Table 7 Classification results based on 2D and 3DCNN model using multi-electrode
From: Automatic seizure detection using three-dimensional CNN based on multi-channel EEG
| Â | Prediction | Accuracy | Specificity | Sensitivity | |||
|---|---|---|---|---|---|---|---|
Inter-ictal | Pre-ictal | ictal | |||||
3D CNN | Inter-ictal | 861 | 81 | 58 | 90.73% | 93.05% | 86.10% |
Pre-ictal | 77 | 894 | 29 | 92.57% | 94.15% | 89.40% | |
Ictal | 62 | 36 | 902 | 93.83% | 94.15% | 90.20% | |
2D CNN | Inter-ictal | 822 | 119 | 59 | 88.13% | 91.10% | 82.20% |
Pre-ictal | 107 | 838 | 55 | 89.20% | 91.90% | 83.80% | |
Ictal | 71 | 43 | 886 | 92.40% | 94.30% | 88.60% | |