Table 6 Comparison of the classification performance of the base learners and their ensemble using the proposed scheme.
From: A fuzzy rank-based ensemble of CNN models for classification of cervical cytology
Dataset | Method | Accuracy(%) | Precision (%) | Recall (%) | F1-Score (%) |
|---|---|---|---|---|---|
SIPaKMeD 2-Class | Inception v3 | 97.71 | 97.65 | 97.75 | 97.70 |
Xception | 95.42 | 95.61 | 95.22 | 95.37 | |
DenseNet-169 | 96.89 | 96.11 | 95.65 | 93.82 | |
Proposed ensemble | 98.55 | 98.57 | 98.52 | 98.54 | |
SIPaKMeD 5-Class | Inception v3 | 94.36 | 94.40 | 94.37 | 94.38 |
Xception | 94.00 | 93.94 | 94.00 | 93.97 | |
DenseNet-169 | 93.26 | 93.34 | 93.27 | 93.30 | |
Proposed ensemble | 95.43 | 95.34 | 95.38 | 95.36 | |
Mendeley LBC | Inception v3 | 97.69 | 97.64 | 97.67 | 97.65 |
Xception | 98.04 | 98.11 | 98.26 | 98.18 | |
DenseNet-169 | 98.07 | 97.47 | 97.53 | 97.50 | |
Proposed ensemble | 99.23 | 99.13 | 99.23 | 99.18 |
