变异粒子群优化的BP神经网络在入侵检测中的应用
发布时间：2019-01-20 19:33
【摘要】：针对入侵检测系统的自主学习性、实时性,提出带变异算子的粒子群优化方法,并用该方法优化BP神经网络以加快其收敛速度,提出了MPSO_BP混合优化算法.为提高入侵检测系统的检测率、降低误报率,提出了一种新的入侵检测模型(MPBIDS).采取Iris数据集对3个BP神经网络进行模拟实验,结果表明,优化后的BP神经网络具有更好的收敛速度和精度.将改进的BP神经网络应用到入侵检测中,采取KDDCUP99为测试数据集,仿真结果表明,基于改进BP神经网络的入侵检测模型能提高检测率、降低误报率.
[Abstract]:Aiming at the autonomous learning and real-time performance of intrusion detection system, a particle swarm optimization method with mutation operator is proposed, and the BP neural network is optimized to speed up its convergence. A hybrid MPSO_BP optimization algorithm is proposed. In order to improve the detection rate of intrusion detection system and reduce false alarm rate, a new intrusion detection model (MPBIDS). Is proposed. Three BP neural networks are simulated with Iris data sets. The results show that the optimized BP neural networks have better convergence speed and accuracy. The improved BP neural network is applied to intrusion detection and KDDCUP99 is used as the test data set. The simulation results show that the improved BP neural network based intrusion detection model can improve the detection rate and reduce the false alarm rate.
【作者单位】： 广西大学计算机与电子信息学院;河北化工医药职业技术学院信息工程系;
【基金】：国家自然科学基金资助项目(60963022)
【分类号】：TP393.08
[Abstract]:Aiming at the autonomous learning and real-time performance of intrusion detection system, a particle swarm optimization method with mutation operator is proposed, and the BP neural network is optimized to speed up its convergence. A hybrid MPSO_BP optimization algorithm is proposed. In order to improve the detection rate of intrusion detection system and reduce false alarm rate, a new intrusion detection model (MPBIDS). Is proposed. Three BP neural networks are simulated with Iris data sets. The results show that the optimized BP neural networks have better convergence speed and accuracy. The improved BP neural network is applied to intrusion detection and KDDCUP99 is used as the test data set. The simulation results show that the improved BP neural network based intrusion detection model can improve the detection rate and reduce the false alarm rate.
【作者单位】： 广西大学计算机与电子信息学院;河北化工医药职业技术学院信息工程系;
【基金】：国家自然科学基金资助项目(60963022)
【分类号】：TP393.08
【参考文献】
相关期刊论文 前3条
1 陶新民;王妍;赵春晖;刘玉;;双尺度协同变异的离散粒子群算法[J];哈尔滨工程大学学报;2011年12期
2 刘俊芳;高岳林;;带自适应变异的量子粒子群优化算法[J];计算机工程与应用;2011年03期
3 肖立中;邵志清;马汉华;王秀英;刘刚;;网络入侵检测中的自动决定聚类数算法[J];软件学报;2008年08期
【共引文献】
相关期刊论文 前10条
1 杨栩;尤学一;季民;潘留明;王秀朵;赵乐军;;城市绿地土壤入渗模型及参数确定[J];城市环境与城市生态;2011年06期
2 李燕楠;包广清;;基于小波包和支持向量机的电能质量扰动识别[J];电力科学与工程;2012年03期
3 韩力;辛懋;罗辞勇;;基于粒子群优化算法的永磁直流电动机设计[J];重庆大学学报;2009年05期
4 王永林;王东云;;织物变形舒适性的双群粒子群聚类研究[J];纺织学报;2010年04期
5 付玲生;文凯;陈小洪;;基于模糊C-均值聚类的认知无线电网络信道选择[J];广东通信技术;2011年11期
6 于海涛;李梓;王振福;方晶;;入侵检测相关技术的研究[J];智能计算机与应用;2013年02期
7 岳阳;;基于BP神经网络的计算机网络安全评估[J];电脑知识与技术;2013年18期
8 郭歆莹;张建康;穆晓敏;张U，
本文编号：2412332
本文链接：https://www.wllwen.com/guanlilunwen/ydhl/2412332.html
