Table 3 Proposed algorithm results using MSR Action dataset
Dataset | Classifier | Sequence | ACC (%) | TPR | FPR | PPV (%) | FDR (%) | FNR (%) | AUC |
|---|---|---|---|---|---|---|---|---|---|
ssMSR Action dataset | M-class SVM | S1:Cv1 | 100 | 1.00 | 0.00 | 100 | 0.00 | 0.00 | 1.00 |
S1:Cv14 | 100 | 1.00 | 0.00 | 100 | 0.00 | 0.00 | 1.00 | ||
S1:Cv16 | 100 | 0.99 | 0.00 | 100 | 0.00 | 0.00 | 0.99 | ||
K-Nearest neighbor | S1:Cv1 | 97.30 | 0.97 | 0.03 | 97.30 | 2.70 | 2.70 | 0.97 | |
S1:Cv14 | 92.50 | 0.94 | 0.05 | 91.15 | 8.85 | 2.70 | 0.94 | ||
S1:Cv16 | 97.30 | 0.97 | 0.02 | 97.00 | 3.05 | 2.70 | 0.97 | ||
Ensemble boosted tree | S1:Cv1 | 100 | 0.99 | 0.00 | 100 | 0.00 | 0.10 | 0.99 | |
S1:Cv14 | 100 | 1.00 | 0.00 | 100 | 0.00 | 0.00 | 1.00 | ||
S1:Cv16 | 99.80 | 0.99 | 0.00 | 100 | 0.00 | 0.20 | 0.99 |