Table 1.
Data repository.
Fig 1.
Trained dataset after preprocessing.
Fig 2.
Test dataset after preprocessing.
Fig 3.
Feature extraction of proposed NIDS.
Fig 4.
Warning dialog box of proposed NIDS.
Fig 5.
Proposed architecture of fast R–CNN.
Table 2.
Optimal hyper–parameters to train the proposed model.
Table 3.
Environmental setup.
Fig 6.
(a). PCA and eigen values of proposed model. (b). SVD matrix results of proposed model.
Fig 7.
(a). Proposed result using direct method. (b). Proposed result using gradient boost regression. (c). Proposed result of hybrid method using In–Built MATLAB. (d). Proposed result of mean square error (MSE).
Fig 8.
Overall accuracy comparison for different algorithms.
Fig 9.
Accuracy comparison for individual cyber attack with various algorithms.
Fig 10.
Performance metrics comparison of various algorithms.
Fig 11.
Performance comparison analysis.
Fig 12.
Accuracy comparison with various datasets.