[author_cn_name].[cn_title][J].空军工程大学学报,[year_id],[volume]([issue]):[start_page]-[end_page] 基于Stacking集成学习的网络安全态势预测方法-Research on Network Security Situation Prediction Method Based on Stacking Integrated Learning
文章摘要
曹波,李成海,宋亚飞,陈晨.基于Stacking集成学习的网络安全态势预测方法[J].空军工程大学学报,2022,23(5):101-107
基于Stacking集成学习的网络安全态势预测方法
Research on Network Security Situation Prediction Method Based on Stacking Integrated Learning
  
DOI:
中文关键词: 态势预测  集成学习  粒子群算法  卷积神经网络  循环神经网络
英文关键词: situation prediction  integrated learning  particle swarm algorithms  convolutional neural network  recurrent neural network
基金项目:国家自然科学基金(62002362;61703426);陕西省高校科协青年人才托举计划(2019038);陕西省创新能力支持计划(2020KJXX-065)
作者单位
曹波,李成海,宋亚飞,陈晨 空军工程大学防空反导学院西安710051 
摘要点击次数: 60
全文下载次数: 55
中文摘要:
      针对现有的网络安全态势预测模型预测精确度低且泛化能力差等问题,提出一种基于Stacking模型融合的态势预测方法。该方法中,借助Stacking算法将TCN网络、WaveNet、GRU、LSTM进行集成挖掘态势数据之间的相关性;之后利用逻辑回归进行预测得到最终态势值;利用粒子群优化算法进行参数寻优,提升模型性能。基于2个数据集进行验证,实验表明,所提预测方法具有较小的均方误差和平均绝对误差,收敛速度较快,拟合度均可达0.999,可以很好解决预测精确度低的问题,提升了模型的泛化能力。
英文摘要:
      To address the problem of low prediction accuracy of existing network security posture prediction models, a prediction method based on Stacking model fusion is proposed. In this method, the TCN network, WaveNet, GRU, and LSTM are integrated with the Stacking algorithm to explore the correlation among the situational data; after that, logistic regression is used to further predict the final situational values; the particle swarm optimization algorithm is used to optimize the parameters and improve the model performance. Based on two data sets for validation, the experiments show that the proposed prediction method has small mean square error and mean absolute error, fast convergence speed, and the fit degree can reach 0.999, which can well solve the problem of low prediction accuracy.
查看全文   查看/发表评论  下载PDF阅读器
关闭