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

Tab.1 Classification accuracy of different methods on BCI Competition IV 2a dataset

分类方法 Acc/% $\overline{\mathrm{Acc}} $/% Kap p A01 A02 A03 A04 A05 A06 A07 A08 A09 FBCSP 76.00 56.50 81.25 61.00 55.00 45.25 82.75 81.25 70.75 67.75 0.57 0.0001 ConvNet 76.39 55.21 89.24 74.65 56.94 54.17 92.71 77.08 76.39 72.53 0.63 0.0022 EEGNet 85.76 61.46 88.54 67.01 55.90 52.08 89.58 83.33 79.51 74.50 0.66 0.0031 DRDA 83.19 55.14 87.43 75.28 62.29 57.15 86.18 83.61 82.00 74.75 0.66 0.0014 IFBCLNet 87.18 58.65 92.67 78.07 70.65 60.46 92.41 82.28 86.74 78.79 0.72 0.0960 Conformer 88.19 61.46 93.40 78.13 52.08 65.28 92.36 88.19 88.89 78.66 0.72 0.5140 MSWATCN 89.24 64.58 93.40 74.65 73.26 62.85 93.75 85.42 86.46 80.40 0.74 —