基于改进随机森林算法的薏苡仁产地溯源研究

1. 中南林业科技大学理学院/应用化学研究所, 湖南长沙 410004;
2. 湖南工业大学生命科学与化学学院, 湖南株洲 412007;
3. 湖南大学化学化工学院/化学生物传感与计量学国家重点实验室, 湖南长沙 410082;
4. 中国中医科学院道地药材国家重点实验室培育基地国家中药资源中心, 北京 100700

作者简介:赵汉卿(1997-),男,山东省东营市人,中南林业科技大学硕士研究生,主要研究方向为多种模式识别方法下中药产地的溯源。E-mail:hanqing4126@126.com;

基金项目:湖南省高新技术产业科技创新引领计划项目（科技攻关类）（2020SK2029）；湖南省教育厅科研优秀青年项目（22B0579）
中图分类号:TS202.1

Research on geographical origin traceability of Coix seed based on a modified random forest algorithm

1. Institute of Applied Chemistry/School of Science, Central South University of Forestry and Technology, Changsha 410004, China;
2. College of Life Sciences and Chemistry, Hunan University of Technology, Zhuzhou 412007, China;
3. State Key Laboratory of Chemo/Biosensing and Chemometrics/College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China;
4. National Resource Center for Chinese Materia Medica, China Academy of Chinese Medical Sciences, State Key Laboratory Breeding Base of Dao-di Herbs, Beijng 100700, China
Received Date:2023-05-04
Accepted Date:2023-06-12

