Intrusion detection algorithms based on correlation information entropy and binary particle swarm optimization

In current intrusion detection, redundant features often lead to the degradation of detection accuracy. Aiming at this problem, an intrusion detection algorithm based on correlation information entropy and binary particle swarm optimization algorithm was proposed. Correlation information entropy was used to sort features. This can filter irrelevant features. So the feature dimension was reduced. Then some better subsets that were gotten from feature sorting were used as the part initial population. In this way, the following particle swarm optimization algorithm would have a good starting point. The test results showed that the better classification performance was obtained according to the selected optimal feature subset, and the testing time of the system was reduced effectively.