基于多尺度滑窗注意力时序卷积网络的脑电信号分类

李宪华,杜鹏飞,宋韬,邱洵,蔡钰

EEG signal classification based on multi-scale sliding-window attention temporal convolutional networks

Xianhua LI,Pengfei DU,Tao SONG,Xun QIU,Yu CAI

表 2 不同分类方法在BCI Competition IV 2b数据集上的分类准确率

Tab.2 Classification accuracy of different methods on BCI Competition IV 2b dataset

分类方法 Acc /% $\overline{\mathrm{Acc}} $/% Kap p B01 B02 B03 B04 B05 B06 B07 B08 B09 FBCSP 70.00 60.36 60.94 97.50 93.12 80.63 78.13 92.50 86.88 80.00 0.60 0.0100 ConvNet 78.56 50.00 51.56 96.88 93.13 85.31 83.75 91.56 85.62 79.37 0.59 0.0039 EEGNet 75.94 57.64 58.43 98.13 81.25 88.75 84.06 93.44 89.69 80.48 0.61 0.0039 DRDA 83.37 62.86 63.63 95.94 93.56 88.19 85.00 95.25 90.00 83.98 0.68 0.0273 IFBCLNet 79.82 80.40 73.04 97.71 96.33 88.84 90.08 93.47 90.20 87.76 0.76 0.4961 Conformer 82.50 65.71 63.75 98.44 86.56 90.31 87.81 94.38 92.19 84.63 0.69 1.0000 MSWATCN 84.06 63.21 80.93 98.15 96.25 89.69 87.50 93.75 91.88 87.27 0.75 —