a box-plot graph. The original spectral data was processed by means of multiplicative scatter correction(MSC), standard normal variate(SNV), Savitzky-Golay(SG), etc. It was gotten the optimal result by the preprocessing method based on the smoothing treatment in SG (3 points) with MSC. The PCA was used to compress the NIRS, the analysis results showed that the cumulative variance contribution of PC1 to PC10 (the first ten principal components) were 99.966%. The first 10 principal components obtained by principal component analysis were selected as input vectors, and four producing areas were selected as target vectors. The recognition models were established by support vector machine (SVM), neighbor algorithm (KNN) and artificial neural network (ANN).The results showed that the BP-ANN model was the best, and the overall discrimination accuracy for the test set was 95.65% by ANN model, and the discrimination accuracy for soybean samples from Argentina, Brazil, Uruguay and the United States were 100%, 100%, 80% and 100%, respectively. The ANN model can identify the origin of soybeans imported from different countriesrall discrimination accuracy for the test set was 95.65% by ANN model, and the discrimination accuracy for soybean samples from Argentina, Brazil, Uruguay and the United States were 100%, 100%, 80% and 100%, respectively. The ANN model can identify the origin of soybeans imported from different countries

FullText(HTML)

References (24)

References

[1]	韩立德, 盖钧镒, 张文明. 大豆营养成分研究现状[J]. 种子,2003(5):58−60.
[2]	马新华, 赵菊鹏, 龙阳, 等. 进口大豆检验检疫[M]. 北京: 中国农业出版社, 2018: 1-2.
[3]	潘广, 杨帆, 章桂明, 等. 进口转基因大豆品系检测及分析[J]. 中国油料作物学报,2020,42(2):298−305.
[4]	龙沈飞, 潘龙, 吴阳, 等. 国产和进口大豆常规化学成分的综合分析[J]. 饲料工业,2020,41(7):55−59.
[5]	袁俊杰, 魏霜, 龙阳, 等. 转基因大豆MON87701和MON87708双重实时荧光PCR检测技术的建立与应用[J]. 农业生物技术学报,2020,28(2):342−348.
[6]	金俊, 姜秋水, 刘新. 进口大豆热损贬值的因素分析与评估[J]. 中国油脂,2019,44(9):133−137.
[7]	薛雅琳, 王雪莲, 赵会义, 等. 利用近红外分析技术测定大豆水分含量方法的研究[J]. 中国油脂,2009,34(7):69−71. doi: 10.3321/j.issn:1003-7969.2009.07.021
[8]	王丽萍, 陈文杰, 赵兴忠, 等. 基于近红外漫反射光谱法的大豆粗蛋白和粗脂肪含量的快速检测[J]. 大豆科学,2019,38(2):280−285.
[9]	宋雪健, 王洪江, 钱丽丽, 等. 基于近红外光谱技术对草莓品质的快速检测研究[J]. 黑龙江八一农垦大学学报,2020,32(3):35−43. doi: 10.3969/j.issn.1002-2090.2020.03.006
[10]	田翔, 刘思辰, 王海岗, 等. 近红外漫反射光谱法快速检测谷子蛋白质和淀粉含量[J]. 食品科学,2017,38(16):140−144. doi: 10.7506/spkx1002-6630-201716022
[11]	Riccardo N, Simone C, Federico M, et al. Geographical characterization by MAE-HPLC and NIR methodologies and carbonic anhydrase inhibition of Saffron components[J]. Food Chemistry,2017,221:855−863. doi: 10.1016/j.foodchem.2016.11.086
[12]	Haroon E T, Muhammad A, Gustav K M, et al. Authentication of the geographical origin of Roselle (Hibiscus sabdariffa L) using various spectroscopies: NIR, low-field NMR and fluorescence[J]. Food Control,2020,114:1−8.
[13]	Patrizia F, Silvia D L, Remo B, et al. Near infrared (NIR) spectroscopy-based classification for the authentication of Darjeeling black tea[J]. Food Control,2019,100:292−299. doi: 10.1016/j.foodcont.2019.02.006
[14]	夏立娅, 申世刚, 刘峥颢, 等. 基于近红外光谱和模式识别技术鉴别大米产地的研究[J]. 光谱学与光谱分析,2013,33(1):102−105. doi: 10.3964/j.issn.1000-0593(2013)01-0102-04
[15]	赵海燕, 郭波莉, 魏益民, 等. 近红外光谱对小麦产地来源的判别分析[J]. 中国农业科学,2011,44(7):1451−1456. doi: 10.3864/j.issn.0578-1752.2011.07.018
[16]	李勇, 严煌倩, 龙玲等. 化学计量学模式识别方法结合近红外光谱用于大米产地溯源分析[J]. 江苏农业科学,2017,45(21):193−195.
[17]	刘文静. 基于大豆异黄酮特征的大豆产地溯源研究[D]. 大庆: 黑龙江八一农垦大学, 2018.
[18]	卢锡纯. 基于脂肪酸含量的大豆产地溯源的研究[J]. 食品研究与开发,2018,39(16):55−59. doi: 10.3969/j.issn.1005-6521.2018.16.011
[19]	Lai H Q, Xi J L, Sun J C, et al. Multi-elemental analysis by energy dispersion X-ray fluorescence spectrometry and its application on the traceability of soybean origin[J]. Atomic Spectroscopy,2020,41(1):20−28. doi: 10.46770/AS.2020.01.003
[20]	鹿保鑫, 马楠, 王霞, 等. 基于电感耦合等离子体质谱仪分析矿物元素含量的大豆产地溯源[J]. 食品科学,2018,39(8):288−294. doi: 10.7506/spkx1002-6630-201808045
[21]	鹿保鑫, 马楠, 王霞, 等. 大豆有机成分辅助矿物元素指纹特征产地溯源[J]. 食品科学,2019,40(4):338−344. doi: 10.7506/spkx1002-6630-20171009-033
[22]	张勇, 李雪, 汪雪芳, 等. 基于脂肪酸组成的进口大豆鉴别技术研究[J]. 食品安全质量检测学报,2020,11(8):2375−2379.
[23]	Akiko O, Akiko H, Izumi N. Determination of trace elements in soybean by X-ray fluorescence analysis and its application to identification of their production areas[J]. Food Chemistry,2014,147:318−326. doi: 10.1016/j.foodchem.2013.09.142
[24]	全国粮油标准化委员会. GB/T 24870-2010 粮油检验大豆粗蛋白质、粗脂肪含量的测定近红外法[S]. 北京: 中国标准出版社, 2010.