Please wait a minute...
 
 
食品与发酵工业  2019, Vol. 45 Issue (11): 211-218    DOI: 10.13995/j.cnki.11-1802/ts.019234
  分析与检 本期目录 | 过刊浏览 | 高级检索 |
基于近红外光谱与支持向量机的甘薯粉丝掺假快速检测
陈嘉1, 高丽1, 叶发银1, 雷琳1, 赵国华1,2,3*
1(西南大学 食品科学学院,重庆,400715)
2(重庆市甘薯工程技术研究中心,重庆,400715)
3(重庆市农产品加工技术重点实验室,重庆,400715)
Rapid detection of adulterated sweet potato starch noodle by near-infraredspectroscopy and support vector machine
CHEN Jia1, GAO Li1, YE Fayin1, LEI Lin1, ZHAO Guohua1,2,3*
1(College of Food Science, Southwest University, Chongqing 400715, China)
2(Chongqing Sweet Potato Engineering and Technology Centre, Chongqing 400715, China)
3(Chongqing Key Laboratory of Agricultural Product Processing, Chongqing 400715, China)
下载:  HTML   PDF (2166KB) 
输出:  BibTeX | EndNote (RIS)      
摘要 探索了近红外光谱(near infrared spectra, NIRS)结合支持向量机(support vector machine, SVM)检测甘薯粉丝掺假(掺杂木薯淀粉和玉米淀粉)的可行性。以掺假甘薯粉丝为研究对象,建立了基于NIRS及SVM的甘薯粉丝掺假定性判别及定量分析模型,并通过光谱预处理及光谱变量筛选对模型进行了优化。结果显示,采用标准正态变量变换和一阶导数对全光谱预处理后,甘薯粉丝掺假SVM定性判别模型的识别准确率可达100%,优于马氏距离判别模型;用标准正态变量变换和一阶导数对光谱预处理,并通过前向区间支持向量机(forward interval support vector machine, fi-SVM)筛选光谱变量后,木薯淀粉含量SVM预测模型的相关系数(r)和预测均方差(RMSEP)可达到0.92和11.20,玉米淀粉含量SVM预测模型的r和RMSEP可达到0.96和7.49。结果表明,基于NIRS和SVM的甘薯粉丝掺假定性判别及定量分析检测模型具有较高的识别率和预测精度,用于检测甘薯粉丝的掺假是可行的。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
陈嘉
高丽
叶发银
雷琳
赵国华
关键词:  甘薯粉丝  掺假  近红外  支持向量机  定性判别  定量分析    
Abstract: The aim of this study was to explore the feasibility of identifying and quantifying adulterated sweet potato starch noodles (adulterated with cassava starch and corn starch) using near-infrared spectroscopy (NIRS) and support vector machine (SVM). Qualitative discrimination and quantitative analysis models based on NIRS and SVM were built, which were optimized by spectra pretreatment and spectral variables selection. The results showed that after using standard normal variate transformation and first derivative pretreatment, the accuracy of SVM model for qualitative discrimination based on whole NIRS spectra for identifying adulterated sweet potato starch noodles achieved 100%, which surpassed the Mahalanobis distance discriminant model. Moreover, by using a forward interval support vector machine (fi-SVM) algorithm to screen out spectral variables, the correlation coefficients (r) of the SVM models for cassava starch content and corn starch content reached 0.92 and 0.96, respectively. Besides, the root mean square error of prediction (RMSEP) of these two models reached 11.2 and 7.49, respectively. The results indicated that models based on NIRS and SVM for qualitative discrimination and quantified analysis for adulterated sweet potato starch noodles had high recognition rates and prediction accuracy. Therefore, it is feasible to detect adulteration of sweet potato starch noodles by using NIRS and SVM.
