Non-destructive Detection of Polysaccharide and Flavonoid Contents in <i>Anoectochilus roxburghii</i> Using Hyperspectral Technology

GU Chuankai; CHU Xuan; LIU Hongli; WEI Hongyu; MU Yinghui; MA Zhiyu

doi:10.13386/j.issn1002-0306.2023100154

Volume 46 Issue 7

Mar. 2025

Turn off MathJax

Article Contents

Abstract

References

Supplements

Science and Technology of Food Industry > 2025 > 46(7): 227-234. > DOI: 10.13386/j.issn1002-0306.2023100154

GU Chuankai, CHU Xuan, LIU Hongli, et al. Non-destructive Detection of Polysaccharide and Flavonoid Contents in Anoectochilus roxburghii Using Hyperspectral Technology[J]. Science and Technology of Food Industry, 2025, 46(7): 227−234. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023100154.

Citation:

PDF (2749 KB)

Non-destructive Detection of Polysaccharide and Flavonoid Contents in Anoectochilus roxburghii Using Hyperspectral Technology

1.
College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
2.
College of Engineering, South China Agricultural University, Guangzhou 510642, China

More Information

Received Date: October 18, 2023
Available Online: January 22, 2025

Graphical Abstract

Abstract

Abstract

This study aimed to rapidly and non-destructively evaluate the levels of polysaccharides and flavonoids in A. roxburghii leaves under various photoperiods (10, 12, 14, 16, 18, and 20 h/d). Hyperspectral imaging was employed to acquire pixel-level spectral data from the leaves, and discriminant models for content levels were developed using traditional machine learning methods (PCA-LDA and PCA-SVM) and deep learning approaches (1D CNN and its optimized version). The findings revealed that the 1D CNN model outperformed the PCA-LDA and PCA-SVM models in terms of discrimination accuracy on the training, validation, and independent test sets, achieving 99.99% and 99.89%, 99.98% and 99.78%, and 91.62% and 87.92%, respectively. The introduction of a Dropout layer in the 1D CNN model enhanced its generalization capability, increasing the discrimination accuracy for polysaccharide and flavonoid content levels on the independent test set to 98.92% and 95.67%, respectively. Additionally, visualization images depicting the discrimination results for different compound levels were constructed, providing an intuitive representation. This study validates the feasibility of hyperspectral imaging in evaluating polysaccharide and flavonoid levels in A. roxburghii leaves cultivated under various photoperiods, and the research results can provide technical support for the quality control of A. roxburghii.
- non-destructive testing,
- deep learning,
- machine learning,
- Anoectochilus roxburghii,
- polysaccharides and flavonoids contents

FullText(HTML)

References (33)

