• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 9, 2764 (2021)
Yong HAO1、1;, Qi-ming WANG1、1;, and Shu-min ZHANG2、2;
Author Affiliations
  • 11. School of Mechatronics and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
  • 22. Technology Center of Nanchang Customs District, Nanchang 330038, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)09-2764-06 Cite this Article
    Yong HAO, Qi-ming WANG, Shu-min ZHANG. Study on Online Detection Method of “Yali” Pear Black Heart Disease Based on Vis-Near Infrared Spectroscopy and AdaBoost Integrated Model[J]. Spectroscopy and Spectral Analysis, 2021, 41(9): 2764 Copy Citation Text show less
    Schematic diagram of the vis-near infrared spectroscopy online sorting device for ‘Yali' pear
    Fig. 1. Schematic diagram of the vis-near infrared spectroscopy online sorting device for ‘Yali' pear
    Arrangement top view of halogen lamp
    Fig. 2. Arrangement top view of halogen lamp
    Energy spectra curve of normal pear and black heart pear
    Fig. 3. Energy spectra curve of normal pear and black heart pear
    Distribution of the first three principal components of normal pears and black heart pears
    Fig. 4. Distribution of the first three principal components of normal pears and black heart pears
    AdaBoost algorithm principle
    Fig. 5. AdaBoost algorithm principle
    Comparison of actual categories and predicted categories in WT-AdaBoost model for ‘Yali' pear samples
    Fig. 6. Comparison of actual categories and predicted categories in WT-AdaBoost model for ‘Yali' pear samples
    样本集正常梨黑心梨
    训练集80110
    测试集4055
    Table 1. Sample set information
    真实情况预测结果
    正常梨黑心梨
    正常梨TPFN
    黑心梨FPTN
    Table 2. confusion matrix for classification result
    预处理方法F-measure/%Accuracy/%
    Raw77.3880.00
    Smooth73.4976.84
    SNV77.3880.00
    MSC77.3880.00
    SG 1st-Der72.1178.42
    WT78.9882.62
    Table 3. kNN model results of qualitative identification of ‘Yali' pears with different pretreatment methods
    预处理方法F-measure/%Accuracy/%
    Raw53.9356.84
    Smooth53.9356.84
    SNV53.9356.84
    MSC54.0257.89
    SG 1st-Der80.9082.11
    WT68.5771.05
    Table 4. NBC model results of qualitative identification of ‘Yali' pears with different pretreatment methods
    预处理方法F-measure/%Accuracy/%
    Raw85.1987.37
    Smooth84.8187.37
    SNV85.1987.37
    MSC85.1987.37
    SG 1st-Der56.5268.42
    WT90.2491.58
    Table 5. SVM model results of qualitative identification of ‘Yali' pears with different pretreatment methods
    预处理方法F-measure/%Accuracy/%
    Raw84.2187.37
    Smooth84.4287.37
    SNV85.8887.37
    MSC83.2385.79
    SG 1st-Der77.1979.47
    WT91.4692.63
    Table 6. AdaBoost qualitative identification results of ‘Yali' pears with different pretreatment methods
    分类模型F-measure
    /%
    Accuracy
    /%
    预测时间
    估算*/s
    WT-kNN79.5282.110.04
    SG 1st-Der-NBC75.6881.050.03
    WT-SVM88.6190.530.04
    WT-AdaBoost90.9192.630.12
    Table 7. KNN, NBC, SVM and AdaBoost model test set prediction results
    Yong HAO, Qi-ming WANG, Shu-min ZHANG. Study on Online Detection Method of “Yali” Pear Black Heart Disease Based on Vis-Near Infrared Spectroscopy and AdaBoost Integrated Model[J]. Spectroscopy and Spectral Analysis, 2021, 41(9): 2764
    Download Citation