• Spectroscopy and Spectral Analysis
  • Vol. 42, Issue 9, 2969 (2022)
Sample data collection
Fig. 1. Sample data collection
Flowchart of tomato gray mold diagnosis and classification
Fig. 2. Flowchart of tomato gray mold diagnosis and classification
Hyperspectral images of inoculated pathogenic sample #1 in the first 8 days
Fig. 3. Hyperspectral images of inoculated pathogenic sample #1 in the first 8 days
Hyperspectral mean reflectivity curves of tomato leaves in different periods
Fig. 4. Hyperspectral mean reflectivity curves of tomato leaves in different periods
Comparison of spectra with different pretreatment methods
Fig. 5. Comparison of spectra with different pretreatment methods
Feature wavebands extracted by DWT-CARS algorithm for three times(a): The first extraction; (b): The second extraction; (c): The third extraction
Fig. 6. Feature wavebands extracted by DWT-CARS algorithm for three times
(a): The first extraction; (b): The second extraction; (c): The third extraction
Feature bands extracted by DWT-CARS algorithm for three times(a): The first extraction; (b): The second extraction; (c): The third extraction
Fig. 7. Feature bands extracted by DWT-CARS algorithm for three times
(a): The first extraction; (b): The second extraction; (c): The third extraction
Confusion matrix of three model test sets(a): DWT-FC-TLBO-ELM; (b): DWT-TLBO-ELM; (c): DWT-CARS-TLBO-ELM
Fig. 8. Confusion matrix of three model test sets
(a): DWT-FC-TLBO-ELM; (b): DWT-TLBO-ELM; (c): DWT-CARS-TLBO-ELM
DWT-CARS方法第1次第2次第3次
特征波段个数/个557
特征波段/nm696, 765, 769, 838, 840696, 767, 769, 772, 840694, 696, 767, 769, 778, 838, 840
RMSECV/%0.295 90.294 50.297 4
最终特征波段/nm694, 696, 765, 767, 769, 772, 778, 838, 840
Table 1. Feature bands extracted by DWT-CARS algorithm for three times
诊断模型模型参数测试集
准确率/%
测试集
精确率/%
召回率
/%
F1
/%
最优权值ω隐藏层最优阈值b
DWT-FC-TLBO-ELM1.044 815595.7196.4795.7196.09
DWT-TLBO-ELM1.044 87095.7196.1795.7195.94
DWT-CARS-TLBO-ELM1107100100100100
Table 2. Model parameters and test set accuracy, accuracy, recall rate and F1 value