<![CDATA[As internet usage continues to increase, the risk of various cyber attacks originating from suspicious activities in networks is also growing. This study focuses on designing a machine learning model for anomaly detection, with a comparative analysis of feature selection methods including filter, wrapper, and hybrid approaches. Subsequently, to evaluate the outcomes of these feature selection methods, classification is performed on the selected features using classifier algorithms such as Random Forest, XGBoost, and MLP. Metrics used for analyzing the methods and classifier algorithms include accuracy level and processing time. The research demonstrates that feature selection can alleviate computational load without compromising accuracy. The filter feature selection method using Information Gain and the XGBoost classifier algorithm exhibit the best performance in terms of accuracy and short execution time.]]>
Copyrights © 2023
