Table 4 Performance of the proposed CFNN using different window sizes.
From: Detecting emotions through EEG signals based on modified convolutional fuzzy neural network
Window size | Accuracy* | Precision | F1-score | Recall |
|---|---|---|---|---|
4 | 97.06% (96.98–97.14) | 96.50% | 96.58% | 96.67% |
8 | 97.24% (97.17–97.31) | 96.47% | 96.79% | 97.12% |
16 | 97.36% (97.29–97.43) | 94.85% | 96.87% | 98.98% |
32 | 97.88% (97.83–97.93) | 99.12% | 98.15% | 97.19% |
64 | 98.54% (98.49–98.59) | 96.47% | 96.79% | 97.12% |
128 | 98.70% (98.66–98.74) | 99.01% | 98.49% | 97.98% |
