An Enhanced Intrusion Detection System (IDS) Framework Using Grey Wolf Optimization (GWO) and Ensemble Machine Learning (EML) Mechanisms

Developing an efficacious Intrusion Detection System (IDS) framework for ensuring the safety of WSN is one of the challenging tasks in now-a-days. For this purpose, there are various optimization and classification methodologies which are designed in the standard works, but the complexity algorithm designs the limit key problem with more computational, failure of handling huge dimensional datasets, and more misclassification results. In this, the proposed work is to design an efficient IDS framework with the needs of hybrid optimization and classification techniques. It involves the data preprocessing which is mainly accomplished to obtain the normalized dataset. After that, the hybrid Grey Wolf Optimization (GWO) technique is utilized for selecting the optimal collection of features based on the best fitness value. Finally, Ensemble Machine Learning (EML) technique predicts the document as whether normal or attack based on selected features. During performance analysis, different assessments have been utilized to evaluate the results of both existing and proposed techniques.