随着计算机网络的不断发展,网络信息安全成为人们越来越关注的一个方面。人侵检测是提高网络信息安全的一个重要手段。为了提高入侵检测的效率,文中在提出了一种基于隶属关系不确定的模糊聚类算法。该算法在迭代过程中为目标函数创建了一个不确定性隶属度和一个相对性隶属度,使样本中的元素不仅仅局限于一个聚类。通过在数据集上的实验,验证了该算法在数据挖掘入侵检测中的检测率高于一般的K均值算法和模糊聚类算法。证明该方法在模糊事件的情况下,会提高正确的聚类结果。
With the continuous development of computer network, network security has become increasingly important aspect. Intrusion detection is an important means to improve the network information security. In order to improve the efficiency of intrusion detection, pos- sible membership degree and uncertainty membership degree are introduced in this paper. The algorithm makes the elements in the sample are not only releated to cluster. By the experiments on dataset testify the detection rate of this algorithm is higer than K-means and FCM algorithm. The method demonstrated in fuzzy event can improve the correct clustering results.