Table 3.
STRAT cross-validation results
| Sensor | Vigilance | Resting | Foraging | Running | Overall Accuracy (%) | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Sen. (%) |
Spec. (%) |
Prec. (%) |
Sen. (%) |
Spec. (%) |
Prec. (%) |
Sen. (%) |
Spec. (%) |
Prec. (%) |
Sen. (%) |
Spec. (%) |
Prec. (%) |
||
| Magnetometer | 97 | 98.6 | 97.8 | 84.4 | 99.4 | 87.1 | 98.8 | 97.2 | 97.8 | 83.1 | 99.9 | 93.9 | 97.3 |
| Accelerometer | 97.1 | 98.8 | 98.1 | 85 | 99.4 | 87.1 | 99.3 | 97.8 | 98.3 | 85.9 | 99.9 | 92.1 | 97.7 |
The performance of the SVM-SVM-SVM hybrid model with magnetometer data is benchmarked against that obtained with accelerometer data reported in [10]. SVM: Support Vector Machine