Table 5 Performance metrics of the best performing classifier (‘fair’ case) when the height is used as a criterion to select the subjects of the training subset.
Dataset | Features and algorithm | Subjects included in the training subset | Se (%) | Sp (%) | \(\sqrt{Se\cdot Sp}\) (%) |
|---|---|---|---|---|---|
DOFDA | HCTSA features Naive Bayes (Gaussian) | Tallest subjects (80%) | 98.65 | 100.00 | 99.32 |
Random selection of users | 97.38 | 100.00 | 98.67 | ||
All (fair distribution) | 97.37 | 100.00 | 98.67 | ||
Shortest subjects (80%) | 93.59 | 100.00 | 96.74 | ||
Erciyes | Own selection of features SVM (quadratic kernel) | Tallest subjects (80%) | 100.00 | 100.00 | 100.00 |
All (fair distribution) | 99.62 | 99.18 | 99.40 | ||
Random selection of users | 97.83 | 98.43 | 98.12 | ||
Shortest subjects (80%) | 91.22 | 93.73 | 92.46 | ||
SisFall | HCTSA features SVM (cubic kernel) | Tallest subjects (80%) | 100.00 | 100.00 | 100.00 |
All (fair distribution) | 99.78 | 99.96 | 99.87 | ||
Random selection of users | 99.74 | 99.96 | 99.85 | ||
Shortest subjects (80%) | 99.78 | 99.83 | 99.80 | ||
UMAFall | Own selection of features KNN (Euclidean. 10 neighbors) | All (fair distribution) | 98.93 | 98.73 | 98.83 |
Shortest subjects (80%) | 100.00 | 96.05 | 98.01 | ||
Random selection of users | 98.28 | 97.05 | 97.66 | ||
Tallest subjects (80%) | 77.78 | 96.67 | 86.71 | ||
UP-Fall | Own selection of features SVM (linear kernel) | Tallest subjects (80%) | 100.00 | 97.83 | 98.91 |
Shortest subjects (80%) | 100.00 | 97.67 | 98.83 | ||
All (fair distribution) | 99.59 | 98.02 | 98.80 | ||
Random selection of users | 99.65 | 97.56 | 98.60 |
