基于注意力机制和深度学习的运动想象脑电信号分类方法

张玮, 赵永虹, 邱桃荣

Classification of motor imagery EEG signals based on attention mechanism and deep learning

Wei Zhang, Yonghong Zhao, TaoRong Qiu

表5 ABiLSTM?CNN与对比算法在MID?a上的分类准确率对比

Table 5 Classification accuracy of ABiLSTM?CNN and other algorithms on MID?a dataset

特征提取 分类器 平均准确率 Kalaivani et al[15] DWT K?means 72.60% Pinheiro et al[17] FFT ANN 74.96% Alomari et al[14] Coif4+IEEG ANN 71.6% Wang[20] — Em?RNN 88.27% Ours — ABiLSTM 78.62% Ours — ABiLSTM?CNN 90.52%