Abnormal event detection scheme based on compressive sensing and GM(1,1) in Wireless Sensor Networks

针对现有的异常事件检测算法准确率低和能量开销较大等问题,该文提出一种基于压缩感知(CS)和GM(1,1) 的异常事件检测方案。首先,基于分簇的思想将传感器节点的数据进行压缩采样后传输至Sink,针对传感器网络中数据稀疏度未知的特点,提出一种基于步长自适应的块稀疏信号重构算法。然后,Sink基于CM(1,1)对节点发生的异常进行预测,并对节点的工作状态进行自适应调整。仿真实验结果表明,相比于其它异常检测算法,该算法的误警率和漏检率较低,在保证异常事件检测可靠性的同时,有效地节省了节点能量。

[1]  Ren C. Luo,et al.  Mobile Sensor Node Deployment and Asynchronous Power Management for Wireless Sensor Networks , 2012, IEEE Transactions on Industrial Electronics.

[2]  Chi-Tsun Cheng,et al.  A Delay-Aware Data Collection Network Structure for Wireless Sensor Networks , 2011, IEEE Sensors Journal.

[3]  Pramod K. Varshney,et al.  Target Localization in Wireless Sensor Networks Using Error Correcting Codes , 2013, IEEE Trans. Inf. Theory.

[4]  Jiankun Hu,et al.  Scalable Hypergrid k-NN-Based Online Anomaly Detection in Wireless Sensor Networks , 2013, IEEE Transactions on Parallel and Distributed Systems.

[5]  Yonina C. Eldar,et al.  Block-Sparse Signals: Uncertainty Relations and Efficient Recovery , 2009, IEEE Transactions on Signal Processing.

[6]  Zhifeng Zhao,et al.  Distributed anomaly event detection in wireless networks using compressed sensing , 2011, 2011 11th International Symposium on Communications & Information Technologies (ISCIT).

[7]  Yang Xiao,et al.  Anomaly Detection Based Secure In-Network Aggregation for Wireless Sensor Networks , 2013, IEEE Systems Journal.