Intrusion detection model based on GA-ELM
Chen Chen, Bo Yang, Xiaoyan Ye, Lintao Yang · 2022
Aiming at the low detection rate of traditional machine learning methods when dealing with massive intrusion data, this paper proposes an intrusion detection model based on genetic algorithm optimization extreme learning machine (GA-ELM). The original network data is normalized, and the data is intrusion detected by ELM. Aiming at the problem that ELM’s detection performance is greatly affected by parameter selection, first, appropriate parameters are selected for GA. Then the input weight and hidden layer bias of ELM are optimized by GA. And an intrusion detection model is established. The simulation experiment is carried out on NSL-KDD data set. The experimental results show that GA-ELM has high detection efficiency and the overall performance is greatly improved.