TABLE 2.
Cultivar | Features | Variables | Model | Tr (%) | Val (%) | Te (%) | Model | Tr (%) | Val (%) | Te (%) | Model | Tr (%) | Val (%) | Te (%) |
Zhefujing83 | Full-HSI | 390 | SVM | 95.00 | 90.00 | 90.38 | LR | 98.33 | 95.00 | 98.08 | CNN | 98.33 | 95.00 | 100 |
Full-MIR | 7,468 | 100 | 100 | 76.92 | 100 | 100 | 82.69 | 100 | 95.00 | 82.69 | ||||
Full-LIBS | 22,036 | 100 | 100 | 71.15 | 100 | 100 | 67.31 | 100 | 100 | 86.54 | ||||
AD516 | Full-HSI | 390 | 100 | 100 | 96.88 | 100 | 100 | 100 | 100 | 100 | 100 | |||
Full-MIR | 7,468 | 99.17 | 90.00 | 85.94 | 100 | 100 | 96.88 | 100 | 90.00 | 81.25 | ||||
Full-LIBS | 22,036 | 100 | 100 | 75.00 | 100 | 100 | 87.50 | 100 | 100 | 81.25 |
Other abbreviations are similar to this fashion. Tr, training set; Val, validation set; Te, test set; Full-HSI, full spectra of HIS.