A tree-based stacking ensemble technique with feature selection for network intrusion detection

Several studies have used machine learning algorithms to develop intrusion systems (IDS), which differentiate anomalous behaviours from the normal activities of network systems. Due ease automated data collection and subsequently an increased size collected on traffic activities, complexity analysis is increasing exponentially. A particular issue, due statistical computation limitations, a single classifier may not perform well for large scale as existent in modern IDS contexts. Ensemble methods been explored literature such big Although more complicated requiring additional computation, has note that ensemble can result better accuracy than classifiers different classification contexts, it interesting explore how approaches IDS. In this research, we introduce tree-based stacking technique (SET) test effectiveness proposed model two datasets (NSL-KDD UNSW-NB15). We further enhance incorporate feature selection techniques select best relevant features with SET. comprehensive performance shows our identify anomaly other existing models. This implies potentials system cybersecurity Internet Things (IoT) networks.