Table 3 Confusion matrix and performance measures for SVM classification of wheat genotypes using Linear and RBF kernels.
From: Ensemble and optimization algorithm in support vector machines for classification of wheat genotypes
Performance statistics | Actual | |||||
|---|---|---|---|---|---|---|
Linear kernel | RBF kernel | |||||
L | M | H | L | M | H | |
Prediction | ||||||
L | 18 | 1 | 0 | 19 | 1 | 0 |
M | 2 | 23 | 0 | 1 | 22 | 0 |
H | 0 | 1 | 14 | 0 | 2 | 14 |
Sensitivity | 0.900 | 0.920 | 1.000 | 0.950 | 0.880 | 1.000 |
Specificity | 0.974 | 0.941 | 0.978 | 0.974 | 0.971 | 0.956 |
Positive predictive value | 0.947 | 0.920 | 0.933 | 0.950 | 0.957 | 0.875 |
Negative predictive value | 0.950 | 0.941 | 1.000 | 0.974 | 0.917 | 1.000 |
Balanced accuracy | 0.937 | 0.931 | 0.989 | 0.962 | 0.925 | 0.978 |
F-measure | 0.923 | 0.920 | 0.966 | 0.950 | 0.917 | 0.933 |
