An Intrusion Detection Feature Selection Method Based on Improved Fireworks Algorithm

Abstract

With the rapid development of network technology, network intrusion has become increasingly frequent. In network intrusion detection technology, how to reduce feature dimensions and reduce redundant information is the key to improve the detection accuracy. To solve this problem, this paper proposes a new feature selection method SIFWA for intrusion detection based on improved fireworks algorithm. SIFWA optimized and improved the selection strategy of fireworks algorithm, which adopted the selection strategy based on fitness value to screen the next generation of fireworks, which could greatly improve the ability of fireworks algorithm to find the optimal solution and search efficiency to select more effective features for intrusion detection. Simulation experiments were conducted using UCI data. Simulation results show that SIFWA has higher detection accuracy than the benchmark algorithm.