基于IHS_RELM的网络安全态势预测方法

发布时间：2018-06-04 20:50

本文选题：和声搜索算法 + 正则极速学习机　；参考：《计算机科学》2013年11期

【摘要】：针对网络安全态势感知中的态势预测问题,提出一种基于IHS_RELM的网络安全态势预测方法。对和声搜索算法的原理进行了研究,在此基础上提出一种改进的和声搜索算法。将正则极速学习机(RELM)嵌入到改进的和声搜索算法(IHS)的目标函数计算过程中,利用IHS算法的全局搜索能力来优化选取RELM的输入权值和隐含层阈值,在一定程度上提升了RLLM的学习能力和泛化能力。仿真实验表明,与已有的其他预测方法相比,该方法具有更好的预测效果。
[Abstract]:Aiming at the situation prediction problem in network security situation awareness, a network security situation prediction method based on IHS_RELM is proposed. The principle of harmonic search algorithm is studied, and an improved harmony search algorithm is proposed. The regular extreme learning machine (RELM) is embedded into the objective function calculation of the improved harmony search algorithm (IHS). The global search ability of the IHS algorithm is used to optimize the selection of the input weights and hidden layer thresholds of the RELM. To some extent, it improves the learning ability and generalization ability of RLLM. Simulation results show that this method has better prediction effect than other existing prediction methods.
【作者单位】：辽宁工程技术大学软件学院;中国传媒大学计算机学院;
【基金】：国家自然科学基金(61103199)资助
【分类号】：TP393.08

【参考文献】