| PSO—RBF在网络入侵检测识别系统中的应用 |
| |
| 引用本文： | 蔡仲博.PSO—RBF在网络入侵检测识别系统中的应用[J].太原大学学报,2010,11(4):132-134. |
| |
| 作者姓名： | 蔡仲博 |
| |
| 作者单位： | [1]太原科技大学计算机科学与技术学院,山西太原030024 [2]太原电力高等专科学校,山西太原030013 |
| |
| 摘 要： | 针对RBF的参数选取的局限性造成检测效率低下的情况，提出一种PSO-RBF的算法，使用粒子群优化算法对RBF中权值、中心和方差三组参数进行优化设置，使三组参数的选择更加符合实际情况，提高了检测效率。将PSO-RBF算法应用到网络入侵检测识别系统中，结果表明该算法具有很好的检测率以及误报率，同时实验也证实了算法的可行性。
|
| 关 键 词： | 粒子群优化算法 径向基神经网络 网络入侵 |
Network Intrusion Detection Based on PSO-RBF |
| |
| CAI Zhong-bo.Network Intrusion Detection Based on PSO-RBF[J].Journal of Taiyuan University,2010,11(4):132-134. |
| |
| Authors: | CAI Zhong-bo |
| |
| Institution: | CAI Zhong-bo ( 1. Taiyuan University of Science and Technology, Computer Science and Technology Institute, Taiyuan 030024, China; 2. Taiyuan Higher Electrical Institute, Taiyuan 030013, China) |
| |
| Abstract: | Because the limitations on parameter selection of RBF cause low detection efficiency, a PSO-RBF algorithm is proposed. Three sets of parameters including weights, the center and variance are optimized by the particle swarm optimization algorithm and they are closed to the practicality, then the detection efficiency is improved. When the algorithm is applied to network intrusion detection and recognition system, the result shows that the performance on detection ration and false alarm ration is well and the experiment further confirms the feasibility of the algorithm |
| |
| Keywords: | PSO RBF Intrusion detection |
| 本文献已被 维普 万方数据 等数据库收录！ |
