Spectroscopy and Spectral Analysis, Volume. 42, Issue 5, 1366(2022)
Detection of Citrus Granulation Based on Near-Infrared Hyperspectral Data
Figures & Tables(11)
Fig. 1. Three different granulation degrees of navel orange in southern Jiangxi
(a): None; (b): Mild; (c): Moderate
Fig. 2. Hyperspectral equipment imaging device
(a): Schematic diagram; (b): Picture
Fig. 3. Modeling flow chart of detection for navel oranges with different granulation degrees
Fig. 4. Original mean reflectance spectra of navel oranges with three granulation degrees
Fig. 5. Cumulative contribution rates of the first 20 principal components of citrus hyperspectral data
Fig. 8. Prediction results of UVE-LS-SVM model based on RBF-Kernel
Table 1. Classification of training sets and prediction sets and sample codes of different coffee beans
View tableView in ArticleTable 1. Classification of training sets and prediction sets and sample codes of different coffee beans
Degree of
granulationSample
codeTotal number
of samplesNumber of training
set samplesNumber of test
set samplesNone 1 174 131 43 Mild 2 174 131 43 Moderate 3 174 131 43
Table 2. Comparison of PLS-DA models based on different dimension reduction methods
View tableView in ArticleTable 2. Comparison of PLS-DA models based on different dimension reduction methods
Model Variable selection
methodsNumber of
variablePCs Rc RMSEC Rp RMSEP Error rate of
prediction set/%PLS-DA Original data 176 12 0.910 0.210 0.890 0.281 7.55 PCA 6 5 0.708 0.442 0.659 0.474 25.58 SPA 17 7 0.832 0.330 0.827 0.338 15.55 UVE 54 7 0.912 0.244 0.895 0.261 5.38
Table 3. Comparison of model performance between different dimension reduction methods and LS-SVM method
View tableView in ArticleTable 3. Comparison of model performance between different dimension reduction methods and LS-SVM method
Methods No. of
variableRBF-Kernel LIN-Kernel γ, σ2 Error rate of
training set/%Error rate of
test set/%γ Error rate of
training set/%Error rate of
test set/%Full spectrum 176 1.796×104, 672.223 1.27 4.65 1.568 2.29 4.65 PCA 6 6.781, 0.735 1.78 1.55 1.039 5.09 17.05 SPA 17 1.362×104, 122.775 0.76 2.33 1.111 0.76 4.65 UVE 54 1.802×104, 500.116 0% 0.78% 1.667 0.25 1.55
Tools
Get Citation
Copy Citation Text
Yan-de LIU, Mao-peng LI, Jun HU, Zhen XU, Hui-zhen CUI. Detection of Citrus Granulation Based on Near-Infrared Hyperspectral Data[J]. Spectroscopy and Spectral Analysis, 2022, 42(5): 1366
Paper Information
Category: Research Articles
Received: Apr. 9, 2021
Accepted: --
Published Online: Nov. 10, 2022
The Author Email: Yan-de LIU (jxliuyd@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20