基于MCS-RELM的网络安全态势预测模型

发布时间：2018-06-13 10:25

本文选题：网络安全态势 + 正则极限学习机　；参考：《科技通报》2017年11期

【摘要】：为了提高网络安全态势的预测准确性,提出一种改进布谷鸟搜索算法和正则极限学习机相融合的网络安全态势预测模型。首先将一维的网络安全态势数据重构成多维时间序列,然后将训练样本集输入到正则极限学习机进行学习,并采用改进布谷鸟搜索算法优化输入权值和隐含层阈值,建立网络安全态势预测模型,最后采用Honeynet数据集对模型性能进行测试。结果表明,相对于其它网络安全态势预测模型,本文模型可更加准确描述网络安全态势的变化趋势,不仅提高了网络安全态势预测准确性,而且加快了建模速度,可以满足网络安全态势在线预测要求。
[Abstract]:In order to improve the accuracy of network security situation prediction, an improved cuckoo search algorithm and a regular limit learning machine are proposed to predict the network security situation. Firstly, the one-dimensional network security situation data is reconstituted into multi-dimensional time series, then the training sample set is input to the regular extreme learning machine for learning, and the improved cuckoo search algorithm is used to optimize the input weights and hidden layer thresholds. Finally, Honeynet dataset is used to test the performance of the model. The results show that compared with other network security situation prediction models, this model can more accurately describe the changing trend of network security situation, not only improve the accuracy of network security situation prediction, but also accelerate the modeling speed. It can meet the requirement of online prediction of network security situation.
【作者单位】：成都航空职业技术学院机电工程学院;四川师范大学计算机学院;
【基金】：国家自然科学基金项目(编号61373163) 四川省教育厅重点项目(编号17ZA0020)
【分类号】：TP393.08

【相似文献】