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

Fig 1.

A typical SDIoT scenario.

More »

Fig 1 Expand

Table 1.

Names of each attack and category.

More »

Table 1 Expand

Fig 2.

Process of SMOTE during synthesis and eliminating noisy samples using ENN.

More »

Fig 2 Expand

Fig 3.

High-level design of anomaly detection framework in SDIoT.

More »

Fig 3 Expand

Fig 4.

Flow diagram of the ML-based anomaly detection model.

More »

Fig 4 Expand

Table 2.

Selected features for FSMI model with both datasets.

More »

Table 2 Expand

Table 3.

Performance metrics for the model.

More »

Table 3 Expand

Table 4.

Parameter settings of different models.

More »

Table 4 Expand

Table 5.

Number of Instances (before and after balancing).

More »

Table 5 Expand

Fig 5.

Results of accuracy with increased features.

(a) CIC-IoT-2023 dataset, (b) NSL KDD99 dataset.

More »

Fig 5 Expand

Table 6.

Selected features and their description.

More »

Table 6 Expand

Table 7.

Evaluation of SFMI without SMOTE-ENN (in %).

More »

Table 7 Expand

Table 8.

Evaluation of SFMI with SMOTE-ENN (in %).

More »

Table 8 Expand

Table 9.

Evaluation of BFE with SMOTE-ENN (in %).

More »

Table 9 Expand

Table 10.

Evaluation of SMOTE-ENN+SFMI+PCA (in %).

More »

Table 10 Expand

Table 11.

Results comparison with classical machine learning method.

More »

Table 11 Expand

Fig 6.

Multiclass comparison of algorithms on test data for KDDCup 99.

(a) Accuracy, (b) Precision, (c) Recall, (d) F1-Score.

More »

Fig 6 Expand

Fig 7.

Multiclass comparison of algorithms on test data for CIC-IoT23.

(a) Accuracy, (b) Precision, (c) Recall, (d) F1-Score.

More »

Fig 7 Expand

Fig 8.

Comparison between proposed FS vs classical FS.

(a) KDD Cup99, (b) CIC-IoT 2023.

More »

Fig 8 Expand

Table 12.

Testing time (Sec) of different models with feature selection.

More »

Table 12 Expand

Fig 9.

Comparison between SMOTE and SMOTE-ENN in execution time with F-15 and F-10.

More »

Fig 9 Expand

Fig 10.

Testing time (sec) of proposed model with PCA vs without PCA.

(a) KDD Cup99, (b) CIC-IoT 2023.

More »

Fig 10 Expand

Fig 11.

CPU and Memory usage of both the datasets.

(a) CPU Usage, (b) Memory Usage.

More »

Fig 11 Expand