基于网络流量变化特征的物联网非法入侵检测研究  

Research on Illegal Intrusion Detection of Internet of Things Based on Change Characteristics of Network Traffic

作　　者：包乌云毕力格 BAO Wuyunbilige(School of Intelligent Manufacturing and Information Engineering,Shaanxi Energy Institute,Xianyang 712000 China)

机构地区：[1]陕西能源职业技术学院智能制造与信息工程学院,陕西咸阳712000

出　　处：《自动化技术与应用》2024年第8期105-108,共4页Techniques of Automation and Applications

基　　金：陕西能源职业技术学院科学研究计划项目(2022KY18KJPQN);陕西能源职业技术学院《人工智能与信息工程教师教学创新团队》成果;陕西能源职业技术学院《低碳清洁能源与智能制造科研创新团队》成果(2021KYTD06);陕西省《通风技术与安全管理(智慧矿山运维与管理)省级双高专业群》建设项目成果。

摘　　要：针对当前物联网非法入侵检测过程中存在的问题,为了获得更加理想的物联网非法入侵检测结果,提出基于网络流量变化特征的物联网非法入侵检测方法。首先采集物联网流量数据,并对网络流量数据展开预处理,聚类分析网络流量数据信息,然后利用滑动窗口采样技术提取特征数据信息,运用增量计算的方法进一步分析特征信息,最后将特征信息输入到TCM-KNN算法的二类分类器,对其展开判断,完成物联网非法入侵的检测。实验结果表明,所提方法的物联网非法入侵检测正确率高、效率高、精准度高、稳定性高、性能好。Aiming at the problems existing in the current illegal intrusion detection process of the Internet of Things,in order to obtain more ideal illegal intrusion detection results of the Internet of Things,this paper proposes an illegal intrusion detection method of the Internet of Things based on the characteristics of network traffic changes.First,it collects the traffic data of the Internet of Things,and then preprocesses the network traffic data,clusters and analyzes the network traffic data information,and then uses the sliding window sampling technology to extract the characteristic data information,The method of incremental calculation is used to further analyze the feature information.Finally,the feature information is input into the second class classifier of TCM-KNN algorithm to judge it and complete the detection of illegal intrusion of the Internet of Things.The experimental results show that the method in this paper has high accuracy,high efficiency,high accuracy,high stability and good performance.

关 键 词：流量变化特征 聚类 滑动窗口 非法入侵 TCM-KNN算法 物联网 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术]