Table 3.
Approaches | Model | CV performance | Testing performance | ||||||
---|---|---|---|---|---|---|---|---|---|
AC | PR | RE | FM | AC | PR | RE | FM | ||
Regular ML approach | DT | 94.4 | 94.98 | 94.51 | 94.56 | 92.11 | 92.11 | 92.11 | 92.1 |
KNN | 89.85 | 90.63 | 89.85 | 89.51 | 86.67 | 87.4 | 86.67 | 86.17 | |
NB | 81.84 | 82.38 | 81.84 | 81.01 | 83.68 | 84.33 | 83.68 | 83.0 | |
RF | 97.01 | 96.74 | 96.75 | 96.68 | 94.04 | 94.05 | 94.04 | 94.03 | |
SVM | 94.73 | 94.94 | 94.73 | 94.66 | 93.86 | 93.85 | 93.86 | 93.84 | |
| |||||||||
DL approach | The optimized deep RNN | 97.92 | 97.77 | 97.79 | 97.78 | 95.18 | 95.44 | 95.18 | 95.21 |