Quantum Particle swarm optimization based network Intrusion feature selection and Detection

摘要: Abstract Considering the relevance among features, which filter-based feature selection method fails to deal with, a kind of hybrid quantum particle swarm optimization and support vector machines based network intrusion wrapper algorithm is put forward. The subset features represented using superposition characteristic probability representation, can make single represent several states, thus potentially increases population diversity. Every in stands for selected features. A probabilistic mutation adopted avoid local optimal taboo search table used enlarge swarm's space repeated computation. fitness defined as correct classification percentage by SVM training set whose patterns are only results experiments demonstrate that proposed be an effective efficient way detection via data sets KDD cup 99.