Table 5.
Comparison of performance metrics of different machine learning models (results of class 1).
| Accuracy | Precision | Recall | F1-Score | |
|---|---|---|---|---|
| Train set | ||||
| Random Forest | 0.74 | 0.93 | 0.73 | 0.82 |
| XGBoost | 0.73 | 0.86 | 0.75 | 0.80 |
| SVM | 0.75 | 0.85 | 0.78 | 0.81 |
| Neural Network | 0.76 | 0.78 | 0.90 | 0.83 |
| Test set | ||||
| Random Forest | 0.75 | 0.92 | 0.76 | 0.83 |
| XGBoost | 0.75 | 0.84 | 0.81 | 0.82 |
| SVM | 0.68 | 0.78 | 0.74 | 0.76 |
| Neural Network | 0.71 | 0.72 | 0.84 | 0.77 |
Class 1 results; target variable: total PA higher or lower than 600 MET·min/week; features included in the model involved age categories, sex, BMI, crowding index, education, marital status, job location during lockdown, auto-declared PA change during lockdown, type of PA during lockdown, employment status, and sitting time.