Impact of Feature Selection on the Performance of Wireless Intrusion Detection Systems
In this paper, the authors study the impact of the optimization of the feature set of wireless intrusion detection systems on the performance and learning time of different types of classifiers based on neural networks. The optimal set of features is selected using a hybrid selection model. In this approach, the wireless frame attributes are first ranked according to a score assigned by the information gain ratio measure. K-means classifier is then used to build the optimal subset of features that maximizes the accuracy of the detectors while reducing their learning time.