一种基于粒子群优化和核极限学习机的入侵检测算法

针对网络入侵检测准确率低、误报率高的问题，本文提出了一种基于粒子群优化和极限学习机的入侵检测算法。粒子群优化算法(PSO)是一种群智能算法，核极限学习机(KELM)是一种学习速度快、泛化能力强的经典核机器学习的方法，但是极限学习机对核函数及参数的选择直接影响它的分类性能。本文算法中利用粒子群算法优化核极限学习机的核参数，采用学习能力强且线性组合泛化能力强的全局性核函数，形成了多核极限学习机，可以有效提高单核极限学习机（ELM）分类器的性能。最后通过实验对算法性能做了对比分析，实验结果验证了本文算法的有效性。

The Algorithm of Intrusion Detection Based on PSO and Kernel Extreme Learning Machine

Aiming at solving the problems of low accuracy and high false alarm rate for network intrusion detection, an algorithm of intrusion detection based on PSO and kernel Extreme learning is proposed in this paper. Particle Swarm Optimization (PSO) is a kind of swarm intelligent algorithm. Kernel extreme learning machine (KELM) is a kind of classical kernel machine learning method with fast learning speed and strong generalization ability, but the selection of kernel function and parameters of KELM directly affects its classification performance. In this paper, PSO is used to optimize the kernel parameters of kernel limit learning machine. The global kernel function with strong generalization ability of linear combination and the local kernel function with strong learning ability are used to form multi-core limit learning machine, which can improve the performance of single core Extreme Learning Machine (ELM) classifier. Finally, the performance of the algorithm is compared and analyzed through experiments, and the experimental results verify the effectiveness of the algorithm.