一种联合时域和空域残差的网络异常检测与节点定位方法
Detection and Localization of Outlier Nodes in Wireless Sensor Networks via Jointing Temporal and Spatial Residuals
查看参考文献18篇
|
文摘
|
无线传感器网络中,有效检测网络异常并定位异常节点是确保数据可靠性的前提.传统的基于图信号处理的网络异常检测和异常节点定位方法无法兼顾检测性能和定位性能.为克服此缺点,提出了一种联合图信号时域和空域残差的网络异常检测与节点定位方法.首先,建立一个基于历史数据相关性和节点距离的图信号模型.接着,联合图信号高频分量的时域残差和空域残差实现网络异常检测.然后,利用图信号时域残差把传感器节点分成两组.在分组过程中,通过最大化有序残差分组间的均值差将异常节点划分到同一组.最后,判定具有较大残差值分组的传感器节点为异常节点.基于全球海平面压力和温度数据的仿真结果表明了所提方法的有效性.针对异常节点海平面压力误差为4 kPa、温度误差为5 ℃和3 ℃的三种情况,与双通道图滤波方法相比,所提方法的检测概率提高了至少20%,正确定位率提高了至少15%. |
|
其他语种文摘
|
In wireless sensor networks(WSNs), detecting the occurrence of abnormal behaviors and localizing the outlier nodes effectively are the premise for ensuring the reliability of collected data. Traditional detection and localization methods based on graph signal processing cannot achieve high performance in detection and localization simultaneously. To overcome this drawback, this work proposed a detection and localization method which jointly taken advantage of both temporal and spatial residuals of graph signals. Firstly, a graph model based on the correlations of historical data and the distances among nodes was established, and temporal and spatial residuals of high-frequency graph components were employed to detect network anomalies. Then, sensor nodes were divided into two groups using temporal residuals of graph signals, and the nodes in the group with larger temporal residuals were identified as outlier nodes. Numerical simulations based on the data sets of sea level pressure and surface temperature are provided to demonstrate the superior performance of the proposed method. Compared with the two-channel graph filtering method, the proposed method improves the performance by at least 20% in detection probability and 15% in outlier positioning rate, for the cases with an abnormal error of sea level pressure of 4 kPa and abnormal errors of temperature of 5 ℃ and 3 ℃. |
|
来源
|
电子学报
,2023,51(5):1172-1178 【核心库】
|
|
DOI
|
10.12263/DZXB.20220910
|
|
关键词
|
无线传感器网络
;
图信号
;
异常节点
;
时域残差
;
空域残差
;
检测与定位
|
|
地址
|
宁波大学信息科学与工程学院, 浙江, 宁波, 315200
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
浙江省杰出青年科学基金
;
浙江省宁波市自然科学基金重点项目
|
|
文献收藏号
|
CSCD:7598313
|
参考文献 共
18
共1页
|
|
1.
Liang W. Relay node placement in wireless sensor networks: From theory to practice.
IEEE Transactions on Mobile Computing,2021,20(4):1602-1613
|
CSCD被引
1
次
|
|
|
|
|
2.
Sheng B. Outlier detection in sensor networks.
Proceedings of the 8th ACM International Symposium on Mobile Ad Hoc Networking and Computing,2007:219-228
|
CSCD被引
2
次
|
|
|
|
|
3.
Palpanas T. Distributed deviation detection in sensor networks.
ACM Sigmod Record,2003,32(4):77-82
|
CSCD被引
12
次
|
|
|
|
|
4.
Liu H. Clustering with outlier removal.
IEEE Transactions on Knowledge and Data Engineering,2021,33(6):2369-2379
|
CSCD被引
1
次
|
|
|
|
|
5.
Yang Z. Distributed online outlier detection in wireless sensor networks using ellipsoidal support vector machine.
Ad Hoc Networks,2013,11(3):1062-1074
|
CSCD被引
6
次
|
|
|
|
|
6.
Yu S. Hyperspectral anomaly detection based on low-rank representation using local outlier factor.
IEEE Geoscience and Remote Sensing Letters,2020,18(7):1279-1283
|
CSCD被引
1
次
|
|
|
|
|
7.
Ramakrishna R. Grid-graph signal processing(Grid-GSP): A graph signal processing framework for the power grid.
IEEE Transactions on Signal Processing,2021,69:2725-2739
|
CSCD被引
1
次
|
|
|
|
|
8.
Sandryhaila A. Discrete signal processing on graphs: frequency analysis.
IEEE Transactions on Signal Processing,2014,62(12):3042-3054
|
CSCD被引
22
次
|
|
|
|
|
9.
蒋俊正. 一种新的无线传感器网络中异常节点检测定位算法.
电子与信息学报,2018,40(10):2358-2364
|
CSCD被引
9
次
|
|
|
|
|
10.
Ma M. Malfunction detection and localization algorithm for wireless sensor network.
Circuits Systems and Signal Processing,2021,4:501-509
|
CSCD被引
1
次
|
|
|
|
|
11.
Xiao Z. Distributed nonlinear polynomial graph filter and its output graph spectrum: filter analysis and design.
IEEE Transactions on Signal Processing,2021,69:1725-1739
|
CSCD被引
1
次
|
|
|
|
|
12.
Yang G. Efficient node selection strategy for sampling bandlimited signals on graphs.
IEEE Transactions on Signal Processing,2021,69:5815-5829
|
CSCD被引
1
次
|
|
|
|
|
13.
Domingos J. Graph Fourier transform: A stable approximation.
IEEE Transactions on Signal Processing,2020,68:4422-4437
|
CSCD被引
3
次
|
|
|
|
|
14.
Jiang J. Nonsubsampled graph filter banks: Theory and distributed algorithms.
IEEE Transactions Signal Processing,2017,67(15):3938-3953
|
CSCD被引
3
次
|
|
|
|
|
15.
Jiang J. Theory and design of joint time-vertex nonsubsampled filter banks.
IEEE Transactions on Signal Processing,2021,69(99):1968-1982
|
CSCD被引
5
次
|
|
|
|
|
16.
Chen J.
Parametric Statistical Change Point Analysis with Applications to Genetics, Medicine, and Finance. 2nd ed,2011
|
CSCD被引
1
次
|
|
|
|
|
17.
Kistler R.
Sea level pressure, 1948-2010,2020
|
CSCD被引
1
次
|
|
|
|
|
18.
NOAA Physical Sciences Laboratory.
Sea surface temperature(SST),2020
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问