Research Article
Robust Deep Network with Maximum Correntropy Criterion for Seizure Detection
Table 4
Comparison with other methods.
| Method | Pt01 | Pt02 | Pt03 | Pt04 | Pt05 | Pt06 | Avg | SEN* | SPE* | SEN | SPE | SEN | SPE | SEN | SPE | SEN | SPE | SEN | SPE | SEN | SPE |
| SVM | 1.00 | 0.96 | 1.00 | 0.89 | 1.00 | 0.93 | 0.99 | 0.95 | 1.00 | 0.96 | 1.00 | 0.78 | 1.00 | 0.91 | SVD(3) + SVM [10] | 0.45 | 1.00 | 0.72 | 0.99 | 0.96 | 0.99 | 0.84 | 0.95 | 0.46 | 0.98 | 0.64 | 0.97 | 0.68 | 0.98 | SVD(10) + SVM [10] | 0.61 | 1.00 | 0.76 | 0.99 | 0.99 | 1.00 | 0.80 | 0.95 | 0.84 | 0.93 | 0.95 | 0.96 | 0.83 | 0.97 | R-SAE(3) | 1.00 | 0.99 | 0.99 | 0.99 | 0.98 | 0.99 | 1.00 | 0.99 | 1.00 | 0.99 | 0.92 | 0.98 | 0.98 | 0.99 | R-SAE(10) (ours) | 1.00 | 0.99 | 1.00 | 0.99 | 1.00 | 0.99 | 1.00 | 0.99 | 1.00 | 0.99 | 0.99 | 0.97 | 1.00 | 0.99 |
|
|
SEN indicates sensitivity and SPE is specificity.
|