Table 3.
Accuracy comparison for combination of classifiers and feature extraction methods.
| (a) Valence | ||||
| Feature extraction method | ||||
|
| ||||
| Classifier type | Accuracy (%) | PCA | NPCA | KLD |
| SVM | 75.45 | 78.04 | 77.51 | |
| KNN | 74.81 | 76.42 | 76.05 | |
| BN | 75.32 | 77.41 | 76.13 | |
|
| ||||
| (b) Arousal | ||||
| Feature extraction method | ||||
|
| ||||
| Classifier type | Accuracy (%) | PCA | NPCA | KLD |
| SVM | 76.26 | 77.25 | 78.23 | |
| KNN | 73.45 | 74.91 | 75.63 | |
| BN | 74.96 | 75.56 | 76.91 | |