基于高光谱成像及机器学习的烟叶糖料液施加量判别模型

张建栋; 杨忠泮; 吴恋恋; 徐大勇; 朱萍; 张雯晶; 堵劲松

doi:10.12187/2024.05.010

October 2024

Article Contents

ZHANG Jiandong, YANG Zhongpan, WU Lianlian, et al. Discrimination model of tobacco leaf sucrose solution application levels based on hyperspectral imaging and machine learning[J]. Journal of Light Industry, 2024, 39(5): 86-94. doi: 10.12187/2024.05.010

Citation: ZHANG Jiandong, YANG Zhongpan, WU Lianlian, et al. Discrimination model of tobacco leaf sucrose solution application levels based on hyperspectral imaging and machine learning[J]. Journal of Light Industry, 2024, 39(5): 86-94. doi: 10.12187/2024.05.010 shu

Discrimination model of tobacco leaf sucrose solution application levels based on hyperspectral imaging and machine learning

1. Technology R&D Center, Gansu Tobacco Industrial Co., Ltd., Lanzhou 730050, China;
2. School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China;
3. Zhengzhou Tobacco Research Institute of CNTC, Zhengzhou 450001, China

Corresponding author: YANG Zhongpan, 363583280@qq.com
Received Date: 2024-02-05
Accepted Date: 2024-04-19
Available Online: 2024-10-15