Key words:  sweet potato starch noodle    adulteration    near-infrared spectroscopy (NIRS)    support vector machine (SVM)    qualitative discrimination    quantitative analysis
收稿日期:  2018-11-03                出版日期:  2019-06-15      发布日期:  2019-07-08      期的出版日期:  2019-06-15
基金资助: 中央高校基本业务费专项资金资助(XDJK2018 C014);重庆市社会事业与民生保障科技创新专项项目(cstc20 15shms-ztzx80006);广西农产资源化学与生物技术重点实验室开放基金资助项目(KF01)
通讯作者:  博士,讲师(赵国华教授为通讯作者,E-mail:zhaoguohua1971@163.com)   
引用本文:    
陈嘉,高丽,叶发银,等. 基于近红外光谱与支持向量机的甘薯粉丝掺假快速检测[J]. 食品与发酵工业, 2019, 45(11): 211-218.
CHEN Jia,GAO Li,YE Fayin,et al. Rapid detection of adulterated sweet potato starch noodle by near-infraredspectroscopy and support vector machine[J]. Food and Fermentation Industries, 2019, 45(11): 211-218.
链接本文:  
http://sf1970.cnif.cn/CN/10.13995/j.cnki.11-1802/ts.019234  或          http://sf1970.cnif.cn/CN/Y2019/V45/I11/211
[1] 康维民, 肖念新. 甘薯淀粉掺假的快速检测研究[J]. 食品科技, 2003,29(1):78-79.
[2] 侯汉学, 董海洲,刘传富. 甘薯淀粉中掺有玉米淀粉的检测方法[J]. 食品与发酵工业, 2010,36(1):134-137.
[3] 杜连起. 甘薯粉条掺杂异种淀粉检验方法的研究[J]. 河北职业技术师范学院学报, 2000,26(2):24-26.
[4] 陈嘉, 刘嘉,马雅钦,等. 葛粉掺假的近红外漫反射光谱快速检测[J]. 食品科学, 2014,35(8):133-136.
[5] SANS S, FERRE J, BOQUE R, et al. Determination of chemical properties in 'calcot' (Allium cepa L.) by near infrared spectroscopy and multivariate calibration[J]. Food Chemistry, 2018,262:178-183.
[6] 贾柳君, 张海红,王健,等. 采用近红外光谱定量分析葡萄酒发酵液中总酸含量和pH值[J]. 食品与发酵工业, 2017,43(2):191-195.
[7] 何佳艳, 李亭,郭长凯,等. 近红外光谱法快速无损测定奶粉的脂肪含量[J]. 食品与发酵工业, 2017,43(10):228-233.
[8] TAHIR H E, ZOU X, SHEN T, et al. Near-Infrared (NIR) spectroscopy for rapid measurement of antioxidant properties and discrimination of sudanese honeys from different botanical origin[J]. Food Analytical Methods, 2016,9(9):2 631-2 641.
[9] RIOS-REINA R, LUIS GARCIA-GONZALEZ D, MARIA CALLEJON R, et al. NIR spectroscopy and chemometrics for the typification of Spanish wine vinegars with a protected designation of origin[J]. Food Control, 2018,89:108-116.
[10] BALLABIO D, ROBOTTI E, GRISONI F, et al. Chemical profiling and multivariate data fusion methods for the identification of the botanical origin of honey[J]. Food Chemistry, 2018,266:79-89.
[11] LIU N, PARRA H A, PUSTJENS A, et al. Evaluation of portable near-infrared spectroscopy for organic milk authentication[J]. Talanta, 2018,184:128-135.
[12] 潘冰燕, 鲁晓翔,张鹏,等. 近红外光谱对甜椒果实质地的无损检测[J]. 食品与发酵工业, 2015,41(11):143-147.
[13] GHOSH S, MISHRA P, MOHAMAD S N H, et al. Discrimination of peanuts from bulk cereals and nuts by near infrared reflectance spectroscopy[J]. Biosystems Engineering, 2016,151:178-186.
[14] MEES C, SOUARD F, DELPORTE C, et al. Identification of coffee leaves using FT-NIR spectroscopy and SIMCA[J]. Talanta, 2018,177:4-11.
[15] LIU J, WEN Y, DONG N, et al. Authentication of lotus root powder adulterated with potato starch and/or sweet potato starch using Fourier transform mid-infrared spectroscopy[J]. Food Chemistry, 2013,141(3):3 103-3 109.
