Table 3 Comparative analysis of EADCD-TIPAIT approach with existing methodologies17]– [18,41]– [42.
Approach | \(\:\varvec{A}\varvec{c}\varvec{c}{\varvec{u}}_{\varvec{r}\varvec{a}\varvec{c}\varvec{y}}\) | \(\:\varvec{P}\varvec{r}\varvec{e}{\varvec{c}}_{\varvec{n}}\) | \(\:{\varvec{F}1}_{\varvec{s}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\) | \(\:\varvec{R}\varvec{e}\varvec{c}{\varvec{a}}_{\varvec{l}}\) |
|---|---|---|---|---|
SVM Classifier | 89.72 | 90.65 | 91.91 | 89.52 |
AdaBoost Method | 94.40 | 93.61 | 91.92 | 92.59 |
DT Methodology | 91.99 | 94.16 | 89.48 | 90.12 |
ET Model | 91.99 | 94.74 | 90.51 | 92.46 |
GB | 93.60 | 91.67 | 93.38 | 92.37 |
K-NN Algorithm | 94.41 | 92.96 | 90.93 | 92.18 |
LR | 94.42 | 92.16 | 94.94 | 90.41 |
NB Classifier | 94.41 | 93.56 | 90.91 | 90.83 |
MC-ViT | 92.06 | 94.24 | 89.55 | 90.20 |
ResNet | 92.04 | 94.81 | 90.56 | 92.54 |
VGGNet | 93.67 | 91.75 | 93.46 | 92.44 |
EADCD-TIPAIT | 95.00 | 95.09 | 94.99 | 94.94 |