Abstract

To address the challenge of non-destructive detection of sucrose solution application in the tobacco leaf processing stage, a discrimination model for sucrose solution application based on hyperspectral imaging and machine learning had been developed. Hyperspectral data of tobacco leaf samples with varying sucrose solution applications were first acquired using a visible-shortwave infrared hyperspectral imaging system and preprocessed with standard normal variate (SNV). Four discrimination models for sucrose solution application were then constructed and validated using full-spectrum data and principal component analysis (PCA) reduced data, in conjunction with support vector machine (SVM), logistic regression (LR), multilayer perceptron (MLP), and random forest (RF). The results showed that SNV preprocessing significantly enhanced the feature concentration of the hyperspectral data. When modeling with full-spectrum data, the models in the shortwave infrared band demonstrated significantly higher prediction accuracy compared to those in the visible light band, with the LR model in the shortwave infrared band achieving the highest accuracy of 98.23%. Compared to full-spectrum data modeling, the prediction accuracy of models using the top 10 principal components from PCA reduced data showed little change in the shortwave infrared band, while the RF model's accuracy in the visible light band improved significantly to 71.43%. In the visible light band, the highest accuracy for PCA-reduced data models corresponded to 217, 55, 47, and 59 principal components, while in the shortwave infrared band, the numbers were 13, 11, 117, and 46, respectively. Overall, LR and RF models exhibited superior predictive perf ormance, with the LR model based on PCA-reduced data in the shortwave infrared band maintaining high accuracy with fewer principal components, demonstrating the capability for rapid, non-destructive, and precise determination of sucrose solution application on tobacco leaves.
- hyperspectral imaging,
- machine learning,
- tobacco leaf processing stage,
- sucrose solution application,
- logistic regression
References
1. [1]
  张永川,李建辉,丁照,等.分组加料柔性控制技术在制丝生产中的应用[J].烟草科技,2010,43(1):7-10.
2. [2]
  潘高伟,王川,甘学文,等.加料工序的不同工艺条件对烟草香味成分含量变化的影响研究[J].郑州轻工业学院学报(自然科学版),2007,22(2/3):43
  -48.
3. [3]
  熊安言,于建春,王二彬,等.叶丝加料工艺参数对加料效果的影响[J].烟草科技,2016,49(1):66-71.
4. [4]
  张辉,彭涛,向勇刚,等.烟叶加料系统的影响因素及对策研究[J].中国设备工程,2021(8):149-150.
5. [5]
  徐庆,陈波,文武,等.基于卷烟制丝加料施加效果改善的系统优化[J].中国新技术新产品,2023(12):46-49.
6. [6]
  梅吉帆,李智慧,李嘉康,等.基于高光谱成像技术的配方烟丝组分判别[J].分析测试学报,2021,40(8):1151-1157.
7. [7]
  YANG Z,ZHANG M M,ZHAO X X,et al.Ammonia induced strong LSPR effect of chain-like ATO nanocrystals for hyperspectral selective energy-saving window applications[J].Chemical Engineering Journal,2024,479:147442.
8. [8]
  胡会强,位云朋,徐华兴,等.基于高光谱成像技术和主成分分析对粉葛年限的鉴别[J].光谱学与光谱分析,2023,43(6):1953-1960.
9. [9]
  刘立新,李梦珠,赵志刚,等.高光谱成像技术在生物医学中的应用进展[J].中国激光,2018,45(2):214-223.
10. [10]
  孙威,陈蕊丽,骆建新.应用于血迹检测的高光谱成像技术研究综述[J].激光与光电子学进展,2021,58(6):84-93.
11. [11]
  张卫正,张伟伟,张焕龙,等.基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J].轻工学报,2017,32(5):95-102.
12. [12]
  HAQ M A,REHMAN Z,AHMED A,et al.Machine learning-based classification of hyperspectral imagery[J].International Journal of Computer Science & Network Security,2022,22(4):193-202.
13. [13]
  ANG K L M,SENG J K P.Big data and machine learning with hyperspectral information in agriculture[J].IEEE Access,2021,9:36699-36718.
14. [14]
  马怡茹,吕新,易翔,等.基于机器学习的棉花叶面积指数监测[J].农业工程学报,2021,37(13):152-162.
15. [15]
  李智慧,梅吉帆,李辉,等.高光谱成像的非烟物质分类识别研究[J].中国烟草学报,2022,28(3):81-88.
16. [16]
  郭文孟,薛宇毅,罗靖,等.基于高光谱成像的烟叶泛青特征分析与表征[J].烟草科技,2023,56(7):84-91.
17. [17]
  余梅,李尚科,杨菲,等.基于近红外光谱技术与优化光谱预处理的陈皮产地鉴别研究[J].分析测试学报,2021,40(1):65-71.
18. [18]
  孙嘉豪,张伟,施鉴芩,等.光谱数据预处理策略选择及应用[J].计量学报,2023,44(8):1284-1292.
19. [19]
  冯慧,熊立仲,陈国兴,等.基于高光谱成像和主成分分析的水稻茎叶分割[J].激光生物学报,2015,24(1):31.
20. [20]
  PAVLIDIS P,WAPINSKI I,NOBLE W S.Support vector machine classification on the web[J].Bioinformatics,2004,20(4):586-587.
21. [21]
  XING J,SYMONS S,SHAHIN M,et al.Detection of sprout damage in Canada Western Red Spring wheat with multiple wavebands using visible/near-infrared hyperspectral imaging[J].Biosystems Engineering,2010,106(2):188-194.
22. [22]
  TU K L,WEN S Z,CHENG Y,et al.A model for genuineness detection in genetically and phenotypically similar maize variety seeds based on hyperspectral imaging and machine learning[J].Plant Methods,2022,18(1):81.
23. [23]
  KNAUER U,MATROS A,PETROVIC T,et al.Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images[J].Plant Methods,2017,13(1):47.
24. [24]
  王钰豪,刘建国,徐亮,等.主成分分析在温室气体时序红外光谱处理中的应用研究[J].光谱学与光谱分析,2023,43(7):2313-2318.
Proportional views

Get Citation

PDF

XML

Article Metrics

Article views(608) PDF downloads(16) Cited by()

Ralated

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

Discrimination model of tobacco leaf sucrose solution application levels based on hyperspectral imaging and machine learning

Abstract

References

Proportional views

Article Metrics

Ralated

Proportional views

通讯作者: 陈斌, bchen63@163.com