[16] XU L, SHI P, YE Z, et al. Rapid analysis of adulterations in Chinese lotus root powder (LRP) by near-infrared (NIR) spectroscopy coupled with chemometric class modeling techniques[J]. Food Chemistry, 2013,141(3):2 434-2 439.
[17] MAHOOD F, JABEEN F, HUSSAIN J, et al. FT-NIRS coupled with chemometric methods as a rapid alternative tool for the detection & quantification of cow milk adulteration in camel milk samples[J]. Vibrational Spectroscopy, 2017,92:245-250.
[18] LU G, HUANG H, ZHANG D. Application of near-infrared spectroscopy to predict sweetpotato starch thermal properties and noodle quality[J]. Journal of Zhejiang University Science B, 2006,7(6):475-481.
[19] DING X, NI Y, KOKOT S. NIR spectroscopy and chemometrics for the discrimination of pure, powdered, purple sweet potatoes and their samples adulterated with the white sweet potato flour[J]. Chemometrics and Intelligent Laboratory Systems, 2015,144:17-23.
[20] CHUANG C C, SU S F, JENG J T, et al. Robust support vector regression networks for function approximation with outliers[J]. IEEE Transactions on Neural Networks, 2002,13(6):1 322-1 330.
[21] 张丽华, 郝莉花,李顺峰,等. 基于支持向量机的近红外光谱技术快速鉴别掺假羊肉[J]. 食品工业科技, 2015,36(23):289-293.
[22] PIERNA J, VOLERY P, BESSON R, et al. Classification of modified starches by Fourier transform infrared spectroscopy using support vector machines[J]. Journal of Agricultural and Food Chemistry, 2005,53(17):6 581-6 585.
[23] CHEN J, ZHU S, ZHAO G. Rapid determination of total protein and wet gluten in commercial wheat flour using siSVR-NIR[J]. Food Chemistry, 2017,221:1 939-1 946.
[24] 褚小立, 袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展, 2004,16(4):528-542.
[25] CHANG C, LIN C. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011,2(3):1-27.
[26] FILGUEIRAS P R, ALVES J C L, POPPI R J. Quantification of animal fat biodiesel in soybean biodiesel and B20 diesel blends using near infrared spectroscopy and synergy interval support vector regression[J]. Talanta, 2014,119:582-589.
[27] 邹婷婷, 窦英,王莹,等. 近红外光谱法结合C-SVM及v-SVM方法快速无损鉴别淀粉种类[J]. 食品工业科技, 2013,34(17):317-319.
[28] CHEN J, YE F, ZHAO G. Rapid determination of farinograph parameters of wheat flour using data fusion and a forward interval variable selection algorithm[J]. Analytical Methods, 2017,9(45):6 341-6 348.
[29] RANZAN C, TRIERWEILER L F, HITZMANN B, et al. NIR pre-selection data using modified changeable size moving window partial least squares and pure spectral chemometrical modeling with ant colony optimization for wheat flour characterization[J]. Chemometrics and Intelligent Laboratory Systems, 2015,142:78-86.
[30] CHUANG C C, JENG J T, TAO C W. Two-Stages support vector regression for fuzzy neural networks with outliers[J]. International Journal of Fuzzy Systems, 2009,11(1):20-28.
[31] SHAO Y, CEN Y, HE Y, et al. Infrared spectroscopy and chemometrics for the starch and protein prediction in irradiated rice[J]. Food Chemistry, 2011,126(4):1 856-1 861.
[32] LIN C, CHEN X, JIAN L, et al. Determination of grain protein content by near-infrared spectrometry and multivariate calibration in barley[J]. Food Chemistry, 2014,162:10-15.
[33] AL-MBAIDEEN A, BENAISSA M. Frequency self deconvolution in the quantitative analysis of near infrared spectra[J]. Analytica Chimica Acta, 2011,705(1-2):135-147.
[34] WU F, MENG Y, YANG N, et al. Effects of mung bean starch on quality of rice noodles made by direct dry flour extrusion[J]. LWT-Food Science and Technology, 2015,63(2):1 199-1 205.
[35] PHOTINAM R, MOONGNGARM A, PASEEPHOL T. Process optimization to increase resistant starch in vermicelli prepared from mung bean and cowpea starch[J]. Emirates Journal of Food and Agriculture, 2016,28(7):449-458.
