Table 3 Performance comparison between different ML/DL models with the proposed model.
ML and DL Techniques | Accuracy (%) | Precision (%) | Recall (%) | F1-Score (%) | Specificity (%) |
|---|---|---|---|---|---|
Decision Tree | 75 | 71 | 56 | 62 | 78 |
Random Forest | 77 | 71 | 56 | 62 | 78 |
SVC | 77 | 80 | 67 | 73 | 83 |
SVC-gridCV | 78 | 73 | 61 | 67 | 78 |
Logistic Regression | 79 | 78 | 65 | 71 | 88 |
RNN | 49 | 53 | 50 | 51 | 48 |
KNN | 77 | 73 | 68 | 70 | 83 |
XGBoost | 76 | 77 | 76 | 76 | 83 |
Extra trees | 79 | 79 | 79 | 79 | 85 |
DNN | 79 | 79 | 79 | 79 | 83 |
AdaBoost | 85 | 85 | 85 | 85 | 88 |
NaiveBayes | 67 | 74 | 67 | 63 | 94 |
Proposed optimized Lightweight MLP Model | 92 | 100 | 83 | 90 | 100 |
