Research Article
[Retracted] EEG Emotion Recognition Based on Temporal and Spatial Features of Sensitive signals
Table 2
Comparison of similar experiment results
| Authors (year) | Features | Classifier | Valence (%) | Arousal (%) | Channel number |
| Guo et al. [4] (2018) | Temporal | SVM | 87.15 | 86.6 | 14 | Jin et al. [5] (2018) | Frequency + temporal | DF | 66.30 | 65.80 | 32 | Zhu [6] (2018) | Temporal + frequency + spatial | SVM | 71.00 | 70.00 | 32 | Liu and Qiao [8] (2021) | Frequency + temporal-frequency + nonlinear | SAE | 80.30 | 81.50 | 32 | Chao et al. [9] (2018) | Temporal + frequency + temporal-frequency + spatial | DBN | 70.15 | 75.92 | 32 | Yang et al. [10] (2019) | Spatial | FC (SoftMax) | 90.01 | 90.65 | 32 | Kim and Choi [11] (2021) | Temporal | FC (SoftMax) | 90.11 | 88.10 | 32 | The authors’ | Temporal + spatial | FC (SoftMax) | 92.87 | 93.23 | 14 |
|
|