Feature selection using genetic algorithm to improve classification in network intrusion detection system
Andrey Ferriyan, Achmad Husni Thamrin, Keiji Takeda, Jun Murai · 2017
In this paper, we present Genetic Algorithm based optimized feature selections for intrusion detection systems. We used one-point crossover for the Genetic Algorithm parameters instead of two-point crossover used by the previous research as it one-point crossover is faster. For evaluations, we used the NSL-KDD Cup 99 data set and we modified the data set by looking into to the recent attacks, hence making the data set more relevant to the current situations. Several classifiers were used on these data sets and we found that Random Forest gave the best results in terms of the classification rate and the training time. The results also showed that our parameters performed better in these two metrics and the classifications using our optimized features on the modified data sets gave mixed results compared to ones with the original features.