食品与发酵工业 >

2023 , Vol. 49 >Issue 2: 271 - 279

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.033368

分析与检测

间隔影响分析波长选择算法在近红外光谱鉴别贝类毒素中的应用

  • 姜微 ,
  • 刘瑶 ,
  • 刘忠艳 ,
  • 曾绍庚 ,
  • 熊建芳 ,
  • 乔付
展开
  • 1(岭南师范学院 计算机与智能教育学院,广东 湛江,524048)
    2(岭南师范学院 电子与电气工程学院,广东 湛江,524048)
第一作者：博士研究生,讲师(通信作者,E-mail:jwlingnan@163.com)

收稿日期: 2022-08-19

  修回日期: 2022-10-09

  网络出版日期: 2023-02-15

基金资助

国家自然科学基金(62005109);广东省基础与应用基础研究基金(2020A1515011368;2021A1515012440);岭南师范学院人才专项(ZL2049);广东省教育科学规划课题(2022GXJK256);2022年度岭南师范学院科研创新团队项目(XJ2022000501);岭南师范学院红树林研究院开放项目(PYXM04)

收起

Application of margin influence analysis wavelength selection algorithm in the identification of shellfish toxins by near infrared spectroscopy

  • JIANG Wei ,
  • LIU Yao ,
  • LIU Zhongyan ,
  • ZENG Shaogeng ,
  • XIONG Jianfang ,
  • QIAO Fu
Expand
  • 1(School of Computer Science and Intelligence Education, Lingnan Normal University, Zhanjiang 524048, China)
    2(School of Electronic and Electrical Engineering, Lingnan Normal University, Zhanjiang 524048, China)

Received date: 2022-08-19

  Revised date: 2022-10-09

  Online published: 2023-02-15

Fold

摘要

该文采用近红外光谱技术与化学计量学方法结合实现贝类毒素无损鉴别。该研究以新鲜翡翠贻贝为研究对象,使用近红外光谱仪采集健康贻贝和感染腹泻性毒素贻贝的反射光谱数据,利用Savitzky-Golay卷积平滑求导结合标准正态变量变换光谱预处理方式消除光谱中的干扰因素,采用间隔影响分析(margin influence analysis,MIA)结合连续投影算法(successive projections algorithm,SPA)对数据进行降维处理,应用偏最小二乘线性判别分析(partial least squares linear discriminant analysis,PLS-LDA)方法构建贝类毒素鉴别模型,并与支持向量机和随机森林分析模型进行比较。结果表明,采用MIA-SPA-PLS-LDA方法,可实现贝类毒素的100%鉴别。为此,利用MIA-SPA-PLS-LDA方法可建立准确的贝类毒素鉴别模型,为贝类毒素的快速鉴别提供了新途径,也为后续各种贝类水产品的毒素鉴别分析提供了参考。

关键词： 近红外光谱; 翡翠贻贝; 间隔影响分析; 腹泻性贝类毒素; 偏最小二乘线性判别分析

本文引用格式

姜微 , 刘瑶 , 刘忠艳 , 曾绍庚 , 熊建芳 , 乔付 . 间隔影响分析波长选择算法在近红外光谱鉴别贝类毒素中的应用[J]. 食品与发酵工业, 2023 , 49(2) : 271 -279 . DOI: 10.13995/j.cnki.11-1802/ts.033368

Abstract

The consumption of mussels contaminated with diarrheal shellfish poisons can cause adverse effects on human health. It is necessary to identify mussels contaminated with poisons. To explore a new method for the identification of shellfish poisons, in this paper, the nondestructive identification of shellfish poisons was realized by combining near-infrared spectroscopy and chemometrics. Taking the fresh mussels as the research object, the near-infrared spectrometer was used to collect the reflection spectrum data of healthy mussels and mussels contaminated with diarrhea shellfish poisons. The spectral preprocessing method combining Savitzky-Golay convolution smooth derivation and standard normal variable transformation was used to eliminate the interference factors in the spectrum. Margin influence analysis (MIA) combined with succession projections algorithm (SPA) was used to reduce the dimension of the data. The identification model of diarrhea shellfish poisons was constructed by the partial least squares linear discriminant analysis (PLS-LDA) method and compared with the identification models by support vector machine and random forest. Results showed that using the MIA-SPA-PLS-LDA method, 100% identification of shellfish toxins could be achieved. Results showed that the MIA-SPA-PLS-LDA method could make the identification accuracy of diarrhea shellfish poisons reach 100%. Therefore, the MIA-SPA-PLS-LDA method can be used to establish an accurate identification model of diarrhea shellfish poisons, which provides a new way for the rapid identification of diarrhea shellfish poisons, and also provides a reference for the subsequent identification and analysis of toxins in various shellfish products.

Key words： near-infrared spectroscopy; mussels; margin influence analysis; diarrheal shellfish poisons; partial least squares linear discriminant analysis

参考文献

[1] YANG L, SINGH A, LANKFORD S K, et al.A rapid method for the detection of diarrhetic shellfish toxins and azaspiracid shellfish toxins in washington state shellfish by liquid chromatography tandem mass spectrometry[J].Journal of AOAC International,2020,103(3):792-799.
[2] WANG X Y, BOUZEMBRAK Y, HANS J P M, et al.Bayesian networks modeling of diarrhetic shellfish poisoning in Mytilus edulis harvested in Bantry Bay,Ireland[J].Harmful Algae,2022,112:102171.
[3] 宿志伟,赵峰,刘远平,等.固相吸附毒素跟踪技术监测牡蛎养殖区中腹泻性贝毒[J].渔业科学进展, 2016,37(6):144-150.
SU Z W, ZHAO F, LIU Y P, et al.Monitoring of diarhettic shellfish poisons in aquatic environment by solid phase adsorbent toxin tracking technology[J].Progress in Fishery Sciences,2016,37(6):144-150.
[4] CORRIERE M, SOLIÑO L, COSTA P R.Effects of the marine biotoxins okadaic acid and dinophysistoxins on fish[J].Journal of Marine Science and Engineering,2021,9(3):293.
[5] JIMÉNEZ-CÁRCAMO D, GARCÍA C, CONTRERAS H R.Toxins of okadaic acid-group increase malignant properties in cells of colon cancer[J].Toxins,2020,12(3):179.
[6] 彭志兰, 罗海军, 王维洁, 等. 舟山海域麻痹性贝类毒素污染情况及其2种检测方法比较[J].食品安全质量检测学报, 2017, 8(4):1 436-1440.
PENG Z L, LUO H J, WANG W J, et al.Investigation of paralytic shellfish poison in waters of Zhoushan and comparison of 2 detection methods[J].Journal of Food Safety & Quality, 2017, 8(4):1 436-1 440.
[7] 胡雪莲,俞漪,曲勤凤,等.腹泻性贝类毒素(DSP)的两种快速检测方法比较[J].食品研究与开发,2012,33(12):127-130.
HU X L, YU Y, QU Q F, et al.The comparison of two screening detecting method of diarrhetic shellfish poisoning(DSP)[J].Food Research and Development,2012,33(12):127-130.
[8] 宿志伟, 赵峰, 姜雪, 等.桑沟湾养殖牡蛎中贝类毒素监测及预警[J].食品科学, 2017, 38(6):303-309.
SU Z W, ZHAO F, JIANG X, et al.Monitoring and early warning of shellfish toxins in oyster cultured in sanggou bay[J].Food Science,2017,38(6):303-309.
[9] 孟庆龙, 尚静, 黄人帅, 等.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.
MENG Q L, SHANG J,HUANG R S, et al. Nondestructive detection of soluble solids content in apple by visible-near infrared spectroscopy[J].Food and Fermentation Industries, 2020, 46(19):205-209.
[10] 褚小立,史云颖,陈瀑,等.近五年我国近红外光谱分析技术研究与应用进展[J].分析测试学报.2019,38(5):603-611.
CHU X L, SHI Y Y, CHEN P, et al.Research and application progresses of near infrared spectroscopy analytical technique in china in past five years[J].Journal of Instrumental Analysis,2019,38(5):603-611.
[11] 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.
[12] 张欣欣,李尚科,李跑,等.近红外光谱的不同产地柑橘无损鉴别方法[J].光谱学与光谱分析,2021,41(12):3 695-3 700.
ZHANG X X, LI S K, LI P, et al.A nondestructive identification method of producing regions of citrus based on near infrared spectroscopy[J].Spectroscopy and Spectral Analysis,2021,41(12):3 695-3 700.
[13] 袁瑞瑞,刘贵珊,何建国,等.可见近红外高光谱成像对灵武长枣定量损伤等级判别[J].光谱学与光谱分析,2021,41(4):1 182-1 187.
YUNA R R, LIU G S, HE J G, et al.Quantitative damage identification of lingwu long jujube based on visible near-infrared hyperspectral imaging[J].Spectroscopy and Spectral Analysis,2021,41(4):1 182-1 187.
[14] 张强,刘成海,孙井坤,等.基于支持向量机的稻谷黄曲霉毒素B1近红外无损检测[J].东北农业大学学报.2015,46(5):84-88.
ZHANG Q, LIU C H, SUN J K, et al.Near-infrared spectroscopy nondestructive determination of aflatoxin B1 in paddy rice based on support vector machine regression[J].Journal of Northeast Agricultural University,2015,46(5):84-88.
[15] 黄冠明,郭香,祁剑飞,等.葡萄牙牡蛎(Crassostrea angulata)六种化学成分近红外定量模型的建立[J].光谱学与光谱分析,2020,40(5):1 509-1 513.
HUANG G M, GUO X, QI J F, et al.Establishment of quantitative model for six chemical compositions in Crassostrea angulata by near infrared spectroscopy[J].Spectroscopy and Spectral Analysis, 2020,40(5):1 509-1 513.
[16] LIU Y, XU L L, ZENG S G, et al.Rapid detection of mussels contaminated by heavy metals using near-infrared reflectance spectroscopy and a constrained difference extreme learning machine[J].Spectrochinica Acta Part A:Molecular and Biomolecular Spectroscopy,2022,269:120776.
[17] 刘忠艳, 刘瑶, 乔付, 等.基于近红外光谱和多层感知机的贻贝中腹泻性贝毒快速无损检测[J/OL].食品与发酵工业,2022.https://doi.org/10.13995/j.cnki.11-1802/ts.032253.
LIU Z Y, LIU Y, QIAO F, et al.Rapid non-destructive detection of diarrheal shellfish poison in mussels based on near-infrared spectroscopy and multi-layer perceptron[J/OL].Food and Fermentation Industries,2022.https://doi.org/10.13995/j.cnki.11-1802/ts.032253.
[18] 何鸿举, 王魏, 王洋洋, 等. 基于近红外高光谱技术快速检测冷鲜猪肉酸价[J].食品与发酵工业, 2020, 46(10):264-270.
HE H J, WANG W, WANG Y Y, et al.NIR hyperspectral imaging technology for rapid detection of acid value in fresh chilled pork[J].Food and Fermentation Industries, 2020, 46(10):264-270.
[19] LI H D,LIANG Y Z,XU Q S,et al.Recipe for uncovering predictive genes using support vector machines based on model population analysis[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2011,8(6):1 633-1 641.
[20] MANN H.B,WHITNEY D R.On a test of whether one of two random variables is stochastically larger than the other[J].The Annals of Mathematical Statistics, 1947, 18(1):50-60.
[21] 楚秉泉,赵艳茹,何勇.基于近红外高光谱技术和特征波谱分析方法的竹类判别研究[J].光谱学与光谱分析,2017,37(6):1 718-1 722.
CHU B Q, ZHAO Y R, HE Y.Discriminant analysis of bamboo leaf types with nir coupled with characteristic wavelengths[J].Spectroscopy and Spectral Analysis,2017,37(6):1 718-1 722.
[22] 白宗秀,朱荣光,王世昌,等.高光谱图像结合特征变量筛选定量检测羊肉中狐狸肉掺假[J].农业工程学报,2021,37(17):276-284.
BAI Z X, ZHU R G, WANG S C, et al.Quantitative detection of fox meat adulteration in mutton by hyper spectral imaging combined with characteristic variables screening[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE), 2021, 37(17):276-284.
[23] MAMANI-LINARES L W, GALLO C, ALOMAR D.Identification of cattle, llama and horse meat by near infrared reflectance or transflectance spectroscopy[J].Meat Science,2012,90(2):378-385.
[24] TUNCER F D, DOGU D, AKDENIZ E.Efficiency of preprocessing methods for discrimination of anatomically similar pine species by NIR spectroscopy[J].Wood Material Science & Engineering,2021:1-10.
[25] LIU Y, QIAO F, XU L L, et al.Fast detection of diarrhetic shellfish poisoning toxins in mussels using nir spectroscopy and improved twin support vector machines[J].Frontiers in Marine Science,2022,9:907378.
Options
文章导航

/

〈 〉

技术支持：北京玛格泰克科技发展有限公司