CLC number:TS202.1

摘要:以9个产地的薏苡仁为研究对象，通过将激发-发射矩阵（EEM）荧光光谱与改进的随机森林算法结合以实现薏苡仁产地的溯源分析。其中，随机森林算法的改进主要包括两方面：一是通过主成分分析（PCA）方法降低EEM荧光光谱的维度；二是利用网格筛选法找出PCA降维过程中最优保留主成分数及判别模型超参数。结果表明：基于薏苡仁的EEM荧光光谱数据构建的改进随机森林模型（加入标准差标准化和PCA降维模块）可以对9个产地薏苡仁样本进行准确预测，最佳模型由100棵最大深度为3、叶节点最小样本数为1个的决策树结合16个主成分数（PCs）构建，其对验证集和测试集（共108个样品）的准确度均为100%，优于偏最小二乘法构建的PLS-DA模型（96%）。
- 薏苡仁/
- 随机森林算法/
- 激发-发射矩阵荧光光谱/
- 产地溯源
Abstract:Coix seeds from 9 different origins were taken as the research object. An attempt was made to achieve geographical origin traceability of Coix seeds through the combination of excitation-emission matrix (EEM) fluorescence spectroscopy with improved random forest algorithm. The improvements to the random forest algorithm mainly include two aspects, firstly, principal component analysis (PCA) was adopted to reduce the dimension of EEM fluorescent data; secondly, a grid search method was used to identify the optimal number of principal components(PCs) to retain and the hyperparameters of the discriminant model during the PCA dimension reduction process. The results showed that an improved random forest model, incorporating standard deviation normalization and PCA dimension reduction modules, based on Coix seeds EEM fluorescence spectroscopy data, accurately predicted the geographical origin of Coix seed samples from 9 different areas. The optimal model was constructed by combining 100 decision trees with a maximum depth of 3 and a minimum sample size of 1 at the leaf node, using 16 principal components (PCs). This model achieved 100% prediction accuracy for both the validation and test sets, which consisted of a total of 108 samples, outperforming the PLS-DA model constructed by the partial least squares method (96% prediction accuracy).
- Coix seed/
- random forest algorithm/
- excitation-emission matrix fluorescence spectroscopy/
- origin traceability
1. [1]
  刘星, 王正武.薏仁的化学成分及其应用研究[J].食品与药品, 2014, 16(2):129-133.
2. [2]
  陆雅丽, 王明力, 闫岩.薏苡仁综合开发利用[J].中国食物与营养, 2013, 19(4):64-66.
3. [3]
  LIN L Y, LIAO Y L, CHEN M H, et al.Molecular action mechanism of Coixol from soft-shelled adlay on tyrosinase:The future of cosmetics[J].Molecules, 2022, 27(14):4626.
4. [4]
  ZENG Y W, YANG J Z, CHEN J, et al.Actional mechanisms of active ingredients in functional food adlay for human health[J].Molecules, 2022, 27(15):4808.
5. [5]
  CHIANG Y F, CHUNG C P, LIN J H, et al.Adlay seed (Coix lacryma-jobi L.var.ma-yuen Stapf.) ethanolic extract fractions and subfractions induce cell cycle arrest and apoptosis in human breast and cervical cancer cell lines[J].Molecules, 2022, 27(13):3984.
6. [6]
  ZHANG W, JIA X Z, XU Y H, et al.Effects of Coix seed extract, bifidobacterium BPL1, and their combination on the glycolipid metabolism in obese mice[J].Frontiers in Nutrition, 2022, 9(39):423-423.
7. [7]
  ZHOU Q Y, YU R Y, LIU T L, et al.Coix seed diet ameliorates immune function disorders in experimental colitis mice[J].Nutrients, 2022, 14(1):123.
8. [8]
  赵杨景, 杨峻山, 张聿梅, 等.不同产地薏苡的经济性状和质量的比较研究[J].中国中药杂志, 2002, 27(9):694-696.
9. [9]
  LIU X, MAO D Z, WANG Z W, et al.Rapid identification of Coix seed varieties by near infrared spectroscopy[J].Spectroscopy and Spectral Analysis, 2014, 34(5):1259-1263.
10. [10]
  刘星, 范楷, 杨俊花, 等.基于主要营养成分含量的大小颗粒薏仁米判别[J].食品与机械, 2019, 35(2):77-81
  , 133.
11. [11]
  郑利, 陈丹, 范世明, 等.不同产地薏苡仁的鉴别及含量测定[J].福建中医药大学学报, 2012, 22(5):52-54.
12. [12]
  TANG W W, WANG J C, LI W, et al.Changes in triacylglycerols content and quality control implications of Coix seeds during processing and storage[J].Foods, 2022, 11(16):2462.
13. [13]
  CHANG Y Y, WU H L, WANG T, et al.Geographical origin traceability of traditional Chinese medicine Atractylodes macrocephala Koidz.by using multi-way fluorescence fingerprint and chemometric methods[J].Spectrochimica Acta Part A(Molecular and Biomolecular Spectroscopy), 2022, 269:120737.
14. [14]
  LI M X, LI Y Z, CHEN Y, et al.Excitation-emission matrix fluorescence spectroscopy combined with chemometrics methods for rapid identification and quantification of adulteration in Atractylodes macrocephala Koidz[J].Microchemical Journal, 2021, 171:106884.
15. [15]
  LONG W J, WU H L, WANG T, et al.Fast identification of the geographical origin of Gastrodia elata using excitation-emission matrix fluorescence and chemometric methods[J].Spectrochimica Acta Part A(Molecular and Biomolecular Spectroscopy), 2021, 258:119798.
16. [16]
  HU L Q, MA S, YIN C L.Discrimination of geographical origin and detection of adulteration of kudzu root by fluorescence spectroscopy coupled with multi-way pattern recognition[J].Spectrochimica Acta Part A(Molecular and Biomolecular Spectroscopy), 2018, 193:87-94.
17. [17]
  MATTHIAS S, ROSIE Y Z.The random forest algorithm for statistical learning[J].The Stata Journal(Promoting Communications on Statistics and Stata), 2020, 20(1):3-29.
18. [18]
  LI S F, JIA M Z, DONG D M.Fast measurement of sugar in fruits using near infrared spectroscopy combined with random forest algorithm[J].Spectroscopy And Spectral Analysis, 2018, 38(6):1766-1771.
19. [19]
  FELIPE L G, GUSTAVO R F, HENRIQUE F D A, et al.Principal component analysis:A natural approach to data exploration[J].ACM Computing Surveys, 2021.54(4):1-34.
20. [20]
  成巍, 侯恩广, 李珂, 等.基于PCA的中药黄芩药效评价方法研究[J].山东科学, 2012, 25(1):47-50.
1. [1]
  李跑,谭惠珍,谢叔娥,苏光林,董怡青,唐辉. 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. 轻工学报, 2024, 39(2): 54-59.doi: 10.12187/2024.02.007
2. [2]
  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
3. [3]
  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): -.
4. [4]
  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
5. [5]
  许春平,王充,李萌姗,马扩彦,曲利利,冉盼盼,孟丹丹,吴彦. 不同产地烤烟花蕾浸膏挥发性成分的主成分分析. 轻工学报, 2017, 32(2): 48-57.doi: 10.3969/j.issn.2096-1553.2017.2.008
6. [6]
  张颖璞,李桂珍,黄朝章,李巧灵. 不同产地烟叶的热解反应动力学研究. 轻工学报, 2018, 33(2): 55-62.doi: 10.3969/j.issn.2096-1553.2018.02.009
7. [7]
  帖金鑫,何文苗,李石头,郝贤伟,李永生,张立立,钟永健,毕一鸣. 基于级联分类的复烤片烟产地预测方法研究. 轻工学报, 2022, 37(4): 94-99.doi: 10.12187/2022.04.013
8. [8]
  牛玉清,赵岩,于鑫淼,宋丽军. 新疆管花肉苁蓉生物活性物质及产地差异分析. 轻工学报, 2022, 37(6): 25-33.doi: 10.12187/2022.06.004
9. [9]
  郝捷,江彩艳,柴颖,王煦松,姜鹏飞. 基于GC-IMS的不同产地烟草中挥发性风味物质分析. 轻工学报, 2023, 38(2): 87-93,117.doi: 10.12187/2023.02.011
10. [10]
  郭黎,李璐,李鹏,赵婕,郭志林. 随机P-集合及其图像安全传递. 轻工学报, 2011, 26(5): 112-116.doi: 10.3969/j.issn.1004-1478.2011.05.028
11. [11]
  陈芝飞,蔡莉莉,陈小龙,张玉霞,马胜涛,席高磊,王清福,张俊岭. 基于香韵活性值的不同产地中间香型烤烟风格特征差异分析. 轻工学报, 2022, 37(1): 79-86.doi: 10.12187/2022.01.011
12. [12]
  高薇,王秀,李见春,涂密密,高菲,徐峰,王玉帅. 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. 轻工学报, 2022, 37(1): 33-39.doi: 10.12187/2022.01.005
13. [13]
  李昕. 一类随机利率下的变额寿险模型. 轻工学报, 2011, 26(2): 121-124.doi: 10.3969/j.issn.1004-1478.2011.02.030
14. [14]
  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
15. [15]
  朱志伟,史慧革,张振,曹桂州. 电力系统随机小扰动区间稳定性分析. 轻工学报, 2021, 36(2): 102-108.doi: 10.12187/2021.02.013
16. [16]
  张平,任静,赵明慧. 有界扰动下虚拟控制系数未知的随机关联系统的分散镇定控制. 轻工学报, 2014, 29(5): 68-73,77.doi: 10.3969/j.issn.2095-476X.2014.05.016
17. [17]
  李石头,毕一鸣,帖金鑫,杨晨,李庆祥,李永生,杨鹏飞,毛多斌. 基于UHPLC法的巨豆三烯酮前体物同分异构体的定量分析及其在不同产地烟叶中的分布情况. 轻工学报, 2023, 38(5): 83-87.doi: 10.12187/2023.05.011
18. [18]
  钱存,王云龙,明亮,李玉林,王继创,程蕾,程春杰,高玉红,闫生辉. 荧光层析定量检测tPSA和fPSA方法研究. 轻工学报, 2017, 32(4): 37-42.doi: 10.3969/j.issn.2096-1553.2017.4.006
19. [19]
  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
20. [20]
  赵大洲. 运用紫外分光光度法测定枣肉、枣核的铁元素含量. 轻工学报, 2019, 34(6): 9-14.doi: 10.3969/j.issn.2096-1553.2019.06.002