[1] 杨晨昱, 袁鸿飞, 马惠玲, 任亚梅, 任小林. 基于傅里叶近红外光谱和电子鼻技术的苹果霉心病无损检测[J]. 食品与发酵工业, 2021, 47(7): 211-216.
[2] 姜洪喆, 蒋雪松, 杨一, 胡逸磊, 陈青, 施明宏, 周宏平. 肉类掺杂掺假的高光谱成像检测研究进展[J]. 食品与发酵工业, 2021, 47(6): 300-305.
[3] 张媛媛, 孟镇, 仇凯, 东思源, 武竹英, 郭新光, 钟其顶. 种属特异性PCR法鉴别罐头食品中猪、牛、羊、鸡、鸭源性成分[J]. 食品与发酵工业, 2021, 47(3): 164-169.
[4] 张珮, 王银红, 李高阳, 单杨, 朱向荣. 基于近红外光谱的桃果实冷害识别分析[J]. 食品与发酵工业, 2021, 47(2): 254-259.
[5] 蔡德玲, 唐春华, 梁玉英, 曾川, 彭碧宁. 融合近红外光谱和颜色参数的草莓可溶性固形物含量定量分析模型构建[J]. 食品与发酵工业, 2020, 46(7): 218-224.
[6] 万晓楠, 畅晓晖, 齐玮, 高欣, 乔彬, 杨向莹, 李小林, 张惠媛, 石嵩, 张捷, 周熙成. 基于近红外免疫层析技术快速检测食源性甲型肝炎病毒[J]. 食品与发酵工业, 2020, 46(7): 213-217.
[7] 盛晓慧, 李宗朋, 李子文, 朱婷婷, 王健, 尹建军, 宋全厚. 近红外光谱技术定量检测果味啤中的果汁含量[J]. 食品与发酵工业, 2020, 46(4): 247-252.
[8] 谈爱玲, 王晓斯, 楚振原, 赵勇. 基于近红外光谱融合与深度学习的玉米成分定量建模方法[J]. 食品与发酵工业, 2020, 46(23): 213-219.
[9] 张淑霞, 田亚, 邢荣花, 刘胜男, 王向军, 张守杰. 基于特征肽段的液相色谱质谱联用技术对核桃、杏仁露进行掺假鉴别[J]. 食品与发酵工业, 2020, 46(21): 215-222.
[10] 郝超, 赵忠盖, 刘飞. 基于近红外光谱的柠檬酸发酵液化清液概率偏最小二乘法监控[J]. 食品与发酵工业, 2020, 46(20): 214-220.
[11] 孟庆龙, 尚静, 黄人帅, 陈露涛, 张艳. 苹果可溶性固形物的可见/近红外无损检测[J]. 食品与发酵工业, 2020, 46(19): 205-209.
[12] 唐保山, 李坤, 张雯雯, 史正军, 关庆芳, 徐涓, 马金菊, 刘兰香, 张弘. 近红外漫反射光谱结合偏最小二乘法对紫胶理化指标的快速测定[J]. 食品与发酵工业, 2020, 46(18): 236-244.
[13] 王广浩, 高红波, 樊双喜, 李国辉, 钟其顶, 李艳. 气相色谱-质谱法检测葡萄酒中外源工业甘油副产物[J]. 食品与发酵工业, 2020, 46(16): 215-219.
[14] 吉鑫, 樊双喜, 李宜聪, 钟其顶, 陆玮, 李安军, 刘国英, 黄艳, 胡心行, 叶方平. 白酒中有机酸和醛类的偏最小二乘回归法定量分析模型[J]. 食品与发酵工业, 2020, 46(14): 204-210.
[15] 于怀智, 陈东杰, 姜沛宏, 张玉华, 郭风军, 张长峰. 近红外光谱对蒙阴黄桃硬度和可溶性固形物的在线检测[J]. 食品与发酵工业, 2020, 46(14): 216-221.
No Suggested Reading articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《食品与发酵工业》编辑部
地址:北京朝阳区酒仙桥中路24号院6号楼111室
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn