基于近红外光谱技术有监督模式识别的青皮产地溯源分析

1. 湖南农业大学食品科学技术学院, 湖南长沙 410128;
2. 湖南省农业科学院湖南省农产品加工研究所, 湖南长沙 410125;
3. 广东省粤北食药资源利用与保护重点实验室, 广东韶关 512005;
4. 湖南省产商品质量监督检验研究院, 湖南长沙 410007

作者简介:李跑(1989-),男,湖南省宁乡市人,湖南农业大学副教授,博士,主要研究方向为食品分析与化学计量学。E-mail:lipao@live.cn;

基金项目:2022年湖南省研究生科研创新项目(QL20220173)
湖南省自然科学基金项目(2023JJ30290)
中国博士后科学基金面上项目(2019M650187)
湖南省教育厅科学研究项目(21A0127)
国家自然科学基金项目(31601551)
中图分类号:TS218;O561.3

Traceability analysis ofPericarpium Citri Reticulatae Virideorigin based on near infrared spectroscopy technology and supervised pattern recognition

1. College of Food Science and Technology, Hunan Agricultural University, Changsha 410128, China;
2. Hunan Agricultural Product Processing Institute, Hunan Academy of Agricultural Sciences, Changsha 410125, China;
3. Guangdong Provincial Key Laboratory of Utilization and Conservation of Food and Medicinal Resources in Northern Region, Shaoguan 512005, China;
4. Hunan Provincial Institute of Quality Supervision and Inspection of Product, Changsha 410007, China
Received Date:2023-03-21
Accepted Date:2023-05-16

CLC number:TS218;O561.3

摘要:利用便携式近红外光谱仪采集不同产地(安徽、广东、四川)青皮外壁和内囊光谱数据,采用单一预处理和组合预处理方法消除光谱中的多种干扰,结合主成分分析(PCA)、簇类独立软模式分类法(SIMCA)及Fisher 线性判别分析(FLDA)等模式识别方法建立青皮产地溯源模型。结果表明,光谱预处理可以在一定程度上消除基线漂移、背景噪声和谱峰重叠干扰,但无法实现产地溯源。3种模式识别方法中,PCA无法实现青皮产地溯源;青皮外壁和内囊原始光谱的SIMCA模型获得的青皮产地溯源整体鉴别率分别为99.14 %和98.28 %;FLDA模型获得的整体鉴别率均为 99.57 %,优于SIMCA模型;经光谱预处理优化后的SIMCA和FLDA模型对青皮产地溯源的鉴别率均可达100 %,即便携式近红外光谱技术结合有监督模式识别方法可实现青皮产地溯源的无损分析,可为食药同源物质产地溯源拓展新途径。
- 青皮/
- 溯源分析/
- 近红外光谱技术/
- 有监督模式识别方法
Abstract:Spectral data of the outer wall and inner capsule of Pericarpium Citri Reticulatae Viridefrom different regions (Anhui, Guangdong, and Sichuan) were collected with portable near infrared spectrometer. Multiple interferences in the spectra were eliminated using single and combined pretreatment methods. Pattern recognition methods such as principal component analysis (PCA), cluster independent soft pattern classification (SIMCA) and Fisher linear discriminant analysis (FLDA) were used to establish traceability models of Pericarpium Citri Reticulatae Virideorigin. The results showed that spectral pretreatment could eliminate the interferences of baseline drift, background, and spectral peak overlap to a certain extent. However, the traceability analysis of the origin couldn't be achieved. Among the three pattern recognition methods, accurate traceability analysis of Pericarpium Citri Reticulatae Viridcouldn't be achieved with PCA method. The whole identification rate of SIMCA model with the outer wall and inner capsule original spectra were 99.14 % and 98.28 %, respectively. The whole identification rates of FLDA models were both 99.57 %, better than that of SIMCA models. The identification rates of SIMCA and FLDA models with appropriate spectral pretreatment were 100 %. Therefore, portable near infrared spectroscopy technology combined with the supervised pattern recognition methods can achieve non-destructive traceability analysis of Pericarpium Citri Reticulatae Virideorigin, expanding a new way for the traceability analysis of food and drug homologous substances origin.
- Pericarpium Citri Reticulatae Viride/
- traceability analysis/
- near infrared spectroscopy technology/
- supervised pattern recognition
1. [1]
  何民友,叶瑞平,段志文,等.青皮及其炮制品UPLC指纹图谱与多成分含量测定研究[J].中药材,2022,45(10):2418-2424.
2. [2]
  刘龙婵,王星宇,李林楠,等.青皮与陈皮化学成分及分析方法研究进展[J].中国中药杂志,2022,47(11):2866-2879.
3. [3]
  任桂林,柯刚,郑琴,等.介孔二氧化硅350FCP固化陈皮、青皮挥发油研究[J].中草药,2021,52(5):1323-1334.
4. [4]
  WANG Y,CUI W L,YANG C G,et al.Comparison of Geqingpi and Sihuaqingpi based on ultra-high-performance liquid chromatography-tandem mass spectrometry combined with multivariate statistics,network pharmacology analysis,and molecular docking[J].Journal of Separation Science,2022,45:4079-4098.
5. [5]
  余代鑫,郭盛,杨健,等.稳定同位素技术在中药材产地溯源中的应用与展望[J].中国中药杂志,2022,47(4):862-871.
6. [6]
  牛露露,刘磊,李瑶瑶,等.柑橘属同源药对青皮-枳壳的薄层色谱鉴别[J].中成药,2022,44(2):667-671.
7. [7]
  高薇,王秀,李见春,等.基于HPLC指纹图谱与多元统计分析的太平猴魁产地判别方法[J].轻工学报,2022,37(1):33-39.
8. [8]
  靳贝贝,裴香萍,梁惠珍.青皮药材的HPLC指纹图谱建立及聚类分析和主成分分析[J].中国药房,2018,29(24):3336-3339.
9. [9]
  KANG K S,OLIKAGU C,LEE T,et al.Sulfenyl chlorides:An alternative monomer feedstock from elemental sulfur for polymer synthesis[J].Journal of the American Chemical Society,2022,144:23044-23052.
10. [10]
  杨建云,田孟玉,裴梓烨,等.基于近红外光谱技术的初烤烟叶致香成分含量特性快速定量评价[J].轻工学报,2018,33(5):60-68.
11. [11]
  YUAN L B,MENG X R,XIN K H,et al.A comparative study on classification of edible vegetable oils by infrared,near infrared and fluorescence spectroscopy combined with chemometrics[J].Spectrochimica Acta Part A (Molecular and Biomolecular Spectroscopy),2023,288:122120.
12. [12]
  PHILLIPS V Z,CANOY R J,PAIK S H,et al.Functional near-infrared spectroscopy as a personalized digital healthcare tool for brain monitoring[J].Journal of Clinical Neurology (Seoul,Korea),2023,19(2):115-124.
