基于卡尔曼滤波和相关系数的异常检测方法  

Anomaly detection approach based on Kalman filtering and correlation coefficient

作　　者：肖政宏[1] 蒋岩[2] 

机构地区：[1]广东技术师范学院计算机科学学院,广东广州510665 [2]哈尔滨工业大学航天学院,黑龙江哈尔滨150001

出　　处：《计算机工程与设计》2009年第10期2401-2403,共3页Computer Engineering and Design

基　　金：国家自然科学基金项目(60573127);湖南省自然科学基金项目(05JJ40098)

摘　　要：由于安全问题是无线传感器网络应用面临的重要挑战之一,提出了一种基于卡尔曼滤波和相关系数相结合的异常入侵检测方法,该方法首先对正常情况下无线传感器网络节点的流量应用卡尔曼滤波进行预测,然后根据传感器节点的流量预测序列和实际流量序列的相关系数变化来进行异常检测。该算法具有能量有效、轻量级、可用性的特点。实验结果表明了该方法的有效性。Security is one of the key problems in wireless sensor networks （WSN） applications, so an anomaly detection approach is proposed based on Kalman filtering and correlation coefficient, firstly the method of Kalman filtering is applied to predict the traffic of WSN nodes in normal, then correlation coefficient of traffic prediction series and real traffic series of WSN nodes is used to identify anomalous nodes. This method has some characteristics such as energy efficiency, lightweight, availability. Experimental results demonstrate the efficiency of the proposed approach.

关 键 词：无线传感器网络 卡尔曼滤波 流量预测 相关系数 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]