Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Overview of current literature in FFD.

More »

Table 1 Expand

Fig 1.

Proposed framework for FFD.

More »

Fig 1 Expand

Table 2.

ECH Dataset 2023 (Header view).

More »

Table 2 Expand

Table 3.

IEEE-CIS dataset sample.

More »

Table 3 Expand

Fig 2.

Flowchart data balancing algorithm (SMOTE).

More »

Fig 2 Expand

Fig 3.

RMGACNet model architecture.

More »

Fig 3 Expand

Table 4.

Optimal hyper parameters for RMGACNet.

More »

Table 4 Expand

Fig 4.

Data correlation of all features (ECH dataset).

More »

Fig 4 Expand

Fig 5.

Data correlation of top 10 features (IEEECIS dataset).

More »

Fig 5 Expand

Fig 6.

Data before and after applying SMOTE algorithm.

More »

Fig 6 Expand

Table 5.

Selected features and their BiLSTM scores on ECH dataset (Sfeat: selected feature).

More »

Table 5 Expand

Fig 7.

Top 40 features selected by BiLSTM from IEEECIS dataset.

More »

Fig 7 Expand

Table 6.

Proposed framework performance values on the ECH dataset.

More »

Table 6 Expand

Table 7.

Proposed Framework Performance values on the IEEE-CIS dataset.

More »

Table 7 Expand

Table 8.

Statistical analysis tests on IEEE-CIS and ECH dataset.

More »

Table 8 Expand

Fig 8.

Confusion matrices of RMGACNet on ECH and IEEE-CIS datasets.

More »

Fig 8 Expand

Fig 9.

ROC curves comparison of proposed and existing methods.

More »

Fig 9 Expand

Fig 10.

Execution time of classifiers.

More »

Fig 10 Expand

Fig 11.

RMGACNet model training accuracy loss analysis.

More »

Fig 11 Expand

Fig 12.

RMGACNet parameter sensitivty analysis.

More »

Fig 12 Expand

Fig 13.

RMGACNet scalability and execution analysis with different dataset size.

More »

Fig 13 Expand

Fig 14.

Memory usage and model size comparison across various models.

More »

Fig 14 Expand