Table 1.
Overview of current literature in FFD.
Fig 1.
Proposed framework for FFD.
Table 2.
ECH Dataset 2023 (Header view).
Table 3.
IEEE-CIS dataset sample.
Fig 2.
Flowchart data balancing algorithm (SMOTE).
Fig 3.
RMGACNet model architecture.
Table 4.
Optimal hyper parameters for RMGACNet.
Fig 4.
Data correlation of all features (ECH dataset).
Fig 5.
Data correlation of top 10 features (IEEECIS dataset).
Fig 6.
Data before and after applying SMOTE algorithm.
Table 5.
Selected features and their BiLSTM scores on ECH dataset (Sfeat: selected feature).
Fig 7.
Top 40 features selected by BiLSTM from IEEECIS dataset.
Table 6.
Proposed framework performance values on the ECH dataset.
Table 7.
Proposed Framework Performance values on the IEEE-CIS dataset.
Table 8.
Statistical analysis tests on IEEE-CIS and ECH dataset.
Fig 8.
Confusion matrices of RMGACNet on ECH and IEEE-CIS datasets.
Fig 9.
ROC curves comparison of proposed and existing methods.
Fig 10.
Execution time of classifiers.
Fig 11.
RMGACNet model training accuracy loss analysis.
Fig 12.
RMGACNet parameter sensitivty analysis.
Fig 13.
RMGACNet scalability and execution analysis with different dataset size.
Fig 14.
Memory usage and model size comparison across various models.