Food and Fermentation Industries >

2020 , Vol. 46 >Issue 23: 213 - 219

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.024847

Research on quantitative modeling method of maize composition based on near infrared spectrum fusion and deep learning

  • TAN Ailing ,
  • WANG Xiaosi ,
  • CHU Zhenyuan ,
  • ZHAO Yong
Expand
  • 1(School of Information and Science Engineering,Yanshan University,The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province,Qinhuangdao 066004,China);
    2(School of Electrical Engineering,Yanshan University,The Key Laboratory of Measurement Technology and Instrumentation of Hebei Province,Qinhuangdao 066004,China)

Received date: 2020-06-23

  Revised date: 2020-07-20

  Online published: 2020-12-30

Fold

Abstract

In order to explore the feasibility of spectral fusion combined with deep learning for quantitative detection of maize components,one-dimensional convolution neural network (1D-CNN) models were constructed for the original,first-order derivative,second-order derivative spectra and the first three types of serial fusion spectra of 80 maize samples,then quantitative regression models of four components of moisture,oil,protein and starch in maize samples were built.The results showed that the performance of the four component models of the 1D-CNN based on serial fusion spectra were all superior to the other three models based on a single spectrum.Compared with the traditional partial least squares and support vector machine regression,the performance of the quantitative modes established by this method is optimal.For the test set,the coefficients of determination and root mean square errors of the four component models were 0.956 and 0.211,0.972 and 0.118,0.982 and 0.239,0.949 and 0.428,respectively.The experimental results showed that the method of serial spectrum fusion combined with convolutional neural network can fully mine the information contained in the spectrum,thus to enhance the model prediction ability,which provides a new idea for the quantitative analysis of near infrared spectroscopy.

Key words： near infrared spectroscopy; maize components; deep learning; one-dimensional convolution neural network; spectrum fusion

Cite this article

TAN Ailing , WANG Xiaosi , CHU Zhenyuan , ZHAO Yong . Research on quantitative modeling method of maize composition based on near infrared spectrum fusion and deep learning[J]. Food and Fermentation Industries, 2020 , 46(23) : 213 -219 . DOI: 10.13995/j.cnki.11-1802/ts.024847

