一种混合入侵检测模型

为了提高入侵检测模型的准确率,提出一种基于K-均值算法、朴素贝叶斯分类算法和反向传播神经网络的混合入侵检测模型。首先,采用基于分区、无监督式聚类分析的K-均值算法进行数据的聚类处理,得到易于被机器处理和学习的数据集。为了进一步获取必要的数据属性,将聚类处理的结果输入到贝叶斯分类器进行分类。然后,具有较短学习周期的反向传播神经网络负责训练数据分类样本。最后,基于KDD CUP99数据集,对混合入侵检测模型进行了仿真实验,实验结果表明,通过混合入侵检测模型,DoS、U2R、R2L和Probe等入侵数据被精准地检测出。相比其它入侵检测模型,混合入侵检测模型取得了较高的准确率和召回率,以及较低的误报率,具有一定的实用价值。     

Molecular simulation of adsorption and intrusion in nanopores

This paper reports Monte Carlo simulations of the adsorption or intrusion in cylindrical silica nanopores. All the pores are opened at both ends towards an external bulk reservoir, so that they mimic real materials for which the confined fluid is always in contact with the external phase. This realistic model allows us to discuss the nature of the filling and emptying mechanisms. The adsorption corresponds to the metastable nucleation of the liquid phase, starting from a partially filled pore (a molecular thick film adsorbed at the pore surface). On the other hand, the desorption occurs through the displacement at equilibrium of a gas/liquid hemispherical interface (concave meniscus) along the pore axis. The intrusion of the non-wetting fluid proceeds through the invasion in the pore of the liquid/gas interface (convex meniscus), while the extrusion consists of the nucleation of the gas phase within the pore. In the case of adsorption, our simulation data are used to discuss the validity of the modified Kelvin equation (which is corrected for both the film adsorbed at the pore surface and the curvature effect on the gas/liquid surface tension).