基于时空注意力机制的轻量级脑纹识别算法
|
|
方芳,严军,郭红想,王勇
|
Lightweight brainprint recognition algorithm based on spatio-temporal attention mechanism
|
|
Fang FANG,Jun YAN,Hongxiang GUO,Yong WANG
|
|
| 表 5 Physionet数据集的运动想象数据比较 |
| Tab.5 Comparison of motor imagery data for Physionet dataset |
|
| 方法 | slot/s | N | ACC/% | EER/% | Np/106 | COH_CNN[21] COH_CNN[21] | 1 1 | 19 15 | 98.22 97.74 | — — | — — | | CNN-LSTM[8] | 1 1 | 16 64 | 99.58 99.58 | 0.410 0.410 | 1927.50 — | | 多任务对抗学习[22] | 1 | 64 | 99.20 | — | — | | BGWO-SVM[23] | 1 | 23 | 94.13 | — | — | | EPI-CGAN[24] | 1 | 64 | 99.02 | — | — | | PCA+SVM[25] | 2 | 64 | 99.91 | — | — | | DNN[26] | 4 | 64 | 97.81 | — | — | | GCT-EEGNet[27] | 1 | 32 | 98.90 | 0.004 | 0.17 | | ResNet18[28] | 1 | 64 | 99.59 | — | 11.25 | 提出方法 提出方法 提出方法 提出方法 提出方法 | 1 1 1 1 1 | 15 16 19 32 64 | 98.52 98.63 98.86 99.48 99.97 | 0.001 0.001 0.001 0.001 0.000 | 0.29 0.29 0.29 0.30 0.32 |
|
|
|