82 | | * Developed CNN using pretrained model (ResNet-18) with the last layer excluded. |
83 | | * Developed SVM as a baseline to make sure CNN was running efficiently. |
84 | | * Performed cross-validation to make sure the models were not overfitting. |
85 | | * Both models reached >95% accuracy. |
| 82 | * Developed a CNN for RFI detection using pre-trained model (ResNet-18) with the last classification layer modified and retrained |
| 83 | * Developed SVM as a baseline to assess the efficiency of the CNN approach (potentially underutilization) |
| 84 | * Performed cross-validation to make sure the models were not overfitting |
| 85 | * Both models reached >95% accuracy |