13. [13]
  帖金鑫,何文苗,李石头,等.基于级联分类的复烤片烟产地预测方法研究[J].轻工学报,2022,37(4):94-99.
14. [14]
  OHASHI A,NISHIO T,SAITO A,et al.Baseline drift vector of multiple points on body surface using a near-infrared camera[J].Physical and Engineering Sciences in Medicine,2022,45(1):143-155.
15. [15]
  吴木兰,宋萧萧,崔武卫,等.基于近红外光谱技术对南阳豌豆产地鉴别研究[J].光谱学与光谱分析,2023,43(4):1095-1102.
16. [16]
  BIAN X H,WANG K Y,TAN E,et al.A selective ensemble preprocessing strategy for near-infrared spectral quantitative analysis of complex samples[J].Chemometrics and Intelligent Laboratory Systems,2020,197:103916.
17. [17]
  HAN L,SUN Y,WANG Y,et al.Ultra-high resolution near-infrared spectrum by wavelet packet transform revealing the hydrogen bond interactions[J].Spectrochimica Acta Part A (Molecular and Biomolecular Spectroscopy),2023,289:122233.
18. [18]
  WANG Y Q,LIU G M,HU L P,et al.Prediction of anthocyanidins content in purple Chinese cabbage based on visible/near infrared spectroscopy[J].Foods,2023,12(9):1922.
19. [19]
  HONG Y S,CHEN Y Y,CHEN S C,et al.Improving spectral estimation of soil inorganic carbon in urban and suburban areas by coupling continuous wavelet transform with geographical stratification[J].Geoderma,2023,430:116284.
20. [20]
  HAN X,TAN Z,HUANG Z X,et al.Nondestructive detection of tri-closan in antibacterial hand soaps using digitally labelled Raman spectroscopy[J].Analytical Methods,2017,9(24):3720-3726.
21. [21]
  涂蓉玲,王建伟.近红外光谱法青皮药材真伪鉴别研究[J].中国民族民间医药,2014,23(24):15-16.
1. [1]
  杨建云,田孟玉,裴梓烨,赵蔚,马骥,李俊谷,杨乾栩. 基于近红外光谱技术的初烤烟叶致香成分含量特性快速定量评价. 轻工学报, 2018, 33(5): 60-68.doi: 10.3969/j.issn.2096-1553.2018.05.008
2. [2]
  赵赫,郑安平,李银华,齐汝宾. 基于长光程近红外光声光谱的微量气体探测研究. 轻工学报, 2019, 34(6): 89-95.doi: 10.3969/j.issn.2096-1553.2019.06.012
3. [3]
  张卫正,张伟伟,张焕龙,陈启强,丁臣臣. 基于高光谱成像技术的甘蔗茎节识别与定位方法研究. 轻工学报, 2017, 32(5): 95-102.doi: 10.3969/j.issn.2096-1553.2017.5.013
4. [4]
  李小娇,马吉明,张向梅. 一种具有分类细化功能的垃圾语言识别方法. 轻工学报, 2014, 29(1): 94-97,108.doi: 10.3969/j.issn.2095-476X.2014.01.020
5. [5]
  朱亚昆,梅吉帆,郭文孟,苏子淇,李嘉康,徐大勇,堵劲松,李辉. 基于PPF投影算法和高光谱技术的卷烟牌号识别模型. 轻工学报, 2024, 0(0): -.
6. [6]
  曾庆培,刘琳,谢静雯,杨焕彬,刘晓丽,宋琳,杨锡洪,解万翠. 烤制鸡翅根加工过程中病原微生物的菌相分析及溯源. 轻工学报, 2021, 36(2): 10-16.doi: 10.12187/2021.02.002
7. [7]
  解相朋,杨录山. 基于智能优化型径向基神经网络的板形模式识别研究. 轻工学报, 2012, 27(3): 89-92.doi: 10.3969/j.issn.1004-1478.2012.03.024
8. [8]
  黄海波,全海燕,谢鹏. 一种融合模块2DPCA与PCA的人脸识别方法. 轻工学报, 2013, 28(6): 81-85.doi: 10.3969/j.issn.2095-476X.2013.06.019
9. [9]
  秦绪亮,吴青娥,韩振宇,郁杰. 基于不同小波基函数的多层小波变换掌纹识别方法研究. 轻工学报, 2011, 26(3): 29-32.doi: 10.3969/j.issn.1004-1478.2011.03.008
10. [10]
  马照瑞,栗娜,甘琤,李霞,朱训林. 采用动态阈值和随机梯度的带噪声混沌系统的识别方法. 轻工学报, 2014, 29(6): 92-94,102.doi: 10.3969/j.issn.2095-476X.2014.06.020
11. [11]
  张延强,李哲谦,王博涵. 基于小波子带融合的单训练样本掌纹识别方法. 轻工学报, 2017, 32(5): 88-94.doi: 10.3969/j.issn.2096-1553.2017.5.012
12. [12]
  米捷. 基于自适应反馈信道调制的多信道跳频通信系统异常跳变识别方法研究. 轻工学报, 2021, 36(4): 112-117.doi: 10.12187/2021.04.014
13. [13]
  何屹,杨本刚,尹嵩,陈实,尹晓东,周文忠,贾学伟,杨盼盼. 基于随机蛙跳筛选的初烤烟叶中β-胡萝卜素和叶黄素含量近红外模型的建立. 轻工学报, 2024, 39(2): 100-106.doi: 10.12187/2024.02.013
14. [14]
  杜秋,唐辉,孙军华,谭益升,吴梓仟,蒋立文,刘洋. 即食豆干加工过程中的细菌污染溯源. 轻工学报, 2024, 39(2): 28-35.doi: 10.12187/2024.02.004
15. [15]
  赵汉卿,王斌,陈瑶,唐章奉,方鑫,陈增萍,杨健,邓婷. 基于改进随机森林算法的薏苡仁产地溯源研究. 轻工学报, 2023, 38(6): 70-77.doi: 10.12187/2023.06.009
16. [16]
  蒋文,齐林. 一种基于指数降维的监督型稀疏保持典型相关分析算法. 轻工学报, 2015, 30(5-6): 93-97.doi: 10.3969/j.issn.2095-476X.2015.5/6.019
17. [17]
  宛宇,张春燕,朱锦翊,陈致,蒋新星,平安. 基于螺旋理论的多模式移动3-RSR并联机构奇异性分析. 轻工学报, 2020, 35(3): 88-98.doi: 10.12187/2020.03.011
18. [18]
  夏永泉,董向滢,王慧敏. 一种适应于远程红外监控的图像增强方法. 轻工学报, 2012, 27(6): 78-81.doi: 10.3969/j.issn.2095-476X.2012.06.021
19. [19]
  邹东尧,郑道理,李晨. RSSI曲线拟合的误差分析与分段方法. 轻工学报, 2014, 29(2): 62-66.doi: 10.3969/j.issn.2095-476X.2014.02.016
20. [20]
  魏甲欣,李琪,马飞,丁美宙,靳亚伟,王艺斌,许文武,王小明. 基于图像识别的烟丝结构检测及烟丝组分分析. 轻工学报, 2022, 37(3): 82-87.doi: 10.12187/2022.03.011

