粗糙集在无线传感器网络安全中的应用研究

Application of rough sets in wireless sensor networks security

为了解决当前无线传感器网络安全问题,针对入侵类型多样性,首先将粗糙集引入到无线传感器网络特征约简中,发现特征数据之前的关系,消除特征集中无相关或者影响较小特征,减少分类器输入向量数,降低计算复杂度,然后采用支持向量机对无线传感器入侵检测进行非线性建模与分类,并采用狼群算法对分类器的参数进行优化和选择,最后采用具体数据对算法的性能进行检验。实验结果表明,本文算法提高了无线传感器网络安全性,获得了较高的无线传感器网络入侵检测率,降低了误警率,增强了无线传感器网络防御各种攻击的能力。

In order to solve the security problems in the wireless sensor network and intrusion has diversity,firstly,rough set was introduced to the wireless sensor network feature reduction to found the relationship features in data and eliminate the no relevant or less affected features to reduce input vector numbers of classifier,the computation complexity is reduced,and secondly,support vector machine is used to nonlinear model and classify wireless sensor intrusion,and g the parameters of the classifier are optimized by wolves algorithm,finally the performance of specific data is used to test the performance of algorithm. Simulation results show that the proposed algorithm can improve the security in wireless sensor networks and obtain higher intrusion detection rate,reduce the false alarm rate,enhance the ability of defense against attacks.