Research Article
DE-CNN: An Improved Identity Recognition Algorithm Based on the Emotional Electroencephalography
Table 5
Comparison of the proposed method with some state-of-the-art EEG-based identification methods.
| Name | Train time (s) | Rank-1 | Parameters | EER |
| CNN + LSTM [9] | 278 | 0.98 ± 0.002 | 32361999 | 0.0121 | D-LSTM [16] | 60 | 0.76 ± 0.04 | 1060943 | 0.011 | DE-CNN | 2 | 0.997 ± 0.0028 | 7918095 | 0.002 | PSD-CNN | 2 | 0.934 ± 0.0034 | 7918095 | 0.021 |
|
|