食品与发酵工业 >

2022 , Vol. 48 >Issue 20: 252 - 259

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.030083

分析与检测

基于可见/近红外光谱的蓝莓新鲜度快速评价

  • 曾明飞 ,
  • 朱玉杰 ,
  • 冯国红 ,
  • 朱金艳 ,
  • 刘思岐
展开
  • (东北林业大学 工程技术学院,黑龙江 哈尔滨,150040)
硕士研究生(朱玉杰教授和冯国红副教授为共同通信作者,E-mail:zhuyujie004@126.com;fgh_1980@126.com)

收稿日期: 2021-11-15

  修回日期: 2021-12-20

  网络出版日期: 2022-11-18

基金资助

中央高校基本科研业务费专项资金项目(2572020BL01);黑龙江省自然科学基金项目(LH2020C050)

收起

Rapid evaluation of blueberry freshness based on visible/near-infrared spectroscopy

  • 曾明飞 ,
  • 朱玉杰 ,
  • 冯国红 ,
  • 朱金艳 ,
  • 刘思岐
Expand
  • (College of Engineering and Technology, Northeast Forestry University, Harbin 150040, China)

Received date: 2021-11-15

  Revised date: 2021-12-20

  Online published: 2022-11-18

Fold

摘要

该研究针对传统人工感官评价方法的不足,基于可见/近红外光谱技术结合支持向量机(support vector machine,SVM)和随机森林(random forest,RF)建立了2种新鲜度快速评价模型,以期为蓝莓新鲜度的快速准确评价提供参考。以10 ℃恒温贮藏绿宝石蓝莓为研究对象,利用可见/近红外光谱仪采集其不同贮藏天数样品的光谱信息,综合考虑贮藏时间、外观、质量损失率、硬度、可溶性固形物和维生素C含量这6个反映蓝莓新鲜度的理化指标,计算新鲜度综合得分,将不同贮藏期的蓝莓样品划分为新鲜、次新鲜和不新鲜3个类别。光谱数据应用Savitzky-Golay(S-G)卷积平滑预处理,再采用主成分分析提取光谱特征信息。为使最佳主成分选取更合理,在使用粒子群算法寻优SVM参数时,对主成分个数在[1,20]范围进行了测试,结合5折交叉检验分类准确率最佳值,确定最佳主成分个数为5。以前5个主成分得分为输入变量,新鲜度类别为输出量,基于SVM和RF建立2种新鲜度快速评价模型。结果显示,SVM模型训练集和测试集识别准确率分别为97.78%和88%,RF模型训练集和测试集识别准确率分别为100%和84%,SVM模型优于RF模型。研究表明可见/近红外光谱技术结合主成分分析和SVM可用于蓝莓新鲜度的快速评价。

关键词： 可见/近红外光谱; 蓝莓; 新鲜度; 主成分分析; 支持向量机; 随机森林

本文引用格式

曾明飞 , 朱玉杰 , 冯国红 , 朱金艳 , 刘思岐 . 基于可见/近红外光谱的蓝莓新鲜度快速评价[J]. 食品与发酵工业, 2022 , 48(20) : 252 -259 . DOI: 10.13995/j.cnki.11-1802/ts.030083

Abstract

Aiming at the deficiency of the traditional artificial sensory evaluation method, this paper established two rapid evaluation models of blueberry freshness by combining visible/near-infrared spectroscopy technology with a support vector machine (SVM) and random forest (RF). Turquoise blueberries stored at 10 ℃ for different days were detected by visible/near-infrared spectrometer. Six physical and chemical indexes including storage days, appearance and quality loss rate, hardness, soluble solid and vitamin C, were comprehensively considered to calculate the comprehensive score of freshness. The spectral data were preprocessed by S-G convolution smoothing, and then the spectral characteristic information was extracted by principal component analysis. To make the selection of optimal principal components more reasonable, a particle swarm optimization algorithm was used to optimize the parameters of SVM, and the number of principal components was tested within the range of [1,20]. Combined with the optimal classification accuracy value under the five-fold cross test, the optimal number of principal components was determined to be 5. The previous 5 principal component scores were input variables, and the freshness category was output quantity. Two kinds of rapid freshness evaluation models were established based on SVM and RF. The results showed that the recognition accuracy of the training set and a test set of the SVM model was 97.78% and 88% respectively, while for the RF model they were 100% and 84% respectively. These results showed that visible/near-infrared spectroscopy combined with principal component analysis and SVM could be used for the rapid evaluation of blueberry freshness.

