Table 4 Confusion matrix and performance measures for SVM classification of wheat genotypes using Sigmoid and Degree-1 polynomial kernels.
From: Ensemble and optimization algorithm in support vector machines for classification of wheat genotypes
Performance statistics | Actual | |||||
|---|---|---|---|---|---|---|
Sigmoid kernel | Degree-1 polynomial kernel | |||||
L | M | H | L | M | H | |
Prediction | ||||||
L | 19 | 3 | 0 | 16 | 2 | 0 |
M | 1 | 21 | 3 | 4 | 21 | 1 |
H | 0 | 1 | 11 | 0 | 2 | 13 |
Sensitivity | 0.950 | 0.840 | 0.786 | 0.800 | 0.840 | 0.929 |
Specificity | 0.923 | 0.882 | 0.978 | 0.949 | 0.853 | 0.956 |
Positive predictive value | 0.864 | 0.840 | 0.917 | 0.889 | 0.808 | 0.867 |
Negative predictive value | 0.973 | 0.882 | 0.936 | 0.902 | 0.879 | 0.977 |
Balanced accuracy | 0.937 | 0.861 | 0.882 | 0.874 | 0.846 | 0.942 |
F-measure | 0.905 | 0.840 | 0.846 | 0.842 | 0.824 | 0.897 |
