基于分层的体域网异常数据检测方法  

Hierarchical anomaly data detection method for body area networks

作　　者：廖栋森 祝长鸿 余琪琦 任君玉[2] 黄福莹[1,2] 覃团发 LIAO Dong-sen;ZHU Chang-hong;YU Qi-qi;REN Jun-yu;HUANG Fu-ying;QIN Tuan-fa(School of Computer and Electronic Information,Guangxi University,Nanning 530004,China;Guangxi Key Laboratory of Multimedia Communications and Network Technology,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004 [2]广西大学多媒体通信与网络技术重点实验室,广西南宁530004

出　　处：《计算机工程与设计》2024年第1期197-203,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(61761007)。

摘　　要：针对无线体域网(wireless body area network,WBAN)异常数据检测方法忽视人体异常数据的连续性,缺乏异常数据集检测等问题,提出一种基于Hampel滤波器和DBSCAN分层的WBAN异常数据检测方法。根据时间相关性利用Hampel滤波器检测异常数据点,保证数据的连续性,使用改进的基于滑动时间窗的DBSCAN算法,检测异常数据集。实验结果表明,所提方法和其它方法相比,实现了分层的异常数据检测,在保证检测精度的同时准确标注出了异常数据集,具有空间复杂度小的优势。Aiming at the problems that the wireless body area network(WBAN)abnormal data detection method ignores the continuity of human abnormal data and lacks abnormal data set detection,a hierarchical WBAN abnormal data detection method based on Hampel filter and DBSCAN was proposed.According to the time correlation,Hampel filter was used to detect abnormal data points to ensure the continuity of data,and the improved DBSCAN algorithm based on sliding time windows was used to detect abnormal data sets.Simulation results show that compared with other methods,the proposed method achieves hierarchical abnormal data detection,and accurately marks the abnormal data set while ensuring the detection accuracy.

关 键 词：无线体域网 异常检测 分层 聚类 连续性 时间窗 检测 

分 类 号：TP393.1[自动化与计算机技术—计算机应用技术]