基于特征选取和样本选择的网络入侵检测

为了获得更加理想的网络入侵检测结果, 针对网络入侵特征选取和样本选择问题, 提出一种基于特征选取和样本选择的网络入侵检测模型. 首先提取网络入侵特征, 并进行归一化处理, 然后采用核主成分分析选择入侵特征, 并对样本进行选择, 最后采用极限学习机建立网络入侵检测分类器, 并采用KDD Cup99数据集进行仿真实验. 仿真结果表明, 本文模型得到了理想的网络入侵检测结果, 检测率超过95%以上, 入侵检测效率可以满足网络安全实际应用要求.

Network Intrusion Detection Based on Features Selecting and Samples Selecting

In order to obtain a more ideal network intrusion detection results, according to the network intrusion feature selection and sample selection problem, this paper proposes a network intrusion detection model based on features selecting and samples selecting. Firstly, the features of network intrusion are extracted, and normalized, and secondly kernel principal component analysis is used to select intrusion features, and the samples are selection, finally, extreme learning machine is used to set up network intrusion detection classifier, and the simulation experiments are carried out with KDD Cup99 data. The simulation results show that that the proposed model has been better network intrusion detection results, the detection rate is above 95%, the efficiency of intrusion detection can meet the requirements of network security protection.