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
Establishment of near infrared models of flue-cured tobacco leaves β-carotene and lutein based on random frog screening
-
摘要: 为提高近红外光谱法测定初烤烟叶中β-胡萝卜素和叶黄素含量的准确性和稳定性,采用随机蛙跳(Random Frog, RF)筛选特征波长建立上述指标的偏最小二乘(Partial Least Squares,PLS)近红外模型,结合模型内部交互验证结果确定最优建模波长数和主成分数,并对最优模型的准确性和稳定性进行内外部评价。结果表明:相较于全波长(1298个波长)建模,利用RF筛选出的181个和216个特征波长建模,模型的决定系数(R2)由0.771 8和0.867 7分别提高至0.951 1和0.958 7,校正均方根误差(RMSEC)由3.362 μg/g和4.930 μg/g 分别降低至1.556 μg/g和2.756 μg/g,交互验证均方根误差(RMSECV)由3.304 μg/g和4.836 μg/g 分别降低至1.529 μg/g和2.703 μg/g;模型外部预测集(样品数=50)的预测平均相对误差分别由11.80 %和9.62 %降低至5.48 %和5.49 %。采用RF筛选特征波长能有效提升初烤烟叶β-胡萝卜素和叶黄素含量近红外模型的准确性和稳定性,可为初烤烟叶质量评价提供理论参考。Abstract: To improve the accuracy and stability of rapid determination of β-carotene and lutein in flue-cured by near infrared spectroscopy, this study used random frog to screen the characteristic wavelength of partial least squares (PLS) near infrared model of the above indicators. Furthermore, the optimal number of wavelengths and principal components were determined by internal interaction verification, and the accuracy and stability of the optimal model were verified by internal parameters and external parameters. The results showed that:compared with the full-wavelength(1298 wavelengths) model, the determination coefficient R2 of the β-carotene and lutein models established 181 and 216 wavelength variables by RF wavelength screening combined with PLS was increased from 0.771 8 and 0.867 7 to 0.951 1 and 0.958 7, respectively. The corrected values of root mean square error of calibration (RMSEC) was reduced from 3.362 μg/g and 4.930 μg/g to 1.556 μg/g and 2.756 μg/g, respectively. The values of root mean square error of cross validation (RMSECV) was reduced from 3.304 μg/g, 4.836 μg/g to 1.529 μg/g, 2.703 μg/g; The average relative error of external validation (50 samples) decreased from 11.80 % and 9.62 % to 5.48 % and 5.49 %, respectively. The random frog screening wavelength method could significantly improve the accuracy and stability of the near infrared models for the determination of β-carotene and lutein of flue-cured tobacco, which could provide more accurate and reliable data reference for its quality evaluation.
-
Key words:
- near infrared model /
- random frog /
- flue-cured tobacco leaf /
- β-carotene /
- lutein
-
-
[1]
贾中林,郑庆霞,戴华鑫,等.烤烟上部叶成熟过程中代谢组的差异分析[J].烟草科技,2023,56(1):1-10.
-
[2]
胡亚杰,王闯,王维,等.酸碱处理对两种土壤类型初烤烟颜色变化的影响[J].南方农业学报,2020,51(9):2261-2268.
-
[3]
曹建敏,别瑞,王玉华,等.烤烟新品种中烟特香301特征香气物质研究[J].中国烟草科学,2022,43(2):64-70.
-
[4]
孔芳芳,王玉华,别瑞,等.不同烘烤方式对烤烟香气成分与品质的影响[J].山东农业科学,2022,54(5):71-78.
-
[5]
韦克苏,涂永高,张念,等.采收成熟度对烘烤过程烟叶色素降解及抗氧化系统的影响[J].江苏农业科学,2021,49(13):176-180.
-
[6]
赵高坤,任可,陈妍洁,等.不同成熟度烟叶烘烤过程中大分子物质代谢动态研究[J].西南农业学报,2020,33(9):1950-1957.
-
[7]
葛炯,孙琳,沈晓洁,等.拉曼光谱结合偏最小二乘同时测定烟草中叶黄素和β-胡萝卜素含量[J].光谱学与光谱分析,2019,39(11):3519-3524.
-
[8]
CASTILLO M S,ACOSTA J J,HODGE G R,et al.Analysis of alkaloids and reducing sugars in processed and unprocessed tobacco leaves using a handheld near infrared spectrometer[J].Journal of Near Infrared Spectroscopy,2023,31(2):55-62.
-
[9]
WEI K S,BIN J,WANG F,et al.On-line monitoring of the tobacco leaf composition during flue-curing by near-infrared spectroscopy and deep transfer learning[J].Analytical Letters,2022,55(13):2089-2107.
-
[10]
宋怡,刘巍,段焰青,等.近红外光谱法快速测定烟草中的植物色素[J].中国烟草学报,2009,15(2):15-18.
-
[11]
侯英,李晓亚,杨式华,等.傅里叶变换近红外光谱法快速测定烟叶中叶黄素和β-胡萝卜素含量[J].云南化工,2009,36(5):20-23.
-
[12]
云永欢,邓百川,梁逸曾.化学建模与模型集群分析[J].分析化学,2015,43(11):1638-1647.
-
[13]
邵学广,蔡文生,徐恒.近红外光谱分析中波长选择的必要性[C]//中国化学会.第27届学术年会第15分会场摘要集:2011卷.厦门:[s.n.],2010.
-
[14]
LI H D,LIANG Y Z,XU Q S,et al.Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration[J].Analytica Chimica Acta,2009,648(1):77-84.
-
[15]
LI H D,XU Q S,LIANG Y Z.Random frog:An efficient reversible jump Markov Chain Monte Carlo-like approach for gene selection and disease classification[J].Analytica Chimica Acta,2012,740:20-26.
-
[16]
王晋,黄海涛,刘欣,等.超高效液相色谱法快速测定烟草样品中的植物色素[J].湖北农业科学,2018,57(22):124-127.
-
[17]
云南省质量技术监督局.烟草及烟草制品主要化学成分指标近红外校正模型建立与验证导则:DB/T 497-2013[S].北京:中国标准出版社,2013.
-
[18]
周文忠,张峻松,邹悦,等.应用近红外光谱法结合波长筛选快速测定烟草绿原酸、莨菪亭和芸香苷含量[J].江西农业学报,2019,31(12):66-71.
-
[19]
梁逸曾,许青松.复杂体系仪器分析:白、灰、黑分析体系及其多变量解析方法[M].北京:化学工业出版社,2012:253.
-
[20]
高瑞琳,杨鹏硕,许刚,等.基于系统建模思想的脑心通胶囊中丹酚酸B近红外定量建模[J].光谱学与光谱分析,2020,40(11):3573-3578.
-
[21]
邹小波,陈正伟,石吉勇,等.基于近红外高光谱图像的黄瓜叶片色素含量快速检测[J].农业机械学报,2012,43(5):152-156.
-
[1]
-
点击查看大图
计量
- PDF下载量: 1
- 文章访问数: 80
- 引证文献数: 0
下载:
