Table 5 Performance evaluation of different ML methods (%)
From: Towards a deep learning-based outlier detection approach in the context of streaming data
Dataset | Algorithm | Accuracy | TNR | FAR | FNR | Precision | Recall | F1-Score |
|---|---|---|---|---|---|---|---|---|
Musk | KNN | 81.580 | 88.390 | 11.61 | 8.347 | 83.752 | 91.653 | 91.285 |
SVM | 84.451 | 90.813 | 9.187 | 5.208 | 84.610 | 94.792 | 92.204 | |
Random forest | 89.413 | 93.684 | 6.316 | 4.989 | 90.688 | 95.011 | 93.942 | |
Proposed model | 99.241 | 97.493 | 2.507 | 1.268 | 98.903 | 98.732 | 98.985 | |
Cardiotocography | KNN | 80.614 | 87.567 | 12.438 | 11.372 | 82.326 | 88.628 | 90.567 |
SVM | 83.828 | 89.651 | 10.349 | 9.963 | 85.711 | 90.037 | 90.930 | |
Random forest | 85.653 | 92.874 | 7.126 | 7.606 | 90.014 | 92.394 | 91.507 | |
Proposed model | 99.631 | 97.682 | 2.318 | 0.986 | 99.702 | 99.014 | 99.437 |