Key words： visible/near-infrared spectroscopy; blueberry; freshness; principal component analysis; support vector machine; random forest

参考文献

[1] 司琦, 胡文忠, 姜爱丽, 等.动态气调贮藏对蓝莓采后生理代谢品质的影响[J].包装工程, 2017, 38(17):13-18.
SI Q, HU W Z, JIANG A L, et al.Effects of dynamic modified atmosphere storage on quality of physiological metabolism of the postharvest blueberry[J].Packaging Engineering, 2017, 38(17):13-18.
[2] SHEN J G, QIAO W M, CHEN H Z, et al.Application of visible/near infrared spectrometers to quickly detect the nitrogen, phosphorus, and potassium content of chemical fertilizers[J].Applied Sciences, 2021, 11(11):5 103.
[3] 高升, 王巧华, 施行, 等.便携式红提葡萄多品质可见/近红外检测仪设计与试验[J].农业机械学报, 2021, 52(2):308-319.
GAO S, WANG Q H, SHI H, et al.Design and test of portable red globe grape extraction multi-quality visible/near infrared detector[J].Transactions of the Chinese Society for Agricultural Machinery,2021,52(2):308-319.
[4] 薛璐, 刘小路, 鲁晓翔, 等.近红外漫反射无损检测蓝莓硬度的研究[J].浙江农业学报, 2015, 27(9):1 646-1 651.
XUE L, LIU X L, LU X X, et al.Non-destructive detection of blueberry hardness based on near-infrared diffused spectroscope[J].Acta Agriculturae Zhejiangensis,2015,27(9):1 646-1 651.
[5] 王姗姗, 孙红男, 陈健, 等.基于近红外光谱技术检测蓝莓可溶性固形物含量[J].食品工业科技, 2012, 33(1):340-341;369.
WANG S S, SUN H N, CHEN J, et al.Determination of soluble solids content of blueberries with near infrared spectroscopy[J].Science and Technology of Food Industry,2012,33(1):340-341;369.
[6] 刘小路, 薛璐, 鲁晓翔, 等.近红外光谱技术快速无损检测蓝莓总黄酮、花青素的研究[J].食品工业科技, 2015, 36(16):58-61;67.
LIU X L, XUE L, LU X X,et al.Fast non-destructive testing of total flavonoids and anthocyanins in blueberries by near-infrared spectroscope[J].Science and Technology of Food Industry,2015,36(16):58-61;67.
[7] 王姗姗, 李路宁, 孙红男, 等.基于近红外光谱技术构建蓝莓总酚含量的模型[J].光谱实验室, 2011, 28(6):3 169-3 174.
WANG S S, LI L N, SUN H N, et al.Content model establishment of total polyphenols in blueberries by near infrared spectroscopy[J].Chinese Journal of Spectroscopy Laboratory,2011,28(6):3 169-3 174.
[8] 张凡, 姜鑫, 张存存, 等.近红外光谱结合灰色关联度分析快速综合评价猪肉新鲜度[J].河北农业大学学报, 2020, 43(1):89-95.
ZHANG F, JIANG X, ZHANG C C, et al.Rapid and comprehensive evaluation of pork freshness using near infrared spectroscopy combined with grey correlation analysis[J].Journal of Hebei Agricultural University,2020,43(1):89-95.
[9] 史策, 孙立涛, 钱建平, 等.可见/近红外技术与感官评价信息融合预测冷藏条件下罗非鱼TVB-N的研究[J].食品工业科技, 2017, 38(21):268-273.
SHI C, SUN L T, QIAN J P, et al.TVB-N prediction of tilapia with scales by information fusion of near infrared spectrum technology and sensory evaluation during chilled storage[J].Science and Technology of Food Industry,2017,38(21):268-273.
[10] DONG X G, ZHANG B B, DONG J, et al.Egg freshness prediction using a comprehensive analysis based on visible near infrared spectroscopy[J].Spectroscopy Letters, 2020, 53(7):512-522.
[11] 李昆. 基于近红外光谱的果蔬新鲜度分析研究[D].成都:电子科技大学, 2019.
LI K.Freshness analysis and research of fruits based on near infrared spectroscopy[D].Chengdu:University of Electronic Science and Technology of China, 2019.
[12] 孙红, 梁媛媛, 田男, 等.鲜切果品新鲜度可见/近红外快速检测装置设计与实验[J].农业机械学报, 2019, 50(S1):393-398.