点击查看大图

计量

PDF下载量:8
文章访问数:1151
引证文献数:0

通讯作者:陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于近红外光谱技术有监督模式识别的青皮产地溯源分析

作者简介:李跑(1989-),男,湖南省宁乡市人,湖南农业大学副教授,博士,主要研究方向为食品分析与化学计量学。E-mail:lipao@live.cn;

Traceability analysis ofPericarpium Citri Reticulatae Virideorigin based on near infrared spectroscopy technology and supervised pattern recognition

计量

通讯作者:陈斌, bchen63@163.com

基于近红外光谱技术有监督模式识别的青皮产地溯源分析

作者简介:李跑(1989-),男,湖南省宁乡市人,湖南农业大学副教授,博士,主要研究方向为食品分析与化学计量学。E-mail:lipao@live.cn

English Abstract

Traceability analysis ofPericarpium Citri Reticulatae Virideorigin based on near infrared spectroscopy technology and supervised pattern recognition

目录

基于近红外光谱技术有监督模式识别的青皮产地溯源分析

作者简介:李跑(1989-),男,湖南省宁乡市人,湖南农业大学副教授,博士,主要研究方向为食品分析与化学计量学。E-mail:lipao@live.cn;

Traceability analysis ofPericarpium Citri Reticulatae Virideorigin based on near infrared spectroscopy technology and supervised pattern recognition

计量

文章相关

通讯作者:陈斌, bchen63@163.com

基于近红外光谱技术有监督模式识别的青皮产地溯源分析

作者简介:李跑(1989-),男,湖南省宁乡市人,湖南农业大学副教授,博士,主要研究方向为食品分析与化学计量学。E-mail:lipao@live.cn

English Abstract

Traceability analysis ofPericarpium Citri Reticulatae Virideorigin based on near infrared spectroscopy technology and supervised pattern recognition

目录