移动通信网络异常信号优化识别研究
|
摘要
对移动通信网络异常信号进行准确识别,可以提高移动通信网络运行的安全性。进行异常信号识别时,需要提取移动通信网络异常信号数据特征,对根据特征对异常信号数据进行分类,建立移动通信网络异常信号识别模型,而传统基于遗传神经网络算法,是通过对大量的网络信号样本信息进行训练及测试实现的,不能对异常信号数据特征进行准确提取,存在识别不准确、误差大的问题。提出基于DFI的移动通信网络异常信号的识别方法。将DFI技术与SVM算法相融合,引入到移动通信网络异常信号的识别分类问题中,获取移动通信网络异常信号数据的特性,利用SVM算法建立移动通信网络异常信号最优分类面,构建移动通信网络异常信号识别模型,基于SVM的控制模块,对移动通信网络异常信号进行识别控制。仿真结果表明,提出的移动通信网络异常信号识别模型具有较高的识别准确度。
This article proposes a method for identifying abnormal signals in mobile communication networks based on DFI.We combined the DFI technology with SVM algorithm,and introduced it into identification and classification of abnormal signals to obtain characteristic of abnormal signal data.The SVM algorithm was used to establish optimal classification face of abnormal signal.A mobile recognition model for abnormal signal was built to control and identify it based on control module of SVM.Simulation results show that the proposed model has higher recognition accuracy.
This article proposes a method for identifying abnormal signals in mobile communication networks based on DFI.We combined the DFI technology with SVM algorithm,and introduced it into identification and classification of abnormal signals to obtain characteristic of abnormal signal data.The SVM algorithm was used to establish optimal classification face of abnormal signal.A mobile recognition model for abnormal signal was built to control and identify it based on control module of SVM.Simulation results show that the proposed model has higher recognition accuracy.
引文
[1]王春枝,张会丽,叶志伟.基于混沌粒子群算法和小波SVM的移动通信网络流量识别方法[J].计算机科学,2015,42(10):117-121.
[2]张治斌,谭静.基于K均值与决策树的移动通信网络流量识别研究[J].计算机工程与设计,2014,35(3):798-802.
[3]樊郁徽,徐宁.基于移动通信网络僵尸主机网络行为的检测与监控方案设计[J].重庆文理学院学报(社会科学版),2014,33(2):99-103.
[4]王炜,程东年,马海龙.基于趋势感知协议指纹的Skype加密流量识别算法[J].计算机应用研究,2015,32(1):183-186.
[5]高长喜,吴亚飚,王枞.基于抽样分组长度分布的加密流量应用识别[J].通信学报,2015,36(9):65-75.
[6]谭静,张治斌.基于混合特征的移动通信网络流量识别方法[J].计算机仿真,2014,31(3):316-319.
[7]钱亚冠,张曼.基于过抽样技术的移动通信网络流量识别方法[J].电信科学,2014,30(4):109-113.
[8]孙瑜玲,林勤花.基于遗传神经网络的移动通信网络流量识别系统[J].现代电子技术,2015,17(38):117-120.
[9]王铭鑫,周华春,陈佳,张宏科.一种SDN中基于熵值计算的异常流量检测方法[J].电信科学,2015,31(9):83-89.
[10]单外平,曾雪琼.基于深度信念网络的信号重构与轴承故障识别[J].电子设计工程2016,4(24):67-71.
[11]王秋平,舒勤,黄宏光.关于交通流量数据预测建模研究[J].计算机仿真,2016,33(2):194-197.
[2]张治斌,谭静.基于K均值与决策树的移动通信网络流量识别研究[J].计算机工程与设计,2014,35(3):798-802.
[3]樊郁徽,徐宁.基于移动通信网络僵尸主机网络行为的检测与监控方案设计[J].重庆文理学院学报(社会科学版),2014,33(2):99-103.
[4]王炜,程东年,马海龙.基于趋势感知协议指纹的Skype加密流量识别算法[J].计算机应用研究,2015,32(1):183-186.
[5]高长喜,吴亚飚,王枞.基于抽样分组长度分布的加密流量应用识别[J].通信学报,2015,36(9):65-75.
[6]谭静,张治斌.基于混合特征的移动通信网络流量识别方法[J].计算机仿真,2014,31(3):316-319.
[7]钱亚冠,张曼.基于过抽样技术的移动通信网络流量识别方法[J].电信科学,2014,30(4):109-113.
[8]孙瑜玲,林勤花.基于遗传神经网络的移动通信网络流量识别系统[J].现代电子技术,2015,17(38):117-120.
[9]王铭鑫,周华春,陈佳,张宏科.一种SDN中基于熵值计算的异常流量检测方法[J].电信科学,2015,31(9):83-89.
[10]单外平,曾雪琼.基于深度信念网络的信号重构与轴承故障识别[J].电子设计工程2016,4(24):67-71.
[11]王秋平,舒勤,黄宏光.关于交通流量数据预测建模研究[J].计算机仿真,2016,33(2):194-197.