Table 7 Machine learning performance with NasNetMobile backbone.
Model | \(\boldsymbol{\alpha }\) | \({\varvec{\pi}}\) | \({\varvec{\rho}}\) | \({\varvec{\phi}}1\) | \({\varvec{\sigma}}\) | \({\varvec{\lambda}}\) | \({\varvec{\kappa}}\) | \({\varvec{\eta}}\) |
|---|---|---|---|---|---|---|---|---|
Random forest classifier | 85.74 | 86.52 | 82.04 | 83.26 | 82.04 | 97.03 | 77.07 | 72.39 |
Decision tree classifier | 83.55 | 82.19 | 82.84 | 82.33 | 82.84 | 94.23 | 74.47 | 70.63 |
Adaboost classifier | 67.2 | 61.47 | 60.09 | 59.47 | 60.09 | 78.32 | 46.14 | 46.18 |
K Neighbors classifier | 94.42 | 94.45 | 93.2 | 93.74 | 93.2 | 98.91 | 91.19 | 88.46 |
Gaussian Nb | 94.71 | 94.33 | 94.32 | 94.32 | 94.32 | 95.8 | 91.71 | 89.34 |
Logistic regression | 98.92 | 98.77 | 98.85 | 98.81 | 98.85 | 99.92 | 98.31 | 97.65 |
