Table 2.
Main study: Mean ± standard deviation of classification performance metrics over the 5-fold model evaluation CV, trained on features extracted over the complete (f-)TSST, respectively.
| Scaler | Feature selection | Classifier | Accuracy [%] | F1-score [%] | Precision [%] |
|---|---|---|---|---|---|
| Standard | SFM | RF | 71.6 (5.9) | 71.2 (4.2) | 75.1 (13.1) |
| Min-Max | RFE | kNN | 67.0 (8.4) | 64.9 (11.2) | 68.1 (8.5) |
| Min-Max | SkB | MLP | 66.8 (6.7) | 62.4 (7.5) | 75.4 (14.8) |
| Min-Max | RFE | DT | 65.2 (9.2) | 65.9 (7.7) | 66.3 (11.3) |
| Min-Max | SkB | NB | 64.1 (10.0) | 57.3 (12.2) | 70.3 (13.3) |
| Standard | SkB | Ada | 63.0 (9.3) | 61.9 (7.3) | 66.3 (13.2) |
| Min-Max | SkB | SVM | 62.9 (5.6) | 53.8 (11.9) | 69.7 (7.0) |
For each evaluated classifier, the classification pipeline combination with the highest mean accuracy is shown. The classification pipelines scoring the highest metrics are highlighted in bold.