检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:于光华[1] 夏魁良[1] YU Guanghua;XIA Kuiliang(Department of Computer Science and Information Engineering,Heihe University,Heihe 164300,China)
机构地区:[1]黑河学院,黑龙江黑河164300
出 处:《激光杂志》2021年第1期154-158,共5页Laser Journal
基 金:黑龙江省教育厅基本科研业务费项目(No.2019-KYYWF-0462)。
摘 要:采用以往入侵检测方法时,通过随机方式对参数进行初始化处理,检测精度低,为此,提出一种基于布谷鸟算法的光纤激光网络异质信息入侵检测方法。分析了布谷鸟算法寻优过程,针对常规布谷鸟算法受参数改变的影响相对较大,具有收敛速度慢、准确率低以及容易陷入局部最优的弊端,依据差分进化方法,通过在新鸟巢位置公式中结合别的鸟巢位置完成简易交叉变异,提升种群多样性,同时利用惯性权重减少迭代次数,保证整体寻优速度。对光纤激光网络异质信息入侵的历史数据进行采集,提取关键特征,通过布谷鸟算法对极限学习机进行改进,获取最优入侵检测分类器,通过分类器构建异质信息入侵检测模型,实现光纤激光网络异质信息入侵检测。实验结果表明,所提方法收敛速度快,误报率低且入侵检测精度高。In the past intrusion detection methods,parameters are initialized by random ways,and the detection accuracy is low.Therefore,a novel intrusion detection method based on cuckoo algorithm for heterogeneous information in optical fiber laser network is proposed.This paper analyzes the optimization process of cuckoo algorithm.In view of the disadvantages of conventional cuckoo algorithm,which is relatively affected by parameter changes,such as slow convergence speed,low accuracy and easy to fall into local optimization,according to the differential evolution method,by combining the new nest location formula with other nest locations to complete simple cross variation,improve population diversity,and reduce inertia weight at the same time.The number of iterations ensures the overall optimization speed.The historical data of heterogeneous information intrusion in optical fiber laser network is collected,the key features are extracted,the limit learning machine is improved by cuckoo algorithm,the optimal intrusion detection classifier is obtained,and the heterogeneous information intrusion detection model is constructed by the classifier to realize heterogeneous information intrusion detection in optical fiber laser network.The experimental results show that the proposed method has fast convergence speed and high intrusion detection accuracy.
分 类 号:TN91[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15