SUN H, LIANG Y Y, TIAN N, et al.Design of freshness detection device for fresh-cut fruit using visible/near-infrared spectroscopy[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(S1):393-398.
[13] 魏文平, 华璐云, 万金庆, 等.蓝莓冰温贮藏的实验研究[J].食品工业科技, 2012, 33(13):346-348.
WEI W P, HUA L Y, WAN J Q, et al.Study on ice-temperature preservation of blueberry[J].Science and Technology of Food Industry,2012,33(13):346-348.
[14] 陈杭君, 王翠红, 郜海燕, 等.不同包装方法对蓝莓采后贮藏品质和抗氧化活性的影响[J].中国农业科学, 2013, 46(6):1 230-1 236.
CHEN H J, WANG C H, GAO H Y, et al.Effect of packaging on the postharvest quality and the antioxidant activity of blueberry[J].Scientia Agricultura Sinica,2013,46(6):1 230-1 236.
[15] 谢忠红, 徐焕良, 黄秋桂, 等.基于高光谱图像和深度学习的菠菜新鲜度检测[J].农业工程学报, 2019, 35(13):277-284.
XIE Z H, XU H L, HUANG Q G, et al.Spinach freshness detection based on hyperspectral image and deep learning method[J].Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(13):277-284.
[16] 黄绵佳, 吴岚芳.热带园艺产品采后实验原理与技术[M].北京:中国林业出版社, 2012:172-174.
HUANG M J, WU L F.Postharvest Experimental Principle and Technology of Tropical Horticultural Products[M].Beijing:China Forestry Publishing House, 2012:172-174.
[17] 李洋, 张茜, 陈业莉, 等.贮运过程中振动损伤对蓝莓品质的影响[J].林业科学, 2020, 56(9):40-50.
LI Y, ZHANG X, CHEN Y L, et al.Effect of vibration damage on blueberry quality during storage and transportation[J].Scientia Silvae Sinicae,2020,56(9):40-50.
[18] 许晴晴, 陈杭君, 郜海燕, 等.真空冷冻和热风干燥对蓝莓品质的影响[J].食品科学, 2014, 35(5):64-68.
XU Q Q, CHEN H J, GAO H Y, et al.Effects of vacuum freeze-drying and hot-air drying on the quality of blueberry fruits[J].Food Science,2014,35(5):64-68.
[19] HERRERA-HERNÁNDEZ M G, GUEVARA-LARA F, REYNOSO-CAMACHO R, et al.Effects of maturity stage and storage on cactus berry (Myrtillocactus geometrizans) phenolics, vitamin C, betalains and their antioxidant properties[J].Food Chemistry, 2011, 129(4):1 744-1 750.
[20] 王培. 基于高光谱和图像处理技术的圆叶菠菜新鲜度检测[D].南京:南京农业大学, 2017.
WANG P.Freshness detection of spinach based on hyperspectral and imaging procsess technology[D].Nanjing:Nanjing Agricultural University,2017.
[21] 郑秀艳, 黄道梅, 孟繁博, 等.基于电子鼻技术的蓝莓果实品质变化研究[J].食品安全质量检测学报, 2016, 7(9):3 642-3 649.
ZHENG X Y, HUANG D M, MENG F B, et al.Quality changes analysis of blueberry fruits based on the electronic nose technology[J].Journal of Food Safety & Quality,2016,7(9):3 642-3 649.
[22] 张珏, 田海清, 张丽娜, 等.高光谱成像技术对羊肉新鲜度的无损检测[J].食品与发酵工业, 2020, 46(12):237-243.
ZHANG J, TIAN H Q, ZHANG L N, et al.Non-destructive detection of lamb freshness with hyperspectral imaging technology[J].Food and Fermentation Industries,2020,46(12):237-243.
[23] LEE H, KIM M S, LEE W H, et al.Determination of the total volatile basic nitrogen (TVB-N) content in pork meat using hyperspectral fluorescence imaging[J].Sensors & Actuators B:Chemical, 2018, 259:532-539.
[24] 王凡, 李永玉, 彭彦昆, 等.基于漫透射光谱技术的番茄可溶性固形物及总糖含量的无损检测[J].光谱学与光谱分析, 2016, 36(10):3 185-3 189.
WANG F, LI Y Y, PENG Y K, et al.Determination of tomato's SSC and TS based on diffuse transmittance spectroscopy[J].Spectroscopy and Spectral Analysis, 2016,36(10):3 185-3 189.
Options
文章导航

/

〈 〉

技术支持：北京玛格泰克科技发展有限公司