References

[1] 唐明霞,陈惠,顾拥建,等.18种玉米组分对其饮料产品颜色和稳定性的影响[J].食品科学,2014,35(3):76-79.
TANG M X,CHEN H,GU Y J,et al.Effect of major components of 18 kinds of corn on the color and stability of corn beverage products[J].Food Science,2014,35(3):76-79.
[2] SAMUEL P P,CHINNU T,MADAN K L.Multi-parameter analysis of corn using near-infrared reflectance spectroscopy and chemometrics[J].Materials Today:Proceedings,2015,2:949-953.
[3] 李宗朋,王健,宋全厚,等.近红外光谱技术在食品检测与质量控制中的应用[J].食品与发酵工业,2012,38(8):125-131.
LI Z P,WANG J,SONG Q H,et al.A review of application of near-infrared spectroscopy in food detection and quality control[J].Food and Fermentation Industries,2012,38(8):125-131.
[4] 郝勇,吴文辉,商庆园.饲料中粗脂肪和粗纤维含量的近红外光谱快速分析[J].光谱学与光谱分析,2020,40(1):215-220.
HAO Y,WU W H,SHANG Q Y.The Research on quantitative analysis of feed crude fat and corase Fi‐ber based on near infrared spectroscopy and variables selection methods[J].Spectroscopy and Spectral Analysis,2020,40(1):215-220.
[5] 刘攀颜,陈碧清,袁珊珊,等.近红外光谱法测定染色红花中常见染料的含量[J].中国中药杂志,2019,44(8):1 537-1 544.
LIU P Y,CHEN B Q,YUAN S S,et al.Determination of common dyes in dyed safflower by near infrared spectroscopy[J].China Journal of Chinese Materia Medica,2019,44(8):1 537-1 544.
[6] 褚小立,许育鹏,陆婉珍.用于近红外光谱分析的化学计量学方法研究与应用进展[J].分析化学,2008,5(10):702-709.
CHU X L,XU Y P,LU W Z.Research and application progress of chemometrics methods in near infrared spectroscopic analysis[J].Chinese Journal of Analytical Chemistry,2008,5(10):702-709.
[7] 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 J,GAO L,YE F Y,et al.Rapid detection of adulterated sweet potato starch noodle by near-infrared spectroscopy and support vector machine[J].Food and Fermentation Industries,2019,45(11):211-218.
[8] 陈永,郭红光,艾亚鹏.基于多尺度卷积神经网络的单幅图像去雾方法[J].光学学报,2019,39(10):141-150.
CHEN Y,GUO H G,AI Y P.Single image dehazing method based on multi-scale convolution neural network[J].Acta Optica Sinica,2019,39(10):141-150.
[9] 王蔚,胡婷婷,冯亚琴.基于深度学习的自然与表演语音情感识别[J].南京大学学报(自然科学版),2019,55(4):660-666.
WANG W,HU T T,FENG Y Q.Speech emotion recognition in nature and scripted state based on deep learning[J].Journal of Nanjing University (Natural Sciences),2019,55(4):660-666.
[10] IBTIHEL B L,LOBNA H,LOTFI B R.Hybrid deep neural network-based text representation model to improve microblog retrieval[J].Cybernetics and Systems,2020,51(2):115-139.
[11] GU J X,WANG Z H,KUEN J,et al.Recent advances in convolutional neural networks[J].Pattern Recognition:The Journal of the Pattern Recognition Society,2018,77:354-377.
[12] INCE T,KIRANYAZ S,EREN L,et al.Real-time motor fault detection by 1-D convolutional neural networks[J].IEEE Transactions on Industrial Electronics,2016,63(11):7 067-7 075.
[13] 赵勇,荣康,谈爱玲.基于一维卷积神经网络的雌激素粉末拉曼光谱定性分类[J].光谱学与光谱分析,2019,39(12):3 755-3 760.
ZHAO Y,RONG K,TAN A L.Qualitative analysis method for raman spectroscopy of estrogen based on one-dimensional convolutional neural network[J].Spectroscopy and Spectral Analysis,2019,39(12):3 755-3 760.
[14] 倪超,李振业,张雄,等.基于短波近红外高光谱和深度学习的籽棉地膜分选算法[J].农业机械学报,2019,50(12):1 000-1 298.
NI C,LI Z Y,ZHANG X,et al.Film sorting algorithm in seed cotton based on near-infrared hyperspectral image and deep learning[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(12):1 000-1 298.
[15] 袁培森,黎薇,任守纲,等.基于卷积神经网络的菊花花型和品种识别[J].农业工程学报,2018,34(5):152-158.
YUAN P S,LI W,REN S G,et al.Recognition for flower type and variety of chrysanthemum with convolutional neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2018,34(5):152-158.
[16] 鲁梦瑶,杨凯,宋鹏飞,等.基于卷积神经网络的烟叶近红外光谱分类建模方法研究[J].光谱学与光谱分析,2018,38(12):3 724-3 728.
LU M Y,YANG K,SONG P F,et al.The study of Ccassification modeling method for near infrared spectroscopy of tobacco leaves based on convolution neural network[J].Spectroscopy and Spectral Analysis,2018,38(12):3 724-37 28.
[17] YANG W,YANG C,HAO Z Y,et al.Diagnosis of plant cold damage based on hyperspectral imaging and convolutional neural network[J].IEEE Access,2019,7:118 239-118 248.
[18] 田永超,张娟娟,姚霞,等.基于近红外光声光谱的土壤有机质含量定量建模方法[J].农业工程学报,2012,28(1):145-152.
TIAN Y C,ZHANG J J,YAO X,et al.Quantitative modeling method of soil organic matter content based on near-infrared photoacoustic spectroscopy[J].Transactions of the Chinese Society of Agricultural Engineering,2012,28(1):145-152.
[19] CHEN Y Y,WANG Z B.End-to-end quantitative analysis modeling of near-infrared spectroscopy based on convolutional neural network[J].Journal of Chemometrics,2019,33(5):3 122.
[20] 江艳艳,粟桂娇,马丽,等.多阶导数紫外光谱法快速测定生物转化液中的肉桂醇、肉桂醛和肉桂酸[J].食品科学,2020,41(10):180-184.
JIANG Y Y,LI G J,MA L,et al.Rapid determination of cinnamyl alcohol,cinnamaldehyde and cinnamic acid in bioconversion products by multiorder derivative ultraviolet spectrometry[J].Food Science,2020,41(10):180-184.
[21] The NIRS data set of corn.http://www.eigenvector.com/data/Corn/index.html.Retrieved 17-03-2014.
[22] 周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1 229-1 251.
ZHOU F Y,JIN L P,DONG J.Review of convolutional neural network[J].Chinese Journal of Computers,2017,40(6):1 229-1 251.
[23] 盛晓慧,李宗朋,李子文,等.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.
SHENG X H,LI Z P,LI Z W,et al.Quantification of fruit juice content in fruity beer by near-infrared spectroscopy[J].Food and Fermentation Industries,2020,46(4):247-252.
Options
Outlines

/

〈 〉

Powered by Beijing Magtech Co. Ltd,.