An Intelligent Fuzzy Rule based Feature Selection for Effective Intrusion Detection

A challenging issue today in the field of data confidentiality is attack detection. This is because of ever increasing number of devices which are associated with the system. From the machine learning field, many unsupervised learning and supervised learning algorithms have been utilized to build the benefit of Intrusion Detection Systems (IDSs). To train a classifier, the labelled examples were utilized from the supervised learning model, but getting adequate labeled examples goes complicated and it requires the domain experts knowledge for training the model. From the real world problems some unlabeled examples can be obtained easily. Contrasted with supervised learning and unsupervised learning models, this paper proposes a new Fuzzy Rule and Information Gain Ratio based feature selection algorithm (FRFSA) for preferring the greatest number of features which are used to classify the records as normal and attacks. Moreover, the existing classifiers called SVM and LSSVM are used for effective classification. The NSL-KDD dataset is used for evaluating the proposed approach by conducting some experiments. The obtained outcomes from this work, proved that the proposed work exceeds the performance measure when compared to the existing algorithms on classification for feature selection.