Review Article
A Review on Machine Learning Strategies for Real-World Engineering Applications
Table 7
ML state-of-the-art systems in computer networking domain.
| | Reference | ML techniques | Applications |
| | Traffic prediction | | [191, 192] | Supervised: MLP-NN | Prediction of network traffic | | [193, 194] | Supervised: KBR, LSTM-RNN, MLP-NN | Prediction of traffic volume |
| | Traffic classification | | | | [195–197] | Supervised: SVM | Classification of traffic based on host behavior | | [198] | Unsupervised: HCA | Classification of traffic based on host behavior | | [199] | Supervised: AdaBoost | Classification of traffic based on host behavior | | [200–202] | Supervised k-NN, NBKE, BAGGING | Supervised flow feature based traffic classification | | [203–205] | Unsupervised DBSCAN, AutoClass,k-means | UnSupervised flow feature based traffic classification | | [206] | Supervised k-NN,Linear-SVM, Radial-SVM, DT, RF, extended tree, AdaBoost, Gradient-AdaBoost, NB, MLP | NFVand SDN-based traffic classification | | [207–209] | Supervised:
(i) MLP-NN
(ii) MART
(iii) Bagging DT
(iv) Extra-trees
(v) SVR
(vi) BN | Congestion inference from the estimation of different network parameters |
|
|
