Hybrid Sequential Feature Selection with Ensemble Boosting Class-based Classification Method

The rapid rise in hacking and computer network assaults throughout the world has highlighted need for more effective intrusion detection prevention solutions. system (IDS) is critical identifying abnormalities on network, which have grown size scope. IDS prevents intruders from gaining access to information field of security as a result. use detecting various types attacks. Because traffic dataset contains large number features, process selecting removing irrelevant features improves accuracy classification algorithms. For fact that dimension allows us include data, feature vector can be built by combining different features. Contains lot redundant or data cause confusion. Over-fitting issues decrease generalization capacity model. Solving such problem necessitates sequence selection methods boosted maximum relevance distance (BMRMD) method report contribution each well predictive based best set. As result, this study were chosen using BMRMD assesses redundancy determine target class optimum ensemble