References

[1]	ZENG B, SU M, CHEN Q, et al. Antioxidant and hepatoprotective activities of polysaccharides from Anoectochilus roxburghii[J]. Carbohydrate Polymers,2016,153:391−398. doi: 10.1016/j.carbpol.2016.07.067
[2]	CUI S C, YU J, ZHANG X H, et al. Antihyperglycemic and antioxidant activity of water extract from Anoectochilus roxburghii in experimental diabetes[J]. Experimental and Toxicologic Pathology,2013,65(5):485−488. doi: 10.1016/j.etp.2012.02.003
[3]	WANG X X, HE J M, WANG C L, et al. Simultaneous structural identification of natural products in fractions of crude extract of the rare endangered plant Anoectochilus roxburghii using 1H NMR/RRLC-MS parallel dynamic spectroscopy[J]. International Journal of Molecular Sciences,2011,12:2556−2571. doi: 10.3390/ijms12042556
[4]	LV T W. TENG R D, SHAO Q S, et al. DNA barcodes for the identification of Anoectochilus roxburghii and its adulterants[J]. Planta,2015,242:1167−1174. doi: 10.1007/s00425-015-2353-x
[5]	应震, 杨燕萍, 林恩义, 等. 林下仿野生栽培和设施栽培金线莲生物量及药用成分含量变化研究[J]. 浙江林业科技,2024,44(2):95−99. [YING Z, YANG Y P, LIN E Y, et al. Variation of biomass and medicinal components in Anoectochilus roxburghii with different cultivation methods[J]. Journal of Zhejiang Forestry Science and Technology,2024,44(2):95−99.] YING Z, YANG Y P, LIN E Y, et al. Variation of biomass and medicinal components in Anoectochilus roxburghii with different cultivation methods[J]. Journal of Zhejiang Forestry Science and Technology, 2024, 44（2）: 95−99.
[6]	蔡文燕, 肖华山, 范秀珍. 金线莲研究进展[J]. 亚热带植物科学,2003,32(3):68−72. [CAI W Y, XIAO H S, FAN X Z. A review of research on Anoectochilus roxburghii[J]. Subtropical Plant Science,2003,32(3):68−72.] doi: 10.3969/j.issn.1009-7791.2003.03.018 CAI W Y, XIAO H S, FAN X Z. A review of research on Anoectochilus roxburghii[J]. Subtropical Plant Science, 2003, 32（3）: 68−72. doi: 10.3969/j.issn.1009-7791.2003.03.018
[7]	WU Y, LIU C, JIANG Y, et al. Structural characterization and hepatoprotective effects of polysaccharides from Anoectochilus zhejiangensis[J]. International Journal of Biological Macromolecules,2022,198:111−118. doi: 10.1016/j.ijbiomac.2021.12.128
[8]	SHEN Y Y, QING S S, MENG J X, et al. Effects of light quality on morphology, enzyme activities, and bioactive compound contents in Anoectochilus roxburghii[J]. Frontiers in Plant Science,2017,8:857. doi: 10.3389/fpls.2017.00857
[9]	郑涛, 刘宁, 孙红, 等. 基于高光谱成像的马铃薯叶片叶绿素分布可视化研究[J]. 农业机械学报,2017,32(S1):153−159,340. [ZHENG T, LIU N, SUN H, et al. Visualization of chlorophyll distribution of potato leaves based on hyperspectral imaging technology[J]. Transactions of the Chinese Society for Agricultural Machinery,2017,32(S1):153−159,340.] doi: 10.6041/j.issn.1000-1298.2017.S0.025 ZHENG T, LIU N, SUN H, et al. Visualization of chlorophyll distribution of potato leaves based on hyperspectral imaging technology[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 32（S1）: 153−159,340. doi: 10.6041/j.issn.1000-1298.2017.S0.025
[10]	赵艳茹, 余克强, 李晓丽, 等. 基于高光谱成像的南瓜叶片叶绿素分布可视化研究[J]. 光谱学与光谱分析,2014,34(5):1378−1382. [ZHAO Y R, YU K Q, LI X L, et al. Study on SPAD visualization of pumpkin leaves based on hyperspectral imaging technology[J]. Spectroscopy and Spectral Analysis,2014,34(5):1378−1382.] doi: 10.3964/j.issn.1000-0593(2014)05-1378-05 ZHAO Y R, YU K Q, LI X L, et al. Study on SPAD visualization of pumpkin leaves based on hyperspectral imaging technology[J]. Spectroscopy and Spectral Analysis, 2014, 34（5）: 1378−1382. doi: 10.3964/j.issn.1000-0593(2014)05-1378-05
[11]	WU L, GONG Y J, BAI X P, et al. Nondestructive determination of leaf nitrogen content in corn by hyperspectral imaging using spectral and texture fusion[J]. Applied Sciences,2023,13(3):1910−1927. doi: 10.3390/app13031910
[12]	YE W, YAN T, ZHANG C, et al. Detection of pesticide residue level in grape using hyperspectral imaging with machine learning[J]. Foods,2022,11(11):1609−1615. doi: 10.3390/foods11111609
