A filter-based feature selection model for anomaly-based intrusion detection systems

Feature selection is an important factor in modeling anomaly-based intrusion detection systems. An irrelevant feature can result in overfitting and affect the modeling power of classification algorithms. The objective of feature selection is to remove irrelevant and redundant attributes from the dataset to improve the predictive power of a classification algorithm. In this paper, we introduce a filter-based feature selection model for anomaly-based intrusion detection systems. The proposed model evaluates the features based on information gain by considering consistency, dependency, information, and distance of each feature. The experimental results show that our proposed model has a key effect in reducing computational and time complexity. The accuracy of the proposed model was measured as 99.70 % and 99.90% for the ISCX and NSL-KDD datasets respectively.