点击查看大图

计量

PDF下载量:18
文章访问数:834
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

基于改进随机森林算法的薏苡仁产地溯源研究

作者简介:赵汉卿(1997-),男,山东省东营市人,中南林业科技大学硕士研究生,主要研究方向为多种模式识别方法下中药产地的溯源。E-mail:hanqing4126@126.com;

Research on geographical origin traceability of Coix seed based on a modified random forest algorithm

计量

通讯作者:陈斌, bchen63@163.com

基于改进随机森林算法的薏苡仁产地溯源研究

作者简介:赵汉卿(1997-),男,山东省东营市人,中南林业科技大学硕士研究生,主要研究方向为多种模式识别方法下中药产地的溯源。E-mail:hanqing4126@126.com

English Abstract

Research on geographical origin traceability of Coix seed based on a modified random forest algorithm

目录

基于改进随机森林算法的薏苡仁产地溯源研究

作者简介:赵汉卿(1997-),男,山东省东营市人,中南林业科技大学硕士研究生,主要研究方向为多种模式识别方法下中药产地的溯源。E-mail:hanqing4126@126.com;

Research on geographical origin traceability of Coix seed based on a modified random forest algorithm

计量

文章相关

通讯作者:陈斌, bchen63@163.com

基于改进随机森林算法的薏苡仁产地溯源研究

作者简介:赵汉卿(1997-),男,山东省东营市人,中南林业科技大学硕士研究生,主要研究方向为多种模式识别方法下中药产地的溯源。E-mail:hanqing4126@126.com

English Abstract

Research on geographical origin traceability of Coix seed based on a modified random forest algorithm

目录