Table 1.
Significant summary of literature.
Fig 1.
Wi-Fi intrusion detection system.
Fig 2.
Proposed methodology.
Algorithm 1.
DT Algorithm.
Algorithm 2.
Convolutional Neural Network (CNN).
Fig 3.
Classes distribution.
Table 2.
Selected features.
Table 3.
Parameters of tree-based classifiers.
Table 4.
DNN architectures.
Table 5.
DT-RFE features.
Fig 4.
Performance evaluation.
Fig 5.
MLP.
Fig 6.
CNN.
Fig 7.
Decision tree.
Fig 8.
Random forest.
Fig 9.
Extra trees.
Fig 10.
Light GBM.
Fig 11.
MLP.
Fig 12.
CNN.
Fig 13.
Average number of misclassified instances.
Fig 14.
Feature transferability evaluation.
Fig 15.
Transferability with DT.
Fig 16.
Transferability with CNN.
Table 6.
Features for each attack.
Table 7.
Performance metrics for feature reduction of each attack.
Fig 17.
Random forest.
Fig 18.
Extra trees.
Fig 19.
Decision trees.
Fig 20.
Random forest.
Fig 21.
Extra trees.
Fig 22.
Random forest.
Fig 23.
Extra trees.
Fig 24.
Random forest.
Fig 25.
Extra trees.
Table 8.
Feature generalization using AWID dataset.
Table 9.
Comparison with state-of-the-art techniques.
Table 10.
Transferability—state-of-the-art performance.