Table 8.
EEG-based DDD Accuracies obtained by using Regression Models and Various Features and Ground Truths.
| Ref. No. | Features | Models | Acc (%) |
GND Truth No. |
|---|---|---|---|---|
| [77] | LBP: Log-transformed SHBP (1–30 Hz) | RBF-SVR |
r2 = 0.932 and RMSE = 0.124 (s) |
1 |
| [31] | Wavelet+: Normalized log energy of the wavelet-packet coefficients, selected by FMI method | MLR | r2 = 0.778 | 22 |
| [62] | PBP: θ and α power | SONFIN |
r2 = 0.613 and RMSE = 0.360 (s) |
1 |
| [50] | FFT+: α burst duration, mean amplitude, relative amplitude, amplitude variance, wave duration variance, wave similarity, slope smoothness measurement | MLP | r2 = 0.272 | 17 |