计算机应用研究2017，Vol.34Issue(12)：3749-3752,4.DOI:10.3969/j.issn.1001-3695.2017.12.052
基于连接数据分析和OSELM分类器的网络入侵检测系统
Network intrusion detection system based on connection data analysis and OSELM classifier
摘要
Abstract
For the problem of real-time network intrusion detection,this paper proposed a network intrusion detection system (IDS) based on network connection data analysis and online sequential extreme learning machine (OSELM) classifier.First,it analyzed the network connection data in the intrusion database and selected the optimal feature subset by the feature selection algorithm.Then,it executed a iterative implementation of cross-validation,and through the Alpha profile to reduce the sample size so as to reduce the complexity 9f the subsequent classifier calculation.Finally,it trained the OSELM classifier by using the optimized sample feature set to construct a real-time network intrusion detection system.Experimental results on the NSL-KDD and DARPA database show that the proposed IDS has a high detection rate and a low false alarm rate,and the detection time is short,which meets the requirements of real-time intrusion detection.关键词
入侵检测系统/网络连接数据/特征选择/在线贯序极限学习机/Alpha剖析Key words
intrusion detection system/network connection data/feature selection/online sequential extreme learning machine/Alpha profile分类
信息技术与安全科学引用本文复制引用
安尼瓦尔·加马力,亚森·艾则孜,木尼拉·塔里甫..基于连接数据分析和OSELM分类器的网络入侵检测系统[J].计算机应用研究,2017,34(12):3749-3752,4.基金项目
国家自然科学基金资助项目(61762086) （61762086）
国家社会科学基金资助项目(13CFX055) （13CFX055）
新疆维吾尔自治区高校科研计划重点项目(XJEDU20161052) （XJEDU20161052）
