Table 4 Classification precision, recall and accuracy calculated by selected classifiers at different EEG data bands when occurrence (k) is considered as the discriminative (or input) feature for classification
From: EEG-based classification of epilepsy and PNES: EEG microstate and functional brain network features
| Â | Alpha | Beta | Delta | Theta |
|---|---|---|---|---|
Accuracy, Precision, Recall | ||||
 Random Forest | 0.522, 0.522, 0.522 | 0.702, 0.763, 0.702 | 0.480, 0.480, 0.480 | 0.534, 0.498, 0.534 |
 SVM (Linear) | 0.516, 0.519, 0.516 | 0.766, 0.808, 0.766 | 0.326, 0.316, 0.326 | 0.506, 0.512, 0.506 |
 SVM (RBF) | 0.508, 0.519, 0.508 | 0.724, 0.782, 0.724 | 0.424, 0.416, 0.424 | 0.576, 0.573, 0.576 |
 Decision Tree | 0.480, 0.477, 0.480 | 0.666, 0.683, 0.666 | 0.588, 0.601, 0.588 | 0.558, 0.555, 0.558 |
 kNN | 0.534, 0.535, 0.534 | 0.688, 0.728, 0.689 | 0.602, 0.615, 0.602 | 0.646, 0.655, 0.646 |
 Gradient Boost | 0.526, 0.524, 0.526 | 0.688, 0.721, 0.688 | 0.614, 0.623, 0.614 | 0.620, 0.632, 0.620 |