基于DBN实现QSSVM模型的WSN数据异常检测
Wireless Sensor Network Anomaly Detection of QSSVM Model Based on DBN
谷军闪1
作者信息
- 1. 河南科技职业大学 信息工程学院,河南 周口 46600
- 折叠
摘要
无线传感器网络(Wireless Sensor Network,WSN)数据异常处理效率保障了现在智能的高效率运行.在分析1/4 超球面支持向量机(Quarter-Sphere support vector machines,QSSVM)测试模型的基础上,进行深度信念网络(Deep Belief Network,DBN)构建实现,设计了一种可以实现在线测试功能的异常检测算法.研究结果表明:随着窗口大小的增加,所需要的计算时间增多.QSSVM在窗口开始扩大时便产生变化,主要表现在准确度的持续提高.QSSVM检测性能随着样本维度不断升高得到较大提升,相反K-means的检测性能却有降低趋势.采用QSSVM算法处理560 维HAR数据时,测试结果显示检测率高达 94.16%.该研究能够满足大规模高维传感器的数据处理需求,具有很高的应用价值.
Abstract
Wireless Sensor Network(WSN)data exception processing efficiency guarantees the high efficiency of intelligent operation.On the basis of analyzing the test model of Quarter-Sphere support vector machines(QSS-VM),the Deep Belief Network(DBN)is constructed and implemented.This paper designs an anomaly detection algorithm which can realize online test function.The results show that the computing time increases with the in-crease of window size.QSSVM changes as the window begins to expand,mainly in the form of continuous improve-ment in accuracy.The detection performance of QSSVM is greatly improved with the continuous increase of sample dimensions,while the detection performance of K-means has a decreasing trend.When QSSVM algorithm is used to process 560 dimensional HAR data,the test results show that the detection rate is as high as 94.16%.The re-search can meet the data processing requirements of large-scale high dimensional sensors and has high application value.
关键词
传感器网络/数据异常/深度信念网络/超球面支持向量机Key words
sensor network/abnormal data/deep belief network/hyperspherical support vector machine引用本文复制引用
基金项目
河南省高等学校重点科研项目(22A470005)
出版年
2024
NETL
NSTL
维普
万方数据