Table 6 SVM models quality in terms of precision, recall and F1
From: Private pathological assessment via machine learning and homomorphic encryption
Kernel | |||||
|---|---|---|---|---|---|
Dataset | Metric | Linear | Poly | RBF | Sigmoid |
CHD | Precision | 0.73 | 0.70 | 0.73 | 0.75 |
Recall | 0.73 | 0.70 | 0.73 | 0.75 | |
F1 | 0.73 | 0.70 | 0.73 | 0.75 | |
WBC | Precision | 0.96 | 0.90 | 0.97 | 0.97 |
Recall | 0.95 | 0.92 | 0.95 | 0.95 | |
F1 | 0.95 | 0.91 | 0.96 | 0.96 | |
BreastMNIST | Precision | − | − | 0.80 | − |
Recall | − | − | 0.81 | − | |
F1 | − | − | 0.80 | − | |
PneumoniaMNIST | Precision | − | − | 0.87 | − |
Recall | − | − | 0.85 | − | |
F1 | − | − | 0.85 | − | |