Table 8 Confusion matrix and performance measures for SVM classification of wheat genotypes using GS, RS and GA algorithms.
From: Ensemble and optimization algorithm in support vector machines for classification of wheat genotypes
Performance statistics | Actual | |||||
|---|---|---|---|---|---|---|
GS-SVM (RS-SVM) | GA-SVM | |||||
L | M | H | L | M | H | |
Prediction | ||||||
L | 17 (17) | 4 (3) | 0 (0) | 19 | 2 | 0 |
M | 3 (3) | 20 (21) | 1 (0) | 1 | 21 | 0 |
H | 0 (0) | 1 (1) | 13 (14) | 0 | 2 | 14 |
Sensitivity | 0.850 (0.850) | 0.800 (0.840) | 0.929 (1.000) | 0.950 | 0.840 | 1.000 |
Specificity | 0.897 (0.923) | 0.882 (0.912) | 0.978 (0.978) | 0.949 | 0.971 | 0.956 |
Positive predictive value | 0.810 (0.850) | 0.833 (0.875) | 0.929 (0.933) | 0.905 | 0.955 | 0.875 |
Negative predictive value | 0.921 (0.923) | 0.857 (0.886) | 0.978 (1.000) | 0.974 | 0.892 | 1.000 |
Balanced accuracy | 0.874 (0.887) | 0.841 (0.876) | 0.953 (0.989) | 0.949 | 0.905 | 0.978 |
F-measure | 0.829 (0.850) | 0.816 (0.857) | 0.929 (0.966) | 0.927 | 0.894 | 0.933 |
