intrusion detection system using an ant colony gene selection method based on information gain ratio using fuzzy rough sets

With the development of network-based technologies, intrusion detection plays an important role in modern computer systems. intrusion detection system (ids) is used to achieve higher security, and detect abnormal activities in computers or networks. the efficiency of intrusion detection systems mainly depends on the dimensions of data features. so, in the implementation of the ids, by applying the feature selection phase irrelevant and redundant features are eliminated, and as a result, the speed and accuracy of the intrusion detection system increases. applying appropriate search strategy and evaluation measure are significantly effective to feature selection. in this paper, we propose a feature selection method which uses a combination of filter and wrapper feature selection method. this method applies a modified ant colony algorithm as a search strategy on filter phase and fuzzy rough sets to calculate the information gain ratio and acquire the evaluation measure in the ant colony algorithm. then, on the wrapper phase the minimal subsets of features with first order and second order accuracies are selected. to confirm the efficiency of our proposed method, we compared this method with three other methods and with a method which is based on artificial neural networks. finally, we compared the proposed method with an ant colony optimization based method. considering the results, the proposed method, on average, has a higher accuracy than the other methods and also selects a subset of features which have a minimum length.