Machine learning-based network intrusion detection for big and imbalanced data using oversampling, stacking feature embedding and feature extraction

Journal of Big Data

Table 15 Comparison analysis of CIC-IDS2018 dataset

SI. No.	Authors	Data balancing	Dimension reduction	Algorithm	Selected feature	Accuracy (%)
1	[33]	–	HFS	LightGBM	24	97.73
2	[43]	–	–	CNN +RNN	–	97.75
3	[41]	–	–	CNN	–	91.50
4	Our proposal	RO	SFE-PCA	DT	10	99.94
5	Our proposal	RO	SFE-PCA	RF	10	99.94