[13]	CHEN Y, XIE M, ZHANG H, et al. Quantification of total polysaccharides and triterpenoids in Ganoderma lucidum and Ganoderma atrum by near infrared spectroscopy and chemometrics[J]. Food Chemistry,2012,135(1):268−275. doi: 10.1016/j.foodchem.2012.04.089
[14]	YANG L, GAO H, MENG L, et al. Nondestructive measurement of pectin polysaccharides using hyperspectral imaging in mulberry fruit[J]. Food Chemistry,2021,334:127614. doi: 10.1016/j.foodchem.2020.127614
[15]	宋镇, 姬长英, 张波. 基于光谱与图像信息的杏鲍菇多糖含量检测[J]. 华南农业大学学报,2019,40(3):104−110. [SONG Z, JI C Y, ZHANG B. Detection of polysaccharide content in Pleurotus eryngii based on spectral and image information[J]. Journal of South China Agricultural University,2019,40(3):104−110.] doi: 10.7671/j.issn.1001-411X.201807047 SONG Z, JI C Y, ZHANG B. Detection of polysaccharide content in Pleurotus eryngii based on spectral and image information[J]. Journal of South China Agricultural University, 2019, 40（3）: 104−110. doi: 10.7671/j.issn.1001-411X.201807047
[16]	张郡赫, 于海业, 党敬民. 基于双光谱技术的高温紫外胁迫下小麦多糖反演模型研究[J]. 光谱学与光谱分析,2023,43(9):2705−2709. [ZHANG J H, YU H Y, DANG J M. Research on inversion model of wheat polysaccharide under high temperature and ultraviolet stress based on dual-spectral technique[J]. Spectroscopy and Spectral Analysis,2023,43(9):2705−2709.] ZHANG J H, YU H Y, DANG J M. Research on inversion model of wheat polysaccharide under high temperature and ultraviolet stress based on dual-spectral technique[J]. Spectroscopy and Spectral Analysis, 2023, 43（9）: 2705−2709.
[17]	邹小波, 陈武, 徐艺伟, 等. 不同生长阶段枇杷叶总黄酮含量的二维分布检测[J]. 天然产物研究与开发,2016,28:354−358. [ZOU X B, CHEN W, XU Y W, et al. Content distribution of total flavonoid in loquat (Eriobotrya japonica) leaves at different growth stages[J]. Natural Product Research and Development,2016,28:354−358.] ZOU X B, CHEN W, XU Y W, et al. Content distribution of total flavonoid in loquat （Eriobotrya japonica） leaves at different growth stages[J]. Natural Product Research and Development, 2016, 28: 354−358.
[18]	王树文, 修成, 董元, 等. 不同时段刺五加叶片黄酮含量的高光谱无损估测[J]. 农机化研究,2022,44(4):119−126,268. [WANG S W, XIU C, DONG Y, et al. Non-destructive estimation of flavonoids in leaves of Acanthopanax senticosus in different periods[J]. Journal of Agricultural Mechanization Research,2022,44(4):119−126,268.] doi: 10.3969/j.issn.1003-188X.2022.04.021 WANG S W, XIU C, DONG Y, et al. Non-destructive estimation of flavonoids in leaves of Acanthopanax senticosus in different periods[J]. Journal of Agricultural Mechanization Research, 2022, 44（4）: 119−126,268. doi: 10.3969/j.issn.1003-188X.2022.04.021
[19]	HE J, CHEN L, CHU B, et al. Determination of total polysaccharides and total flavonoids in Chrysanthemum morifolium using near-infrared hyperspectral imaging and multivariate analysis[J]. Molecules,2018,23(9):2395. doi: 10.3390/molecules23092395
[20]	余克强, 赵艳茹, 李晓丽, 等. 高光谱成像技术的不同叶位尖椒叶片氮素分布可视化研究[J]. 光谱学与光谱分析,2015,35(3):746−750. [YU K Q, ZHAO Y R, LI X L, et al. Application of hyperspectral imaging for visualization of nitrogen content in pepper leaf with different positions[J]. Spectroscopy and Spectral Analysis,2015,35(3):746−750.] doi: 10.3964/j.issn.1000-0593(2015)03-0746-05 YU K Q, ZHAO Y R, LI X L, et al. Application of hyperspectral imaging for visualization of nitrogen content in pepper leaf with different positions[J]. Spectroscopy and Spectral Analysis, 2015, 35（3）: 746−750. doi: 10.3964/j.issn.1000-0593(2015)03-0746-05
[21]	石吉勇, 邹小波, 张德涛, 等. 不同颜色银杏叶总黄酮含量分布高光谱图像检测[J]. 农业机械学报, 2014, 45(11):242−245, 33. [SHI J Y, ZOU X B, ZHANG D T, et al. Determination of total flavonoid content distribution on different colorGinkgo biloba leaves[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(11):242−245, 33.] SHI J Y, ZOU X B, ZHANG D T, et al. Determination of total flavonoid content distribution on different color Ginkgo biloba leaves[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45（11）: 242−245, 33.
[22]	李芳, 石吉勇, 张德涛, 等. 银杏叶中黄酮含量的叶面分布检测研究[J]. 食品工业科技,2015,36(9):270−272. [LI F, SHI J Y, ZHANG D T, et al. Determination of total flavonoid content distribution on Ginkgo biloba leaf[J]. Science and Technology of Food Industry,2015,36(9):270−272.] LI F, SHI J Y, ZHANG D T, et al. Determination of total flavonoid content distribution on Ginkgo biloba leaf[J]. Science and Technology of Food Industry, 2015, 36（9）: 270−272.
[23]	黄瑞平, 黄颖桢, 陈菁瑛, 等. 不同月龄金线莲多糖和总黄酮含量的比较[J]. 热带生物学报,2012,3(2):174−176. [HUANG R P, HUANG Y Z, CHEN J Y, et al. Comparison of polysaccharide and flavonoid contents in Anoictochilus roxburghii (Wall.) Lindl under different cultivation forms and harvest time[J]. Journal of Tropical Biology,2012,3(2):174−176.] doi: 10.3969/j.issn.1674-7054.2012.02.017 HUANG R P, HUANG Y Z, CHEN J Y, et al. Comparison of polysaccharide and flavonoid contents in Anoictochilus roxburghii （Wall.） Lindl under different cultivation forms and harvest time[J]. Journal of Tropical Biology, 2012, 3（2）: 174−176. doi: 10.3969/j.issn.1674-7054.2012.02.017
[24]	de SANTANA F B, OTANI S K, de SOUZA A M, et al. Comparison of PLS and SVM models for soil organic matter and particle size using vis-NIR spectral libraries[J]. Geoderma Regional,2021,27:e00436. doi: 10.1016/j.geodrs.2021.e00436
[25]	AMSARAJ R, AMBADE N D, MUTTURI S. Variable selection coupled to PLS2, ANN and SVM for simultaneous detection of multiple adulterants in milk using spectral data[J]. International Dairy Journal,2021,123:105172. doi: 10.1016/j.idairyj.2021.105172
[26]	李灵巧, 潘细朋, 冯艳春, 等. 深度卷积网络的多品种多厂商药品近红外光谱分类[J]. 光谱学与光谱分析,2019,39(11):3606−3613. [LI L Q, PAN X P, FENG Y C, et al. Deep convolution network application in identification of multi-variety and mult-manufacturer pharmaceutical[J]. Spectroscopy and Spectral Analysis,2019,39(11):3606−3613.] LI L Q, PAN X P, FENG Y C, et al. Deep convolution network application in identification of multi-variety and mult-manufacturer pharmaceutical[J]. Spectroscopy and Spectral Analysis, 2019, 39（11）: 3606−3613.
[27]	GUO Y H, SUN L, ZHANG Z H, et al. Algorithm research on improving activation function of convolutional neural networks[C]//In Proceedings of the 31st Chinese Control and Decision Conference. Nan Chang, China:2019:3582−3586.
[28]	BARANSKI R, BARANSKA M, SCHULZ H. Changes in carotenoid content and distribution in living plant tissue can be observed and mapped in situ using NIR-FT-Raman spectroscopy[J]. Planta,2005,222:448−457. doi: 10.1007/s00425-005-1566-9
[29]	邹红玉, 郑红平. 浅述植被“红边”效应及其定量分析方法[J]. 遥感信息,2010(4):112−116. [ZOU H Y, ZHENG H P. The Effect and method of quantitative analysis of "Red Edge" of vegetation[J]. Remote Sensing Information,2010(4):112−116.] doi: 10.3969/j.issn.1000-3177.2010.04.021 ZOU H Y, ZHENG H P. The Effect and method of quantitative analysis of "Red Edge" of vegetation[J]. Remote Sensing Information, 2010（4）: 112−116. doi: 10.3969/j.issn.1000-3177.2010.04.021
[30]	王震, 李映雪, 吴芳, 等. 冠层光谱红边参数结合随机森林机器学习估算冬小麦叶绿素相对含量[J]. 农业工程学报,2024,40(4):171−182. [WANG Z, LI Y X, WU F, et al. Estimation of winter wheat chlorophyll relative content combing with canopy spectrum red edge parameters and random forest machine learning[J]. Transactions of the CSAE,2024,40(4):171−182.] WANG Z, LI Y X, WU F, et al. Estimation of winter wheat chlorophyll relative content combing with canopy spectrum red edge parameters and random forest machine learning[J]. Transactions of the CSAE, 2024, 40（4）: 171−182.
[31]	YU K Q, ZHAO Y R, ZHU F L, et al. Mapping of chlorophyll and SPAD distribution in pepper leaves during leaf senescence using visible and near-infrared hyperspectral imaging[J]. Transactions of the ASABE,2016,59(1):13−24. doi: 10.13031/trans.59.10536
[32]	蒋国瑞, 司学峰. 基于代价敏感SVM的电信客户流失预测研究[J]. 计算机应用研究,2009,26(2):521−523. [JIANG G R, SI X F. Study of telecom customer churn prediction based on cost sensitive SVM[J]. Application Research of Computers,2009,26(2):521−523.] JIANG G R, SI X F. Study of telecom customer churn prediction based on cost sensitive SVM[J]. Application Research of Computers, 2009, 26（2）: 521−523.
[33]	XU Q, ZHANG M, GU Z, et al. Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs[J]. Neurocomputing,2019,382:69−74.