Table 7 Performance metrics of the best performing classifier (‘fair’ case) when the age 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) | Youngest subjects (80%) | 100.00% | 100.00 | 100.00% |
Oldest subjects (80%) | 100.00% | 100.00 | 100.00% | ||
Random selection of users | 97.38% | 100.00 | 98.67% | ||
All (fair distribution) | 97.37% | 100.00 | 98.67% | ||
Erciyes | Own selection of features SVM (quadratic kernel) | All (fair distribution) | 99.62% | 99.18 | 99.40% |
Youngest subjects (80%) | 98.74% | 100.00 | 99.37% | ||
Oldest subjects (80%) | 98.07% | 100.00 | 99.03% | ||
Random selection of users | 97.83% | 98.43 | 98.12% | ||
SisFall | HCTSA features SVM (cubic kernel) | Youngest subjects (80%) | n.c. | 99.56 | n.c. |
Oldest 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% | ||
Subjects older than 50 | 98.03% | 98.66 | 98.34% | ||
Subjects younger than 50 | 30.67% | 99.32 | 55.19% | ||
UMAFall | Own selection of features KNN (Euclidean. 10 neighbors) | Youngest subjects (80%) | n.c. | 100.00 | n.c. |
Oldest subjects (80%) | 100.00% | 100.00 | 100.00% | ||
All (fair distribution) | 98.93% | 98.73 | 98.83% | ||
Random selection of users | 98.28% | 97.05 | 97.66% | ||
UP-Fall | Own selection of features SVM (linear kernel) | Oldest 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% | ||
Youngest subjects (80%) | 97.62% | 97.83 | 97.72% |
