基于特征模糊聚类的物联网节点异常检测方法  

An Anomaly Detection Method Based On Feature Fuzzy Clustering for Internet of Things Nodes

作　　者：谭超[1] 叶勇健[1] TAN Chao;YE Yong-jian(Xiamen Huatian International Vocation Institute, Xiamen 361102, China)

机构地区：[1]厦门华天涉外职业技术学院,福建厦门361102

出　　处：《南京工程学院学报（自然科学版）》2020年第3期20-23,共4页Journal of Nanjing Institute of Technology(Natural Science Edition)

基　　金：福建省教育厅中青年教师教育科研项目(JAT191587)。

摘　　要：针对物联网环境中通过传感器装置采集到的数据容易受到外界因素的影响、造成数据传输不准确、产生异常数据的问题,开展对物联网节点异常检测方法的研究.通过物联网节点异常特征数据采集、节点异常概率检测,提出一种基于特征模糊聚类的物联网节点异常检测方法.通过对比试验证明,该方法与传统检测方法相比能够有效降低检测结果的漏检率,完整地对物联网环境中的节点异常进行检测,并且得到更加理想的效果,维护物联网中数据的安全传输.In the environment of the Internet of things,the data acquired from sensor devices is more likely to be affected by external factors,causing inaccuracy of transmission data and abnormal data.To address such problems,this paper attempts to study the abnormal detection method of IoT(Internet of Things)nodes of Internet of things.Through the abnormal feature data collection of IoT nodes and the detection of node anomaly probability,an abnormal detection method of IoT nodes based on feature fuzzy clustering is proposed.Through comparative experiments,it is proved that compared with traditional detection methods,this method can effectively reduce the missed detection rate of detection results,completely detect node abnormalities in the Internet of Things environment,and achieve more ideal results,and maintain the security of data in the Internet of things transmission.

关 键 词：特征模糊聚类 物联网 节点 异常检测 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]