Table 5 Cross-subject classification accuracy (in percentage %) and Kappa of state-of-the-art algorithms on the BCI IV-2b dataset.
From: CTNet: a convolutional transformer network for EEG-based motor imagery classification
|  | B01 | B02 | B03 | B04 | B05 | B06 | B07 | B08 | B09 | Average ± Std | Kappa |
|---|---|---|---|---|---|---|---|---|---|---|---|
ShallowConvNet+ 27 | 74.03 | 63.53 | 59.72 | 82.84 | 82.43 | 80.97 | 74.86 | 72.37 | 77.78 | 74.28 ± 8.13 | 0.4856 |
DeepConvNet+ 27 | 74.03 | 65.15 | 63.47 | 80.81 | 82.70 | 74.86 | 81.39 | 76.32 | 77.92 | 75.18 ± 6.84 | 0.5037 |
EEGNet+ 28 | 74.44 | 69.26 | 62.36 | 80.41 | 83.24 | 75.56 | 79.86 | 73.55 | 77.50 | 75.13 ± 6.35 | 0.5026 |
Conformer+ 53 | 71.39 | 62.35 | 65.28 | 82.97 | 80.41 | 69.31 | 75.00 | 76.32 | 78.61 | 73.52 ± 6.96 | 0.4703 |
CTNet (Proposed) | 76.25 | 71.03 | 66.39 | 81.76 | 83.11 | 77.22 | 79.17 | 73.56 | 77.92 | 76.27 ± 5.26 | 0.5252 |
