Optimal feature selection for firewall log analysis using Machine learning and Hybrid Metaheuristic algorithms

Abstract

Firewall log classification is important to monitor network traffic. Most firewall log classification via machine learning has shown good result by network-related features and classifiers. However, feature with many dimensions take a lot of time to do classification. In this paper, we applied a method of feature selection using optimized bee swarm optimization with reinforcement learning. We evaluated average performance by accuracy, macro-averaged precision, macro-averaged recall, and macro-averaged F1 score in 5-stratified folds using a random forest, k-nearest neighbor, and naïve bayes classifier. As a results, it could be applied for an automatic firewall log analysis system.